The Community for Technology Leaders
Green Image
TABLE OF CONTENTS
ISSN: 0162-8828
COMMENTS

The Cues in "Dependent Multiple Cue Integration for Robust Tracking" are Independent (Abstract)

Ido Leichter , Technion - Israel Institute of Technology, Haifa
Michael Lindenbaum , Technion - Israel Institute of Technology, Haifa
Ehud Rivlin , Technion - Israel Institute of Technology, Haifa
Papers

Design and Evaluation of More Accurate Gradient Operators on Hexagonal Lattices (Abstract)

Tetsuo Shima , Tokyo Institute of Technology, Meguro-ku
Suguru Saito , Tokyo Institute of Technology, Meguro-ku
Masayuki Nakajima , Tokyo Institute of Technology, Meguro-ku

Linear Dependency Modeling for Classifier Fusion and Feature Combination (Abstract)

Andy J. Ma , Hong Kong Baptist University, Hong Kong
Pong C. Yuen , Hong Kong Baptist University, Kowloon
Jian-Huang Lai , Sun Yat-Sen University, Guangzhou

Linear Dependency Modeling for Classifier Fusion and Feature Combination (Abstract)

Andy J. Ma , Hong Kong Baptist University, Hong Kong
Pong C. Yuen , Hong Kong Baptist University, Kowloon
Jian-Huang Lai , Sun Yat-Sen University, Guangzhou

Contextualized Trajectory Parsing with Spatio-Temporal Graph (Abstract)

Xiaobai Liu , Huazhong University of Science Technology, China and University of California at Los Angeles, Los Angeles
Liang Lin , Sun Yat-sen University, Guangzhou
Hai Jin , Huazhong University of Science Technology, China
REGULAR PAPERS

Feature Coding in Image Classification: A Comprehensive Study (Abstract)

Yongzhen Huang , Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing
Zifeng Wu , Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing
Liang Wang , Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing
Tieniu Tan , Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing

Automatic Alignment of Genus-Zero Surfaces (Abstract)

Patrice Koehl , University of California, Davis, Davis
Joel Hass , University of California, Davis, Davis
Papers

A Markov Random Field Groupwise Registration Framework for Face Recognition (Abstract)

Shu Liao , The Hong Kong University of Science and Technology, Hong Kong
Dinggang Shen , The University of North Carolina at Chapel Hill, Chapel Hill
Albert C. S. Chung , The Hong Kong University of Science and Technology, Hong Kong
REGULAR PAPERS

Attribute-Based Classification for Zero-Shot Learning of Object Categories (Abstract)

Christoph H. Lampert , IST Austria, Klosterneuburg
Hannes Nickisch , Philips Research, Hamburg
Stefan Harmeling , Max Planck Institute for Intelligent Systems, Tübingen

On the Role of Correlation and Abstraction in Cross-Modal Multimedia Retrieval (Abstract)

Jose Costa Pereira , University of California, San Diego, La Jolla
Emanuele Coviello , University of California, San Diego, La Jolla
Gabriel Doyle , University of California, San Diego, La Jolla
Nikhil Rasiwasia , Yahoo! Labs, Bangalore
Gert R.G. Lanckriet , University of California, San Diego, La Jolla
Roger Levy , University of California, San Diego, La Jolla
Nuno Vasconcelos , University of California, San Diego, La Jolla

Variational Light Field Analysis for Disparity Estimation and Super-Resolution (Abstract)

Sven Wanner , Heidelberg Collaboratory for Image Processing (HCI), Heidelberg
Bastian Goldluecke , Heidelberg Collaboratory for Image Processing (HCI), Heidelberg

Tensor Sparse Coding for Positive Definite Matrices (Abstract)

Ravishankar Sivalingam , University of Minnesota, Twin Cities, Minneapolis
Daniel Boley , University of Minnesota, Twin Cities, Minneapolis
Vassilios Morellas , University of Minnesota, Twin Cities, Minneapolis
Nikos Papanikolopoulos , University of Minnesota, Twin Cities, Minneapolis

Good Practice in Large-Scale Learning for Image Classification (Abstract)

Zeynep Akata , Xerox Research Centre Europe, Meylan and INRIA Rhone-Alpes, Montbonnot
Florent Perronnin , Xerox Research Centre Europe, Meylan
Zaid Harchaoui , INRIA Rhone-Alpes, Montbonnot
Cordelia Schmid , INRIA Rhone-Alpes, Montbonnot

Animated Pose Templates for Modelling and Detecting Human Actions (Abstract)

Benjamin Yao , University of California, Los Angeles, Los Angeles
Zicheng Liu , Microsoft Research, Redmond
Xiaohan Nie , University of California, Los Angeles, Los Angeles
Song-Chun Zhu , University of California, Los Angeles , Los Angeles

Retrieval-based Face Annotation by Weak Label Regularized Local Coordinate Coding (Abstract)

Dayong Wang , Nanyang Technological University, Singapore
Steven C.H. Hoi , Nanyang Technological University, Singapore
Ying He , Nanyang Technological University, Singapore
Jianke Zhu , Zhejiang University, Hangzhou
Tao Mei , Microsoft Research Asia, Beijing
Jiebo Luo , University of Rochester, Rochester

Fast and Scalable Approximate Spectral Matching for Higher-Order Graph Matching (Abstract)

Soonyong Park , Samsung Advanced Institute of Technology (SAIT), Yongin-si
Sung-Kee Park , Korea Institute of Science and Technology (KIST), Seoul
Martial Hebert , Carnegie Mellon University, Pittsburgh
Papers

Learning Nonlinear Functions Using Regularized Greedy Forest (Abstract)

Rie Johnson , RJ Research Consulting, Tarrytown
Tong Zhang , Rutgers University
REGULAR PAPERS

Online Multiple Kernel Similarity Learning for Visual Search (Abstract)

Hao Xia , Nanyang Technological University, Singapore
Steven C.H. Hoi , Nanyang Technological University, Singapore
Rong Jin , Michigan State University, East Lansing
Peilin Zhao , Nanyang Technological University, Singapore

Scene Particles: Unregularized Particle Based Scene Flow Estimation (Abstract)

Simon Hadfield , University of Surrey, Guildford
Richard Bowden , University of Surrey, Guildford
Papers

Virtual and Real World Adaptation for Pedestrian Detection (Abstract)

David Vazquez , Universitat Autònoma de Barcelona (UAB) Computer Vision Center (CVC), Bellaterra Bellaterra
Antonio M. Lopez , Universitat Autònoma de Barcelona (UAB) Computer Vision Center (CVC), Bellaterra Bellaterra
Javier Marin , Computer Vision Center (CVC), Bellaterra
Daniel Ponsa , Universitat Autònoma de Barcelona (UAB), Bellaterra
David Geronimo , Computer Vision Center, Bellaterra (Cerdanyola)
REGULAR PAPERS

Simultaneous Tensor Decomposition and Completion Using Factor Priors (Abstract)

Yi-Lei Chen , National Tsing Hua University, Hsinchu
Chiou-Ting Candy Hsu , National Tsing Hua University, Hsinchu
Hong-Yuan Mark Liao , Academia Sinica, Taipei and National Chiao Tung University, Hsinchu
Papers

Automatic Upright Adjustment of Photographs with Robust Camera Calibration (Abstract)

Hyunjoon Lee , Pohang University of Science and Technology (POSTECH), Pohang
Eli Shechtman , Creative Technologies Lab of Adobe Research, Seattle
Jue Wang , Creative Technologies Lab of Adobe Research, Seattle
Seungyong Lee , Pohang University of Science and Technology (POSTECH), Pohang

Associative Hierarchical Random Fields (Abstract)

L'ubor Ladický , ETH Zurich, Zurich
Chris Russell , University College London, London
Pushmeet Kohli , Microsoft Research, Cambridge
Philip H. S. Torr , Oxford Brookes University, Oxford

Learning with Augmented Features for Supervised and Semi-supervised Heterogeneous Domain Adaptation (Abstract)

Wen Li , Nanyang Technological University, Singapore
Lixin Duan , Institute for Infocomm Research, Singapore
Dong Xu , Nanyang Technological University, Singapore
Ivor W. Tsang , Nanyang Technological University, Singapore

Exemplar-Based Colour Constancy and Multiple Illumination (Abstract)

Hamid Reza Vaezi Joze , Simon Fraser University, Burnaby
Mark S. Drew , Simon Fraser University, Burnaby

A Geometric Particle Filter for Template-Based Visual Tracking (Abstract)

Junghyun Kwon , TeleSecurity Sciences, Inc., Las Vegas
Hee Seok Lee , Seoul National University, Seoul
Frank C. Park , Seoul National University, Seoul
Kyoung Mu Lee , Seoul National University, Seoul

Online Learning and Sequential Anomaly Detection in Trajectories (Abstract)

Rikard Laxhammar , University of Skövde and Saab AB, Skövde
Göran Falkman , University of Skövde, Skövde

3D Traffic Scene Understanding from Movable Platforms (PDF)

Andreas Geiger , MPI for Intelligent Systems in Tübingen and Karlsruhe Institute of Technology, Karlsruhe
Martin Lauer , Karlsruhe Institute of Technology, Karlsruhe
Christian Wojek , Carl Zeiss Corporate Research, Saarbrücken
Christoph Stiller , Karlsruhe Institute of Technology, Karlsruhe
Raquel Urtasun , Toyota Technological Institute at Chicago, Chicago

Support Vector Machine Classifier with Pinball Loss (Abstract)

Xiaolin Huang , KU Leuven, Leuven
Lei Shi , Fudan University, Shanghai
Johan A.K. Suykens , KU Leuven, Leuven

Geodesic Mapping for Dynamic Surface Alignment (Abstract)

Tony Tung , Kyoto University, Kyoto
Takashi Matsuyama , Kyoto University, Kyoto

Iterative Discovery of Multiple Alternative Clustering Views (Abstract)

Donglin Niu , Northeastern University, Boston
Jennifer G. Dy , Northeastern University, Boston
Michael I. Jordan , University of California Berkeley, Berkeley

Robust Text Detection in Natural Scene Images (Abstract)

Xu-Cheng Yin , University of Science and Technology Beijing, Beijing
Xuwang Yin , University of Science and Technology Beijing, Beijing
Kaizhu Huang , Xi'an Jiaotong-Liverpool University, Suzhou
Hong-Wei Hao , Institute of Automation, Chinese Academy of Sciences, Beijing

Gaussian Process-Mixture Conditional Heteroscedasticity (Abstract)

Emmanouil A. Platanios , Imperial College London, London
Sotirios P. Chatzis , Cyprus University of Technology, Limassol

Learning Pullback HMM Distances (Abstract)

Fabio Cuzzolin , Oxford Brookes University, Oxford
Michael Sapienza , Oxford Brookes University, Oxford

Bayesian Nonparametric Methods for Partially-Observable Reinforcement Learning (Abstract)

Finale Doshi-Velez , MIT, Cambridge
David Pfau , Columbia University, New York
Frank Wood , University of Oxford, Oxford
Nicholas Roy , MIT, Cambridge

Robust Recovery of Corrupted Low-rank Matrix by Implicit Regularizers (Abstract)

Ran He , Institute of Automation, Chinese Academy of Sciences, Beijing
Tieniu Tan , Institute of Automation, Chinese Academy of Sciences, Beijing
Liang Wang , Institute of Automation, Chinese Academy of Sciences, Beijing

Semi-Supervised Kernel Mean Shift Clustering (Abstract)

Saket Anand , Rutgers University, Piscataway
Sushil Mittal , Scibler Technologies, Bangalore
Oncel Tuzel , Mitsubishi Electric Research Laboratories, Cambridge
Peter Meer , Rutgers University, Piscataway

Hardware-Efficient Bilateral Filtering for Stereo Matching (Abstract)

Qingxiong Yang , City University of Hong Kong, Hong Kong
COMMENTS
Papers

Jointly Learning Visually Correlated Dictionaries for Large-scale Visual Recognition Applications (Abstract)

Ning Zhou , University of North Carolina at Charlotte, Charlotte
Jianping Fan , University of North Carolina at Charlotte, Charlotte

Scaling Multidimensional Inference for Structured Gaussian Processes (Abstract)

Elad Gilboa , Washington University in St. Louis, St. Louis
Yunus Saatçi , University of Cambridge, Cambridge
John P. Cunningham , Washington University in St. Louis, St. Louis

Relating Things and Stuff via Object Property Interactions (Abstract)

Min Sun , University of Washington, Seattle
Byung-soo Kim , University of Michigan, Ann Arbor
Pushmeet Kohli , Microsoft Research Cambridge, Cambridge
Silvio Savarese , Stanford University, Stanford

Transform-Invariant PCA: A Unified Approach to Fully Automatic Face Alignment, Representation, and Recognition (Abstract)

Weihong Deng , Beijing University of Posts and Telecommunications, Beijing
Jiani Hu , Beijing University of Posts and Telecommunications, Beijing
Jiwen Lu , Advanced Digital Sciences Center, Singapore
Jun Guo , Beijing University of Posts and Telecommunications, Beijing

Bi-polynomial Modeling of Low-frequency Reflectances (Abstract)

Boxin Shi , University of Tokyo, Tokyo
Ping Tan , National University of Singapore, Singapore
Yasuyuki Matsushita , Microsoft Research Asia, Beijing
Katsushi Ikeuchi , University of Tokyo, Tokyo

Learning Categories from Few Examples with Multi Model Knowledge Transfer (Abstract)

Tatiana Tommasi , KU Leuven, Leuven, ESAT-PSI and iMinds, Belgium
Francesco Orabona , Toyota Technological Institute at Chicago, Chicago
Barbara Caputo , University of Rome La Sapienza, Rome

Stereo Time-of-Flight with Constructive Interference (Abstract)

Victor Castaneda , Technische Universitaet Muenchen, Munich
Diana Mateus , CAMP-TUM and Helmholtz Zentrum, Munich
Nassir Navab , CAMP-TUM and ICBM, Faculty of Medicine, University of Chile

2D Affine and Projective Shape Analysis (Abstract)

Darshan Bryner , Naval Surface Warfare Center Panama City Division, Panama City and Florida State University, Tallahassee
Eric Klassen , Florida State University, Tallahassee
Huiling Le , University of Nottingham, Nottingham
Anuj Srivastava , Florida State University, Tallahassee

Learning Actionlet Ensemble for 3D Human Action Recognition (Abstract)

Jiang Wang , Northwestern University, Evanston
Zicheng Liu , Microsoft Research Redmond, Redmond
Ying Wu , Northwestern University, Evanston
Junsong Yuan , Nanyang Technological University, Singapore

What Makes a Photograph Memorable? (Abstract)

Phillip Isola , Massachusetts Institute of Technology, Cambridge
Jianxiong Xiao , Massachusetts Institute of Technology, Cambridge
Devi Parikh , Virginia Polytechnic Institute and State University, Blacksburg
Antonio Torralba , Massachusetts Institute of Technology, Cambridge
Aude Oliva , Massachusetts Institute of Technology, Cambridge

Bayesian Nonparametric Models for Multiway Data Analysis (Abstract)

Zenglin Xu , Purdue University, West Lafayette
Feng Yan , Facebook and Purdue University, West Lafayette
Yaun Qi , Purdue University, West Lafayette

Domain Anomaly Detection in Machine Perception: A System Architecture and Taxonomy (Abstract)

Josef Kittler , University of Surrey, Guildford
William Christmas , University of Surrey, Guildford
Teo de Campos , University of Surrey, Guildford
David Windridge , University of Surrey, Guildford
Fei Yan , University of Surrey, Guildford
John Illingworth , University of Surrey, Guildford
Magda Osman , Queen Mary, University of London, London

Multi-Commodity Network Flow for Tracking Multiple People (Abstract)

Horesh Ben Shitrit , École Polytechnique Fédérale de Lausanne, Lausanne
Jérôme Berclaz , Microsoft, Sunnyvale and École Polytechnique Fédérale de Lausanne, Lausanne
François Fleuret , Idiap Research Institute, Martigny and École Polytechnique Fédérale de Lausanne, Lausanne
Pascal Fua , École Polytechnique Fédérale de Lausanne, Lausanne

Negative Binomial Process Count and Mixture Modeling (Abstract)

Mingyuan Zhou , University of Texas at Austin, Austin
Lawrence Carin , Duke University, Durham

Modeling Non-Gaussian Time Series with Nonparametric Bayesian Models (Abstract)

Zhiguang Xu , The Ohio State University, Columbus
Steven MacEachern , The Ohio State University, Columbus
Xinyi Xu , The Ohio State University, Columbus

Shape Analysis of Planar Multiply-connected Objects using Conformal Welding (Abstract)

Lok Ming Lui , The Chinese University of Hong Kong, Hong Kong
Wei Zeng , Florida International University, Miami
Shing-Tung Yau , Harvard University, Cambridge
Xianfeng Gu , Stony Brook University at Stony Brook, Stony Brook

Multiple Kernel Learning for Visual Object Recognition: A Review (Abstract)

Serhat S. Bucak , Michigan State University, East Lansing
Rong Jin , Michigan State University, East Lansing
Anil K. Jain , Michigan State University, East Lansing and Korea University, Seoul

Web Image Re-ranking Using Query-Specific Semantic Signatures (Abstract)

Xiaogang Wang , The Chinese University of Hong Kong, Hong Kong
Shi Qiu , The Chinese University of Hong Kong, Hong Kong
Ke Liu , The Chinese University of Hong Kong, Hong Kong
Xiaoou Tang , The Chinese University of Hong Kong, Hong Kong and Shenzhen Institutes of Advanced Technology, CAS

Graduated NonConvexity and Concavity Procedure for Partial Graph Matching (Abstract)

Zhi-Yong Liu , Institute of Automation, Chinese Academy of Sciences, Beijing
Hong Qiao , Institute of Automation, Chinese Academy of Sciences, Beijing

Multimodal Similarity-Preserving Hashing (Abstract)

Jonathan Masci , Istituto Dalle Molle di Studi sull'Intelligenza Artificiale (IDSIA), Manno
Michael M. Bronstein , Università della Svizzera Italiana, Lugano
Alexander M. Bronstein , Tel Aviv University, Tel Aviv and Intel Semiconductor, Israel
Jürgen Schmidhuber , Istituto Dalle Molle di Studi sull'Intelligenza Artificiale (IDSIA), Manno

Are Gibbs-Type Priors the Most Natural Generalization of the Dirichlet Process? (Abstract)

Pierpaolo De Blasi , University of Torino and Collegio Carlo Alberto, Italy
Stefano Favaro , University of Torino and Collegio Carlo Alberto, Italy
Antonio Lijoi , University of Pavia and Collegio Carlo Alberto, Italy
Ramsés H. Mena , Universidad Autónoma de México, México
Igor Prünster , University of Torino and Collegio Carlo Alberto, Italy
Matteo Ruggiero , University of Torino and Collegio Carlo Alberto, Italy

Tracking by Sampling and Integrating Multiple Trackers (Abstract)

Junseok Kwon , Seoul National University, Seoul
Kyoung Mu Lee , Seoul National University, Seoul

Preserving Structure in Model-Free Tracking (Abstract)

Lu Zhang , Delft University of Technology, Delft
Laurens van der Maaten , Delft University of Technology, Delft

Soft Biometrics; Human Identification using Comparative Descriptions (Abstract)

Daniel A. Reid , University of Southampton, Southampton
Mark S. Nixon , University of Southampton, Southampton
Sarah V. Stevenage , University of Southampton, Southampton

Understanding Collective Activities of People from Videos (Abstract)

Wongun Choi , NEC Laboratories, USA
Silvio Savarese , Stanford University, Stanford

A Survey of Non-Exchangeable Priors for Bayesian Nonparametric Models (Abstract)

Nicholas J. Foti , University of Washington, Seattle
Sinead A. Williamson , University of Texas at Austin, Austin

Mixtures of Shifted Asymmetric Laplace Distributions (Abstract)

Brian C. Franczak , University of Guelph, Guelph
Ryan P. Browne , University of Guelph, Guelph
Paul D. McNicholas , University of Guelph, Guelph

The Sum-over-Forests Density Index: Identifying Dense Regions in a Graph (Abstract)

Mathieu Senelle , Université catholique de Louvain (UCL), Belgium
Silvia Garcia-Diez , Université catholique de Louvain (UCL), Belgium
Amin Mantrach , Yahoo! Labs, Barcelona
Masashi Shimbo , Nara Institute of Science and Technology, Takayama
Marco Saerens , Université catholique de Louvain (UCL), Belgium
François Fouss , Université catholique de Louvain (UCL), Belgium

Automatic and Accurate Shadow Detection using Near-Infrared Information (Abstract)

Dominic Rüfenacht , Ecole Polytechnique Fédérale de Lausanne (EPFL), Lausanne
Clément Fredembach , Ecole Polytechnique Fédérale de Lausanne (EPFL), Lausanne
Sabine Süsstrunk , Ecole Polytechnique Fédérale de Lausanne (EPFL), Lausanne

Visual Tracking: An Experimental Survey (PDF)

Arnold W. M. Smeulders , University of Amsterdam, Amsterdam
Dung M. Chu , University of Amsterdam, Amsterdam
Rita Cucchiara , University of Modena and Reggio Emilia, Modena
Simone Calderara , University of Modena and Reggio Emilia, Modena
Afshin Dehghan , University of Central Florida, Orlando
Mubarak Shah , University of Central Florida, Orlando

From Bits to Images: Inversion of Local Binary Descriptors (Abstract)

Emmanuel d'Angelo , Advanced Silicon S.A., Lausanne
Laurent Jacques , Université catholique de Louvain UCL), Louvain
Alexandre Alahi , Stanford University, Stanford
Pierre Vandergheynst , Ecole Polytechnique Fédérale de Lausanne, Lausanne

Fast Exact Search in Hamming Space with Multi-Index Hashing (Abstract)

Mohammad Norouzi , University of Toronto, Toronto
Ali Punjani , University of Toronto, Toronto
David J. Fleet , University of Toronto, Toronto

Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments (PDF)

Catalin Ionescu , Institute of Mathematics of the Romanian Academy, Bucharest and University of Bonn, Bonn
Dragos Papava , Institute of Mathematics of the Romanian Academy, Bucharest
Vlad Olaru , Institute of Mathematics of the Romanian Academy, Bucharest
Cristian Sminchisescu , Lund University, Lund and Institute of Mathematics of the Romanian Academy, Bucharest

As-Projective-As-Possible Image Stitching with Moving DLT (Abstract)

Julio Zaragoza , The University of Adelaide, Adelaide
Tat-Jun Chin , The University of Adelaide, Adelaide
Quoc-Huy Tran , The University of Adelaide, Adelaide
Michael S. Brown , National University of Singapore, Singapore
David Suter , The University of Adelaide, Adelaide

On-line Video Event Detection by Constraint Flow (Abstract)

Suha Kwak , POSTECH, Pohang
Bohyung Han , POSTECH, Pohang
Joon Hee Han , POSTECH, Pohang

Structured Time Series Analysis for Human Action Segmentation and Recognition (Abstract)

Dian Gong , University of Southern California, Los Angeles
Gérard Medioni , University of Southern California, Los Angeles
Xuemei Zhao , University of Southern California, Los Angeles

Segmentation of Moving Objects by Long Term Video Analysis (Abstract)

Peter Ochs , University of Freiburg, Freiburg
Jitendra Malik , University of California at Berkeley, Berkeley
Thomas Brox , University of Freiburg, Freiburg

Camera Localization using Trajectories and Maps (Abstract)

Raúl Mohedano , Universidad Politécnica de Madrid, Madrid
Andrea Cavallaro , Queen Mary University of London, London
Narciso García , Universidad Politécnica de Madrid, Madrid

Unsupervised Adaptation Across Domain Shifts By Generating Intermediate Data Representations (Abstract)

Raghuraman Gopalan , AT&T Labs-Research, Middletown
Ruonan Li , Harvard University, Cambridge
Rama Chellappa , University of Maryland, College Park

"Clustering by Composition" - Unsupervised Discovery of Image Categories (Abstract)

Alon Faktor , The Weizmann Institute of Science, Rehovot
Michal Irani , The Weizmann Institute of Science, Rehovot

Object Tracking by Oversampling Local Features (Abstract)

Federico Pernici , University of Florence, Florence
Alberto Del Bimbo , University of Florence, Florence

Measuring Crowd Collectiveness (Abstract)

Bolei Zhou , B. Zhou is with the Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, USA

Fast Exact Euclidean Distance (FEED): A New Class of Adaptable Distance Transforms (PDF)

Theo E. Schouten , Radboud University, Nijmegen
Egon L. Van den Broek , Utrecht University, Utrecht, University of Twente, Karakter University Center, Radboud University Medical Center, Nijmegen

The Hidden Sides of Names - Face Modeling With First Name Attributes (Abstract)

Huizhong Chen , H.Chen is with the Department of Electrical Engineering, Stanford University, Stanford CA 94305 USA (e-mail: hchen2@stanford.edu).

Direct Orthogonal Distance to Quadratic Surfaces in 3D (Abstract)

Gus Lott , G. Lott is with the MITRE Corporation, McLean VA 22102 USA (e-mail: glott@mitre.org).

Image Segmentation Using Higher-Order Correlation Clustering (Abstract)

Sungwoong Kim , S. Kim is with Qualcomm Research Korea, Gangnam Gu, Seoul 135-820, South Korea (e-mail: sungwoong.kim01@gmail.com).

Contextualized Trajectory Parsing with Spatio-Temporal Graph (Abstract)

Xiaobai Liu , Huazhong University of Science Technology, China and University of California at Los Angeles, Los Angeles
Liang Lin , Sun Yat-sen University, Guangzhou
Hai Jin , Huazhong University of Science Technology, China

Distinct Multi-Colored Region Descriptors for Object Recognition (Abstract)

Naik S. Kumar , C. A. Murthy is in the Machine Intelligence Unit of Indian Statistical Institute, 203 B. T. Road, Kolkata - 700108, India. E-mail: murthy@isical.ac.in
C.A. Murthy , C. A. Murthy is in the Machine Intelligence Unit of Indian Statistical Institute, 203 B. T. Road, Kolkata - 700108, India. E-mail: murthy@isical.ac.in

Beyond Sharing Weights for Deep Domain Adaptation (Abstract)

Artem Rozantsev , CVLAB, EPFL, Lausanne, Vaud Switzerland 1015 (e-mail: artem.rozantsev@epfl.ch)
Mathieu Salzmann , IC - CVLab, EPFL, Lausanne, VD Switzerland 1015 (e-mail: mathieu.salzmann@epfl.ch)
Pascal Fua , IC CVLAB, EPFL, Lausanne, Vaud Switzerland CH-1015 (e-mail: pascal.fua@epfl.ch)

Deeply Supervised Salient Object Detection with Short Connections (Abstract)

Qibin Hou , Computer Science, Nankai University, 12538 Tianjin, Tianjin China 300071 (e-mail: andrewhoux@gmail.com)
Ming-Ming Cheng , CCCE, Nankai University, Tianjin, Tianjin China (e-mail: cmm@nankai.edu.cn)
Xiaowei Hu , Computer Science, Nankai University, 12538 Tianjin, Tianjin China 300071 (e-mail: xiaowei.hu@mail.nankai.edu.cn)
Ali Borji , Computer Science, University of Central Florida, 6243 Orlando, Florida United States (e-mail: aliborji@gmail.com)
Zhuowen Tu , Cognitive Science, University of California, San Diego, La Jolla, California United States 92093-0515 (e-mail: ztu@ucsd.edu)
Philip H.S. Torr , Department of Engineering, University of Oxford, 6396 Oxford, Oxfordshire United Kingdom of Great Britain and Northern Ireland (e-mail: philip.torr@eng.ox.ac.uk)

MonoCap: Monocular Human Motion Capture using a CNN Coupled with a Geometric Prior (Abstract)

Xiaowei Zhou , Computer Science, Zhejiang University, Hangzhou, Zhejiang China (e-mail: xzhou@cad.zju.edu.cn)
Menglong Zhu , Computer and Information Science, University of Pennsylvania, Philadephia, Pennsylvania United States (e-mail: menglong@seas.upenn.edu)
Georgios Pavlakos , Computer and Information Science, University of Pennsylvania, Philadephia, Pennsylvania United States (e-mail: pavlakos@seas.upenn.edu)
Spyridon Leonardos , Computer and Information Science, University of Pennsylvania, Philadephia, Pennsylvania United States (e-mail: spyridon@seas.upenn.edu)
Konstantinos G. Derpanis , Computer Science, Ryerson University, 7984 Toronto, Ontario Canada (e-mail: kosta@ryerson.ca)
Kostas Daniilidis , Computer Information Science, University of Pennsylvania, Philadelphia, Pennsylvania United States 19104-6389 (e-mail: kostas@cis.upenn.edu)

From Social to Individuals: a Parsimonious Path of Multi-level Models for Crowdsourced Preference Aggregation (Abstract)

Qianqian Xu , Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, Beijing China (e-mail: xuqianqian@iie.ac.cn)
Jiechao Xiong , BICMR-LMAM-LMEQF-LMP, School of Mathematical Sciences, Peking University, Beijing, Beijing China (e-mail: jcxiong@tencent.com)
Xiaochun Cao , State Key Laboratory Of Information Security, Institute of Information Engineering, Chinese Academy of Sciences, Beijing, Beijing China (e-mail: caoxiaochun@iie.ac.cn)
Qingming Huang , School of Computer and Control Engineering, University of the Chinese Academy of Sciences, 74519 Beijing, Beijing China (e-mail: qmhuang@ucas.ac.cn)
Yuan Yao , Department of Mathematics, and by courtesy, Computer Science and Engineering, Hong Kong University of Science and Technology, Hong Kong, Hong Kong Hong Kong (e-mail: yuany@math.pku.edu.cn)

High-Speed Hyperspectral Video Acquisition By Combining Nyquist and Compressive Sampling (Abstract)

Lizhi Wang , School of Computer Science, Beijing Institute of Technology, 47833 Beijing, Beijing China (e-mail: lzwang@bit.edu.cn)
Zhiwei Xiong , Electronic Engineering & Information Science, University of Science and Technology of China, Hefei, Anhui China (e-mail: zwxiong@ustc.edu.cn)
Hua Huang , School of Computer Science, Beijing Institute of Technology, Beijing, Beijing China (e-mail: huahuang@bit.edu.cn)
Guangming Shi , School of Electronic Engineering, Xidian University, Xi'an, Shaanxi China (e-mail: gmshi@xidian.edu.cn)
Feng Wu , Electronic Engineering & Information Science, University of Science and Technology of China, Hefei, Anhui China (e-mail: fengwu@ustc.edu.cn)
Wenjun Zeng , Internet Media Group, Microsoft Research Asia, Beijing, Beijing China (e-mail: wezeng@microsoft.com)

Automated Latent Fingerprint Recognition (Abstract)

Kai Cao , Computer Science and Engineering, Michigan State University, East Lansing, Michigan United States (e-mail: caokai0505@gmail.com)
Anil K. Jain , Computer Science & Engineering, Michigan State University, East Lansing, Michigan United States 48824-1226 (e-mail: jain@cse.msu.edu)

Multi-Task Structure-aware Context Modeling for Robust Keypoint-based Object Tracking (Abstract)

Xi Li , College of Computer Science, Zhejiang University, Hangzhou, Zhejiang China (e-mail: xilizju@zju.edu.cn)
Liming Zhao , College of Computer Science, Zhejiang University, Hangzhou, Zhejiang China (e-mail: zhaoliming@zju.edu.cn)
Wei Ji , College of Computer Science, Zhejiang University, Hangzhou, Zhejiang China (e-mail: jiwei@zju.edu.cn)
Yiming Wu , College of Computer Science, Zhejiang University, Hangzhou, Zhejiang China (e-mail: ymw@zju.edu.cn)
Fei Wu , College of Computer Science, Zhejiang University, Hangzhou, Zhejiang China (e-mail: wufei@zju.edu.cn)
Ming-Hsuan Yang , EECS, University of California at Merced, Merced, California United States (e-mail: mhyang@ucmerced.edu)
Dacheng Tao , Engineering and Information Technologies, University of Sydney, 4334 Sydney, New South Wales Australia (e-mail: dacheng.tao@sydney.edu.au)
Ian Reid , Department of Engineering Science, University of Oxford, Oxford, Oxon United Kingdom of Great Britain and Northern Ireland OX1 3PJ (e-mail: ian.reid@adelaide.edu.au)

Memory Efficient Max Flow for Multi-label Submodular MRFs (Abstract)

Thalaiyasingam Ajanthan , Torr Vision Group, University of Oxford Department of Engineering Science, 98956 Oxford, Oxfordshire United Kingdom of Great Britain and Northern Ireland (e-mail: ajanthan@robots.ox.ac.uk)
Richard Hartley , rubbish, Department of Systems Engineering, rubbish, jkj Timor-Leste rubbish (e-mail: richard.hartley@anu.edu.au)
Mathieu Salzmann , IC - CVLab, EPFL, Lausanne, VD Switzerland 1015 (e-mail: mathieu.salzmann@epfl.ch)

Patchmatch-based Robust Stereo Matching under Radiometric Changes (Abstract)

Jaeseung Lim , GSAIM, Seoul, Seoul Korea (the Republic of) (e-mail: wanicono@gmail.com)
Sangkeun Lee , GSAIM, Chung-Ang University, 26729 Seoul, Seoul Korea (the Republic of) (e-mail: sangkny@cau.ac.kr)

Accurate 3D Reconstruction from Small Motion Clip for Rolling Shutter Cameras (Abstract)

Sunghoon Im , Electrical Engineering, Korea Advanced Institute of Science and Technology, 34968 Daejeon, Daejeon Korea (the Republic of) 305-701 (e-mail: sunghoonim27@gmail.com)
Hyowon Ha , Electrical Engineering, Korea Advanced Institute of Science and Technology, 34968 Daejeon, Daejeon Korea (the Republic of) (e-mail: hwha@rcv.kaist.ac.kr)
Gyeongmin Choe , Electrical Engineering, Korea Advanced Institute of Science and Technology, 34968 Daejeon, Daejeon Korea (the Republic of) (e-mail: gmchoe08@gmail.com)
Hae-Gon Jeon , Electrical Engineering, KAIST, Yuseong-gu, Daejeon Korea, Republic of (e-mail: earboll@kaist.ac.kr)
Kyungdon Joo , School of EE, Korea Advanced Institute of Science and Technology, 34968 Daejeon, Daejeon Korea (the Republic of) 305-701 (e-mail: kdjoo369@gmail.com)
In So Kweon , The School of Electrical Engineering, KAIST, Daejeon, Daejeon Korea (the Republic of) (e-mail: iskweon77@kaist.ac.kr)

Ordinal Constraint Binary Coding for Approximate Nearest Neighbor Search (Abstract)

Hong Liu , Cognitive Science, Xiamen University, Xiamen, Fujian China (e-mail: lynnliu0207@163.com)
Rongrong Ji , Cognitive Science, Xiamen University, Xiamen, Fujian China 361005 (e-mail: rrji@xmu.edu.cn)
Jingdong Wang , Media Computing Group, Microsoft Research Asia, Beijing, Beijing China (e-mail: jingdw@microsoft.com)
Chunhua Shen , School of Computer Science, University of Adelaide, Adelaide, South Australia Australia (e-mail: chunhua.shen@adelaide.edu.au)

Look into Person: Joint Body Parsing & Pose Estimation Network and a New Benchmark (Abstract)

Xiaodan Liang , School of Data and Computer Science, Sun Yat-sen University, Guangzhou, Guangdong China (e-mail: xdliang328@gmail.com)
Ke Gong , Human Cyber Physical Intelligence Integration Lab, Sun Yat-Sen University, 26469 Guangzhou, Guangdong China 510275 (e-mail: kegong936@gmail.com)
Xiaohui Shen , Adobe Research, Adobe Systems Inc., San Jose, California United States 95110 (e-mail: xshen@adobe.com)
Liang Lin , School of Information Science and Technology, Sun Yat-sen University, Guangzhou, Guangdong China (e-mail: linliang@ieee.org)

Non-Negative Matrix Factorizations for Multiplex Network Analysis (Abstract)

Vladimir Gligorijevic , Computing, Imperial College London, 4615 London, England United Kingdom of Great Britain and Northern Ireland (e-mail: v.gligorijevic@imperial.ac.uk)
Yannis Panagakis , Computer Science Department, Middlesex University, 4907 London, London United Kingdom of Great Britain and Northern Ireland (e-mail: i.panagakis@imperial.ac.uk)
Stefanos P. Zafeiriou , Computing, Imperial College London, London, London United Kingdom of Great Britain and Northern Ireland SW7 2AZ (e-mail: s.zafeiriou@imperial.ac.uk)

Robust Spatio-Temporal Clustering and Reconstruction of Multiple Deformable Bodies (Abstract)

Antonio Agudo , Computer Vision and Machine Learning, Institut de Robotica i Informatica Industrial (CSIC-UPC), Barcelona, Cataluia Spain (e-mail: aagudo@iri.upc.edu)
Francesc Moreno-Noguer , Computer Vision and Machine Learning, Institut de Robotica i Informatica Industrial (CSIC-UPC), Barcelona, Cataluia Spain (e-mail: fmoreno@iri.upc.edu)

Towards Personalized Image Captioning via Multimodal Memory Networks (Abstract)

Cesc Chunseong Park , Lunit, Lunit Incorporation, SEOUL, SEOUL Korea (the Republic of) (e-mail: cspark@lunit.io)
Byeongchang Kim , Department of Computer Science and Engineering, Seoul National University, SEOUL, SEOUL Korea (the Republic of) (e-mail: byeongchang.kim@vision.snu.ac.kr)
Gunhee Kim , Computer Science and Engineering, Seoul National University, Seoul, Seoul Korea (the Republic of) 08826 (e-mail: gunhee@snu.ac.kr)

On the Reconstruction of Face Images from Deep Face Templates (Abstract)

Guangcan Mai , Computer Science, Hong Kong Baptist University, 26679 Kowloon Tong, Kowloon Hong Kong (e-mail: csgcmai@comp.hkbu.edu.hk)
Kai Cao , Computer Science and Engineering, Michigan State University, East Lansing, Michigan United States (e-mail: kaicao@cse.msu.edu)
Pong C. YUEN , Computer Science, Hong Kong Baptist University, Kowloon, Kowloon Hong Kong 9999999 (e-mail: pcyuen@comp.hkbu.edu.hk)
Anil K. Jain , Computer Science & Engineering, Michigan State University, East Lansing, Michigan United States 48824-1226 (e-mail: jain@cse.msu.edu)

Anchor-Free Correlated Topic Modeling (Abstract)

Xiao Fu , School of Electrical Engineering and Computer Science, Oregon State University, 2694 Corvallis, Oregon United States (e-mail: xiao.fu@oregonstate.edu)
Kejun Huang , Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, Minnesota United States (e-mail: huang663@umn.edu)
Nicholas D. Sidiropoulos , Department of Electrical and Computer Engineering, University of Virginia, Charlottesville, Virginia United States (e-mail: nikos@virginia.edu)
Qingjiang Shi , School of Software Engineering, Tongji University, 12476 Shanghai, Shanghai China (e-mail: qing.j.shi@gmail.com)
Mingyi Hong , Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, Minnesota United States (e-mail: mhong@umn.edu)

A graph based image interpretation method using a priori qualitative inclusion and photometric relationships (Abstract)

Jean-Baptiste Fasquel , EA4094 - Laboratory of the Automated systems Engineering, University of LUNAM-Angers, Angers, Maine et Loire France 49000 (e-mail: Jean-Baptiste.Fasquel@univ-angers.fr)
Nicolas Delanoue , EA4094 - Laboratory of the Automated systems Engineering, University of LUNAM-Angers, Angers, Maine et Loire France (e-mail: nicolas.delanoue@univ-angers.fr)

Recurrent Shape Regression (Abstract)

Zhen Cui , School of Computer Science and Engineering, Nanjing University of Science and Technology, 12436 Nanjing, Jiangsu China (e-mail: zhen.cui@vipl.ict.ac.cn)
Shengtao Xiao , Electrical and Computer Engineering, National University of Singapore Singapore, Singapore, Singapore Singapore (e-mail: xstgavin124@gmail.com)
Zhiheng Niu , Electrical and Computer Engineering, National University of Singapore, Singapore, Singapore Singapore (e-mail: niuzhiheng@gmail.com)
Shuicheng Yan , ece, NUS, sg, SG Singapore 117576 (e-mail: eleyans@nus.edu.sg)
Wenming Zheng , Research Center for Learning Science, Southeast University, Nanjing, Jiangsu China 210096 (e-mail: wenming_zheng@seu.edu.cn)

Robust 3D Human Pose Estimation from Single Images or Video Sequences (Abstract)

Chunyu Wang , Computer Science, Peking University, Beijing, Beijing China (e-mail: wangchunyu@pku.edu.cn)
Yizhou Wang , Computer Science, Peking University, Beijing, Beijing China (e-mail: Yizhou.Wang@pku.edu.cn)
Zhouchen Lin , Computer Science, Peking University, Beijing, Beijing China (e-mail: zlin@pku.edu.cn)
Alan Yuille , Statistics, University of California Los Angeles, 8783 Los Angeles, California United States (e-mail: yuille@stat.ucla.edu)

Discriminative Optimization: Theory and Applications to Computer Vision (Abstract)

Jayakorn Vongkulbhisal , Electrical and Computer Engineering, Carnegie Mellon University, 6612 Pittsburgh, Pennsylvania United States (e-mail: jvongkul@andrew.cmu.edu)
Fernando De La Torre , Robotics Institute, Carnegie Mellon, Pittsburgh, Pennsylvania United States (e-mail: ftorre@cs.cmu.edu)
Joao Paulo Costeira , ECE, Instituto de Sistemas e Robotica, Lisbon, Lisbon Portugal 1049-001 (e-mail: jpc@isr.ist.utl.pt)

Visual Dialog (Abstract)

Abhishek Das , Computer Science, Georgia Institute of Technology College of Computing, 166857 Atlanta, Georgia United States (e-mail: abhshkdz@gatech.edu)
Satwik Kottur , Electrical and Computer Engineering, Carnegie Mellon University, 6612 Pittsburgh, Pennsylvania United States (e-mail: skottur@andrew.cmu.edu)
Khushi Gupta , Electrical and Computer Engineering, Carnegie Mellon University, 6612 Pittsburgh, Pennsylvania United States (e-mail: khushig@andrew.cmu.edu)
Avi Singh , Computer Science, University of California Berkeley, 1438 Berkeley, California United States (e-mail: avisingh@cs.berkeley.edu)
Deshraj Yadav , Computer Science, Georgia Institute of Technology College of Computing, 166857 Atlanta, Georgia United States (e-mail: deshraj@gatech.edu)
Stefan Lee , Computer Science, Georgia Institute of Technology College of Computing, 166857 Atlanta, Georgia United States (e-mail: steflee@gatech.edu)
Jose Moura , Electrical and Computer Engineering, Carnegie Mellon University, 6612 Pittsburgh, Pennsylvania United States (e-mail: moura@andrew.cmu.edu)
Devi Parikh , Computer Science, Georgia Institute of Technology College of Computing, 166857 Atlanta, Georgia United States (e-mail: parikh@gatech.edu)
Dhruv Batra , Computer Science, Georgia Institute of Technology College of Computing, 166857 Atlanta, Georgia United States (e-mail: dbatra@gatech.edu)

Learning Support Correlation Filters for Visual Tracking (Abstract)

Wangmeng Zuo , Harbin Institute of Technology, School of Computer Science and Technology, Harbin, California United States (e-mail: cswmzuo@gmail.com)
Xiaohe Wu , Harbin Institute of Technology, School of Computer Science and Technology, Harbin, Heilongjiang China (e-mail: angela612@126.com)
Liang Lin , School of Information Science and Technology, Sun Yat-sen University, Guangzhou, Guangdong China (e-mail: linliang@ieee.org)
Lei Zhang , Dept. of Computing, The Hong Kong Polytechnic University, Hong Kong, Hong Kong Hong Kong N.A (e-mail: cslzhang@comp.polyu.edu.hk)
Ming-Hsuan Yang , EECS, University of California at Merced, Merced, California United States 95344 (e-mail: mhyang@ucmerced.edu)

Hedging Deep Features for Visual Tracking (Abstract)

Yuankai Qi , School of Computer Science and Technology, Harbin Institute of Technology, 47822 Harbin, Heilongjiang China (e-mail: yk.qi@hit.edu.cn)
Shengping Zhang , School of Computer Science and Technology, Harbin Institute of Technology, 47822 Weihai, Shangdong China (e-mail: s.zhang@hit.edu.cn)
Lei Qin , Institute of Computing Technology, Chinese Academy of Sciences, Beijing, Beijing China (e-mail: qinlei@ict.ac.cn)
Qingming Huang , School of Computer and Control Engineering, University of the Chinese Academy of Sciences, 74519 Beijing, Beijing China (e-mail: qmhuang@jdl.ac.cn)
Hongxun Yao , Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, Heilongjiang China (e-mail: h.yao@hit.edu.cn)
Jongwoo Lim , Computer Science and Engineering, Hanyang University, Seoul, Gyeonggi-do Korea (the Republic of) (e-mail: jlim@hanyang.ac.kr)
Ming-Hsuan Yang , EECS, University of California at Merced, Merced, California United States 95344 (e-mail: mhyang@ucmerced.edu)

What Makes Objects Similar: A Unified Multi-Metric Learning Approach (Abstract)

Han-Jia Ye , Computer Science and Technology, Nanjing University, Nanjing, Jiangsu China (e-mail: yehj@lamda.nju.edu.cn)
De-Chuan Zhan , Computer Science Department, Nanjing University, Nanjing, Jiangsu China (e-mail: zhandc@nju.edu.cn)
Yuan Jiang , Department of Computer Science & Technology, Nanjing University, Nanjing, Jiangsu China 210046 (e-mail: jiangy@lamda.nju.edu.cn)
Zhi-Hua Zhou , National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu Pronvince China 210093 (e-mail: zhouzh@nju.edu.cn)

Deep Mixture of Diverse Experts for Large-Scale Visual Recognition (Abstract)

Tianyi Zhao , CS, Charlotte, North Carolina United States (e-mail: tzhao@uncc.edu)
Qiuyu Chen , CS, UNC-Charlotte, Charlotte, North Carolina United States (e-mail: qychen@uncc.edu)
Zhenzhong Kuang , CS, UNC-Charlotte, Charlotte, North Carolina United States (e-mail: kuang@uncc.edu)
Jun Yu , CS, UNC-Charlotte, Charlotte, North Carolina United States (e-mail: junyu@uncc.edu)
Wei Zhang , CS, UNC-Charlotte, Charlotte, North Carolina United States (e-mail: weizhang@uncc.edu)
Ming He , CS, Charlotte, North Carolina United States (e-mail: heming@uncc.edu)
Jianping Fan , cs, University of North Carolina, Charlotte, North Carolina United States 28223 (e-mail: jfan@uncc.edu)

Online Data Thinning via Multi-Subspace Tracking (Abstract)

Xin Jiang Hunt , Advanced Analytics, SAS Institute Inc., Cary, North Carolina United States (e-mail: chlorisjiang@gmail.com)
Rebecca Willett , ECE, University of Wisconsin-Madison, Madison, Wisconsin United States (e-mail: willett@discovery.wisc.edu)

Regularized Diffusion Process on Bidirectional Context for Object Retrieval (Abstract)

Song Bai , Electronics and Information Engineering, Huazhong University of Science and Technology, Wuhan, Hubei China 430074 (e-mail: songbai@hust.edu.cn)
Xiang Bai , Dept. of Electronics and Information Engineering, HUST, Wuhan, Hubei China (e-mail: xbai@hust.edu.cn)
Qi Tian , Department of Computer Science, University of Texas at San Antonio, San Antonio, Texas United States 78249 (e-mail: qitian@cs.utsa.edu)
Longin Jan Latecki , Computer and Informatio Sciences, Temple University, Philadelphia, Pennsylvania United States 19122 (e-mail: latecki@temple.edu)

Detecting Regions of Maximal Divergence for Spatio-Temporal Anomaly Detection (PDF)

Bjorn Barz , Department of Mathematics and Computer Science, Friedrich-Schiller-University Jena, Jena, Thuringia Germany (e-mail: bjoern.barz@uni-jena.de)
Erik Rodner , Corporate Research and Technology, Carl Zeiss AG, 14004 Oberkochen, Baden-Wurttemberg Germany (e-mail: Erik.Rodner@uni-jena.de)
Yanira Guanche Garcia , Department of Mathematics and Computer Science, Friedrich-Schiller-University Jena, Jena, Thuringia Germany (e-mail: yanira.guanche.garcia@uni-jena.de)
Joachim Denzler , Department of Mathematics and Computer Science, Friedrich-Schiller-University Jena, Jena, Thuringia Germany (e-mail: joachim.denzler@uni-jena.de)

Efficient Registration of High-Resolution Feature Enhanced Point Clouds (Abstract)

Philipp Jauer , Institut für Robotik und Kognitive Systeme, Universität zu Lübeck, Lübeck, Schleswig-Holstein Germany 23562 (e-mail: jauer@rob.uni-luebeck.de)
Ivo Kuhlemann , Institut für Robotik und Kognitive Systeme, Universität zu Lübeck, Lübeck, Schleswig-Holstein Germany (e-mail: kuhlemann@rob.uni-luebeck.de)
Ralf Bruder , Institut für Robotik und Kognitive Systeme, Universität zu Lübeck, Lübeck, Schleswig-Holstein Germany (e-mail: bruder@rob.uni-luebeck.de)
Achim Schweikard , Institut für Robotik und Kognitive Systeme, Universität zu Lübeck, Lübeck, Schleswig-Holstein Germany (e-mail: schweikard@rob.uni-luebeck.de)
Floris Ernst , Institut für Robotik und Kognitive Systeme, Universität zu Lübeck, Lübeck, Schleswig-Holstein Germany (e-mail: ernst@rob.uni-luebeck.de)

Image Projective Invariants (Abstract)

Erbo Li , Key lab of Intelligent Information Processing, Chinese Academy of Sciences, Beijing, Beijing China (e-mail: sophialiuli@gmail.com)
Hanlin Mo , Key lab of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, Beijing China (e-mail: mohanlin@ict.ac.cn)
Dong Xu , Ambry Genetics, Aliso Viejo, California United States (e-mail: xudong0614@hotmail.com)
Hua Li , Key lab of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, Beijing China (e-mail: lihua@ict.ac.cn)

Physically-based Simulation of Cosmetics via Intrinsic Image Decomposition with Facial Priors (Abstract)

Chen Li , State Key Lab of CAD&CG, Zhejiang University, Hangzhou, Zhejiang China (e-mail: lich0622@gmail.com)
Kun Zhou , State Key Lab of CAD&CG, Zhejiang University, Hangzhou, Zhejiang China (e-mail: kunzhou@acm.org)
Hsiang-Tao Wu , Internet Graphics group, Microsoft Research Asia, Beijing, Beijing China (e-mail: musclewu@microsoft.com)
Stephen Lin , Internet Graphics group, Microsoft Research Asia, Beijing, Beijing China 100080 (e-mail: stevelin@microsoft.com)

Egocentric Meets Top-View (Abstract)

Shervin Ardeshir , Computer Science, University of Central Florida, 6243 Orlando, Florida United States 32816-2368 (e-mail: shervin.ardeshir@gmail.com)
Ali Borji , Computer Science, University of Central Florida, 6243 Orlando, Florida United States (e-mail: aliborji@gmail.com)

Aggregating Randomized Clustering-Promoting Invariant Projections for Domain Adaptation (Abstract)

Jian Liang , National Laboratory of Pattern Recognition, CRIPAC,CASIA, Beijing, Beijing China (e-mail: jian.liang@nlpr.ia.ac.cn)
Ran He , National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, Beijing China 100190 (e-mail: rhe@nlpr.ia.ac.cn)
Zhenan Sun , Center for Biometrics and Security Research, CAS Institute of Automation, Beijing, Beijing China 100190 (e-mail: znsun@nlpr.ia.ac.cn)
Tieniu Tan , NLPR, CASIA, Beijing 100080, Hunan China 100080 (e-mail: tnt@nlpr.ia.ac.cn)

Learning to Deblur Images with Exemplars (Abstract)

Jinshan Pan , Electrical Engineering and Computer Science, University of California at Merced, Merced, California United States 95344 (e-mail: sdluran@gmail.com)
Wenqi Ren , School of Computer Science and Technology, Tijian University, Tianjin, Tianjin China (e-mail: rwq.renwenqi@gmail.com)
Zhe Hu , Electrical Engineering and Computer Science, Light Co., Palo Alto, California United States (e-mail: elapse.hz@gmail.com)
Ming-Hsuan Yang , EECS, University of California at Merced, Merced, California United States 95344 (e-mail: mhyang@ucmerced.edu)

Transferring Knowledge Fragments for Learning Distance Metric from A Heterogeneous Domain (Abstract)

Yong Luo , School of Computer Science and Engineering, Nanyang Technological University, 54761 Singapore, Singapore Singapore (e-mail: yluo180@gmail.com)
Yonggang Wen , School of Computer Science and Engineering, Nanyang Technological University, Singapore, Singapore Singapore (e-mail: ygwen@ntu.edu.sg)
Tongliang Liu , The the UBTech Sydney Artificial Intelligence Institute and the School of Information Technologies in the Faculty of Engineering and Information Technologies at The University of Sydney, The University of Sydney, Sydney, New South Wales Australia (e-mail: tongliang.liu@sydney.edu.au)
Dacheng Tao , Faculty of Engineering and Information Technologies, University of Sydney, 4334 Sydney, New South Wales Australia (e-mail: dacheng.tao@sydney.edu.au)

Occlusion-aware Method for Temporally Consistent Superpixels (Abstract)

Matthias Reso , Institut fur Informationsverarbeitung, Leibniz Universitat Hannover, 26555 Hannover, Niedersachsen Germany (e-mail: reso@tnt.uni-hannover.de)
Jorn Jachalsky , Research & Innovation, Technicolor SA, 214012 Issy-les-Moulineaux, le-de-France France (e-mail: jachalsky@tnt.uni-hannover.de)
Bodo Rosenhahn , Institut fur Informationsverarbeitung, Leibniz Universitat Hannover, 26555 Hannover, Niedersachsen Germany (e-mail: rosenhahn@tnt.uni-hannover.de)
Joern Ostermann , Institut fur Informationsverarbeitung, Leibniz Universitat Hannover, 26555 Hannover, Niedersachsen Germany (e-mail: ostermann@tnt.uni-hannover.de)

Imbalanced Deep Learning by Minority Class Incremental Rectification (Abstract)

Qi Dong , EECS, Queen Mary University of London, London, England United Kingdom of Great Britain and Northern Ireland (e-mail: q.dong@qmul.ac.uk)
Shaogang Gong , EECS, Queen Mary, University of London, London, London United Kingdom of Great Britain and Northern Ireland (e-mail: s.gong@qmul.ac.uk)
Xiatian Zhu , EECS, Queen Mary University of London, London, England United Kingdom of Great Britain and Northern Ireland (e-mail: xiatian.zhu@qmul.ac.uk)

Dynamic Clustering Algorithms via Small-Variance Analysis of Markov Chain Mixture Models (Abstract)

Trevor Campbell , Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, Massachusetts United States (e-mail: tdjc@mit.edu)
Brian Kulis , Electrical and Computer Engineering, Boston University, 1846 Boston, Massachusetts United States (e-mail: bkulis@bu.edu)
Jonathan P. How , Aeronautics and Astronautics, Massachusetts Institute of Technology, Cambridge, Massachusetts United States (e-mail: jhow@mit.edu)

Unsupervised Deep Learning of Compact Binary Descriptors (Abstract)

Kevin Lin , Department of Electrical Engineering, Seattle, Washington United States (e-mail: kvlin@uw.edu)
Jiwen Lu , Department of Automation, Tsinghua University, Beijing, Beijing China 100084 (e-mail: lujiwen@tsinghua.edu.cn)
Chu-Song Chen , Insititute of Information Science, Academia Sinica, Nankang, Taipei Taiwan 115 (e-mail: song@iis.sinica.edu.tw)
Jie Zhou , Department of Automation, Tsinghua University, Beijing, Beijing China 100084 (e-mail: jzhou@tsinghua.edu.cn)
Ming-Ting Sun , Electrical Engineering, University of Washington, Seattle, Washington United States (e-mail: mts@uw.edu)

Composite Quantization (Abstract)

Jingdong Wang , Visual Computing Group, Microsoft Research Aisa, Beijing, Beijing China (e-mail: welleast@outlook.com)
Ting Zhang , Visual Computing, Microsoft Research Aisa, Beijing, Beijing China (e-mail: tinzhan@microsoft.com)

Super-Fine Attributes with Crowd Prototyping (Abstract)

Daniel Martinho-Corbishley , Vision, Learning & Control, University of Southampton Faculty of Physical Sciences and Engineering, 243732 Southampton, Hampshire United Kingdom of Great Britain and Northern Ireland SO17 1BJ (e-mail: dmc@ecs.soton.ac.uk)
Mark Nixon , Electronics and Computer Science, University of Southampton, Highfield, Southampton, SOUTHAMPTON United Kingdom of Great Britain and Northern Ireland S017 1BJ (e-mail: msn@ecs.soton.ac.uk)
John N. Carter , School of Electronics and Comptuer Science, University of Southampton, Southampton, Hampshire United Kingdom of Great Britain and Northern Ireland S017 1BJ (e-mail: jnc@ecs.soton.ac.uk)

CNN-based Real-time Dense Face Reconstruction with Inverse-rendered Photo-realistic Face Images (Abstract)

Yudong Guo , Mathematical Sciences, University of Science and Technology of China, Hefei, Anhui China (e-mail: gyd2011@mail.ustc.edu.cn)
Juyong Zhang , Mathematical Sciences, University of Science and Technology of China, Hefei, Anhui China (e-mail: juyong@ustc.edu.cn)
Jianfei Cai , School of Computer Engineering, Nanyang Technological University, Singapore, Singapore Singapore (e-mail: asjfcai@ntu.edu.sg)
Boyi Jiang , Mathematical Sciences, University of Science and Technology of China, Hefei, Anhui China (e-mail: jby1993@mail.ustc.edu.cn)
Jianmin Zheng , School of Computer Engineering, Nanyang Technological University, Singapore, Singapore Singapore 639798 (e-mail: asjmzheng@ntu.edu.sg)

Learning and selecting confidence measures for robust stereo matching (Abstract)

Min-Gyu Park , Intelligent Image Processing Research Center, Korea Electronics Technology Institute, 65362 Seongnam, Gyeonggi Korea (the Republic of) (e-mail: mpark@keti.re.kr)
Kuk-Jin Yoon , Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, 65419 Gwangju, Jeollanamdo Korea (the Republic of) (e-mail: kjyoon@kaist.ac.kr)

Monocular Depth Estimation using Multi-Scale Continuous CRFs as Sequential Deep Networks (Abstract)

Dan Xu , Department of Information Engineering and Computer Science, University of Trento, TRENTO, TRENTO Italy (e-mail: dan.xu@unitn.it)
Elisa Ricci , Technologies of Vision, Fondazione Bruno Kessler, 18466 Trento, Trentino-Alto Adige Italy (e-mail: eliricci@fbk.eu)
Wanli Ouyang , School of Electrical and Information Engineering, University of Sydney, Sydney, New South Wales Australia (e-mail: wanli.ouyang@sydney.edu.au)
Xiaogang Wang , Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, Hong Kong Hong Kong (e-mail: xgwang@ee.cuhk.edu.hk)
Nicu Sebe , Multimodal Human Understanding Group, University of Trento, Trento, Trentino Italy (e-mail: niculae.sebe@unitn.it)

A Fast Frequent Directions Algorithm for Low Rank Approximation: (Previous Title: Sparse Frequent Directions Algorithm for Low Rank Approximation) (Abstract)

Dan Teng , Mathematics, National University of Singapore, Singapore, Singapore Singapore (e-mail: tengdan@u.nus.edu)
Delin Chu , Mathematics, National University of Singapore, Singapore, Singapore Singapore (e-mail: matchudl@nus.edu.sg)

Piecewise Flat Embedding for Image Segmentation (Abstract)

Chaowei Fang , Dept. of Computer Science, The University of Hong Kong, HK, Hong Kong Hong Kong (e-mail: chwfang@connect.hku.hk)
Zicheng Liao , College of Computer Science, Zhejiang University, Hangzhou, Zhejiang China (e-mail: zliao@zju.edu.cn)
Yizhou Yu , Dept. of Computer Science, The University of Hong Kong, Pokfulam, Hong Kong Hong Kong (e-mail: yizhouy@acm.org)

Video Object Segmentation Without Temporal Information (Abstract)

Kevis-Kokitsi Maninis , Computer Vision Lab, ETHZ, Zürich, Zürich Switzerland 8092 (e-mail: kmaninis@vision.ee.ethz.ch)
Sergi Caelles , Computer Vision Lab, ETHZ, Zürich, Zürich Switzerland (e-mail: scaelles@vision.ee.ethz.ch)
Yuhua Chen , Computer Vision Lab, ETHZ, Zürich, Zürich Switzerland (e-mail: yuhua.chen@vision.ee.ethz.ch)
Jordi Pont-Tuset , Computer Vision Lab, ETHZ, Zürich, Zürich Switzerland 8092 (e-mail: jponttuset@vision.ee.ethz.ch)
Laura Leal-Taixe , Informatics, TU Munich, München, Bayern Germany (e-mail: leal.taixe@tum.de)
Daniel Cremers , Department of Computer Science, TU München, Munich, Bayern Germany 85748 (e-mail: cremers@tum.de)
Luc Van Gool , Computer Vision Laboratory, ETH Zurich, Zurich, Zurich Switzerland (e-mail: vangool@vision.ee.ethz.ch)

Content Aware Image Pre-Compensation (Abstract)

Jinwei Ye , Computer Science and Engineering, Louisiana State University, Baton Rouge, Louisiana United States 70803 (e-mail: jye@csc.lsu.edu)
Yu Ji , Computer and Information Sciences, University of Delaware, 5972 Newark, Delaware United States (e-mail: yuji@udel.edu)
Mingyuan Zhou , Computer and Information Science, University of Delaware, Newark, Delaware United States (e-mail: mzhou@udel.edu)
Sing Bing Kang , Microsoft Research, Microsoft Corporation, Redmond, Washington United States (e-mail: sbkang@microsoft.com)
Jingyi Yu , School of Information Science and Technology, ShanghaiTech University, 387433 Shanghai, Shanghai China (e-mail: yu@eecis.udel.edu)

Large Scale Image Segmentation with Structured Loss based Deep Learning for Connectome Reconstruction (PDF)

Jan Funke , Institut de Robotica i Informatica Industrial, Universitat Politecnica de Catalunya, 16767 Barcelona, Barcelona Spain (e-mail: jfunke@iri.upc.edu)
Fabian David Tschopp , n/a, Institut fur Neuroinformatik UZH/ETH, 30974 Zurich, ZH Switzerland (e-mail: tschopfa@student.ethz.ch)
William Grisaitis , Turaga Lab, Howard Hughes Medical Institute, Janelia Research Campus, Ashburn, Virginia United States (e-mail: grisaitisw@janelia.hhmi.org)
Arlo Sheridan , Turaga Lab, Howard Hughes Medical Institute, Janelia Research Campus, Ashburn, Virginia United States (e-mail: sheridana@janelia.hhmi.org)
Chandan Singh , Turaga Lab, Howard Hughes Medical Institute, Janelia Research Campus, Ashburn, Virginia United States (e-mail: singhc@janelia.hhmi.org)
Stephan Saalfeld , Saalfeld Lab, Howard Hughes Medical Institute, Janelia Research Campus, Ashburn, Virginia United States (e-mail: saalfelds@janelia.hhmi.org)
Srinivas C. Turaga , Turaga Lab, Howard Hughes Medical Institute, Janelia Research Campus, Ashburn, Virginia United States (e-mail: turagas@janelia.hhmi.org)

Distributed Very Large Scale Bundle Adjustment by Global Camera Consensus (Abstract)

Runze Zhang , The Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Kowloon, Hong Kong Hong Kong (e-mail: rzhangaj@cse.ust.hk)
Siyu Zhu , A.I. Labs, Alibaba, Hangzhou, Zhejiang China (e-mail: siting.zsy@alibaba-inc.com)
Tianwei Shen , The Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Kowloon, Hong Kong Hong Kong (e-mail: tshenaa@cse.ust.hk)
Lei Zhou , The Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Kowloon, Hong Kong Hong Kong (e-mail: lzhouai@cse.ust.hk)
Zixin Luo , The Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Kowloon, Hong Kong Hong Kong (e-mail: zluoag@cse.ust.hk)
Tian Fang , Shenzhen Zhuke Innovation Technology, Shenzhen Zhuke Innovation Technology, Shenzhen, Guangzhou China (e-mail: fangtian@altizure.com)
Long Quan , The Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Kowloon, Hong Kong Hong Kong (e-mail: quan@cse.ust.hk)

A Deep Network Solution for Attention and Aesthetics Aware Photo Cropping (Abstract)

Wenguan Wang , Department of Computer Science, Beijing Institute of Technology, Beijing, Beijing China (e-mail: wenguanwang@bit.edu.cn)
Jianbing Shen , Department of Information Technology and Electrical Engineering, ETH Zurich, Zurich, Zurich Switzerland CH-8092 (e-mail: shenjianbing@bit.edu.cn)
Haibin Ling , Computer and Information Sciences, Temple University, Philadelphia, Pennsylvania United States (e-mail: hbling@temple.edu)

Wasserstein CNN: Learning Invariant Features for NIR-VIS Face Recognition (Abstract)

Ran He , National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, Beijing China 100190 (e-mail: rhe@nlpr.ia.ac.cn)
Xiang Wu , National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, Beijing China (e-mail: alfredxiangwu@gmail.com)
Zhenan Sun , Center for Biometrics and Security Research, CAS Institute of Automation, Beijing, Beijing China 100190 (e-mail: znsun@nlpr.ia.ac.cn)
Tieniu Tan , NLPR, CASIA, Beijing 100080, Hunan China 100080 (e-mail: tnt@nlpr.ia.ac.cn)

DeepIGeoS: A Deep Interactive Geodesic Framework for Medical Image Segmentation (PDF)

Guotai Wang , Center for Medical Image Computing, University College London, 4919 London, London United Kingdom of Great Britain and Northern Ireland (e-mail: guotai.wang.14@ucl.ac.uk)
Maria A. Zuluaga , Centre for Medical Image Computing, University College London, London, London United Kingdom of Great Britain and Northern Ireland (e-mail: maria.zuluaga@gmail.com)
Wenqi Li , Centre for Medical Image Computing, University College London, London, London United Kingdom of Great Britain and Northern Ireland (e-mail: wenqi.li@ucl.ac.uk)
Rosalind Pratt , Institute for Women's Health, University College London, 4919 London, London United Kingdom of Great Britain and Northern Ireland (e-mail: rosalind.pratt@ucl.ac.uk)
Premal A. Patel , Centre for Medical Image Computing, University College London, London, London United Kingdom of Great Britain and Northern Ireland (e-mail: premal.patel@ucl.ac.uk)
Michael Aertsen , Department of Radiology, University Hospitals KU Leuven, Leuven, Leuven Belgium (e-mail: michaelaertsen@gmail.com)
Tom Doel , Centre for Medical Image Computing, University College London, London, London United Kingdom of Great Britain and Northern Ireland (e-mail: t.doel@ucl.ac.uk)
Anna L. Divid , Institute for Women's Health, University College London, 4919 London, London United Kingdom of Great Britain and Northern Ireland (e-mail: a.david@ucl.ac.uk)
Jan Deprest , Department of Obstetrics, University Hospitals KU Leuven, Leuven, Leuven Belgium (e-mail: Jan.Deprest@uzleuven.be)
Sebastien Ourselin , Centre for Medical Image Computing, University College London, London, London United Kingdom of Great Britain and Northern Ireland (e-mail: s.ourselin@ucl.ac.uk)
Tom Vercauteren , Centre for Medical Image Computing, University College London, London, London United Kingdom of Great Britain and Northern Ireland (e-mail: t.vercauteren@ucl.ac.uk)

Pólya Urn Latent Dirichlet Allocation: a doubly sparse massively parallel sampler (Abstract)

Alexander Terenin , Mathematics, Imperial College London, London, London United Kingdom of Great Britain and Northern Ireland (e-mail: a.terenin17@imperial.ac.uk)
Mans Magnusson , Computer and Information Science, Linkopings universitet, 4566 Linkoping, Linkoping Sweden (e-mail: mons.magnusson@gmail.com)
Leif Jonsson , Computer and Information Science, Linkopings universitet Campus Norrkoping, 101031 Norrkoping, Linkoping Sweden (e-mail: leif.jonsson@ericsson.se)
David Draper , Applied Mathematics and Statistics, University of California Santa Cruz Department of Applied Mathematics and Statistics, 218530 Santa Cruz, California United States 95064-1077 (e-mail: draper@ucsc.edu)

Unifying Visual Attribute Learning with Object Recognition in a Multiplicative Framework (Abstract)

Kongming Liang , Chinese Academy of Sciences, Institute of Computing Technology, Beijing, Beijing China (e-mail: kongming.liang@vipl.ict.ac.cn)
Hong Chang , Chinese Academy of Sciences, Institute of Computing Technology, Beijing, Beijing China (e-mail: changhong@ict.ac.cn)
Bingpeng Ma , Chinese Academy of Sciences, Institute of Computing Technology, Beijing, Beijing China (e-mail: bingpeng.ma@vipl.ict.ac.cn)
Shiguang Shan , Institute of Computing Technology, Chinese Academy of Science, Haidian, Beijing China 100080 (e-mail: sgshan@ict.ac.cn)
Xilin Chen , Institute of Computing Technology, Chinese Academy of Sciences, Beijing, Beijing China 100080 (e-mail: xlchen@ict.ac.cn)

Feedback Convolutional Neural Network for Visual Localization and Segmentation (Abstract)

Chunshui Cao , Department of Automation, University Of Science And Technology Of China, Beijing, Beijing China (e-mail: ccs@mail.ustc.edu.cn)
Yongzhen Huang , National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, Beijing China (e-mail: yzhuang@nlpr.ia.ac.cn)
Yi Yang , Institute of Deep Learning, Baidu Inc, 438127 Beijing, Beijing China (e-mail: yangyi05@baidu.com)
Liang Wang , Institute of Automation, Chinese Academy of Sciences, Beijing, Beijing China (e-mail: wangliang@nlpr.ia.ac.cn)
Zilei Wang , Automation, University of Science and Technology of China, Hefei, Anhui China 230027 (e-mail: zlwang@ustc.edu.cn)
Tieniu Tan , NLPR, CASIA, Beijing 100080, Hunan China 100080 (e-mail: tnt@nlpr.ia.ac.cn)

Error Backprojection Algorithms for Non-Line-of-Sight Imaging (Abstract)

Marco La Manna , Biostatistics and Medical Informatics, University of Wisconsin - Madison, Madison, Wisconsin United States 53706 (e-mail: marcolmn@gmail.com)
Fiona Kine , Biostatistics and Medical Informatics, University of Wisconsin - Madison, Madison, Wisconsin United States (e-mail: kine@wisc.edu)
Eric Breitbach , Biostatistics and Medical Informatics, University of Wisconsin - Madison, Madison, Wisconsin United States (e-mail: ebreitbach2@wisc.edu)
Jonathan Jackson , Physics, University of California Berkeley Research, 140239 Berkeley, California United States (e-mail: jonathanj@berkeley.edu)
Talha Sultan , Biostatistics and Medical Informatics, University of Wisconsin - Madison, Madison, Wisconsin United States (e-mail: tsultan@wisc.edu)
Andreas Velten , Biostatistics and Medical Informatics, University of Wisconsin - Madison, Madison, Wisconsin United States (e-mail: velten@gmail.com)

Mask R-CNN (Abstract)

Kaiming He , AI Research, Facebook Inc, 342996 Menlo Park, California United States 94025-1452 (e-mail: kmh.kaiminghe@gmail.com)
Georgia Gkioxari , AI Research, Facebook Inc, 342996 Menlo Park, California United States (e-mail: gkioxari@eecs.berkeley.edu)
Piotr Dollar , AI Research, Facebook Inc, 342996 Menlo Park, California United States (e-mail: pdollar@gmail.com)
Ross Girshick , -, Facebook Inc, 342996 Seattle, Washington United States (e-mail: rbg@fb.com)

Few-Example Object Detection with Model Communication (Abstract)

Xuanyi Dong , Centre for Artificial Intelligence, University of Technology Sydney, Sydney, New South Wales Australia (e-mail: dongxuanyi888@icloud.com)
Liang Zheng , QCIS, University of Technology Sydney, Sydney, New South Wales Australia 2007 (e-mail: liangzheng06@gmail.com)
Fan Ma , Ministry of Education Key Lab of Intelligent Networks and Network Security, Xi'an Jiaotong University, Xi'an, Shaanxi China (e-mail: flower.fan@foxmail.com)
Yi Yang , Centre for Artificial Intelligence, UTS, Ultimo, New South Wales Australia (e-mail: Yi.Yang@uts.edu.au)
Deyu Meng , Faculty of Science, Institute for Information and System Science, Xi'an, Shaan'xi China 710049 (e-mail: dymeng@mail.xjtu.edu.cn)

Light Field Reconstruction Using Convolutional Network on EPI and Extended Applications (Abstract)

Gaochang Wu , the State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, 12434 Shenyang, Liaoning China (e-mail: ahwgc2009@163.com)
Yebin Liu , Automation Department, Tsinghua University, Beijing, Beijing China (e-mail: liuyebin@tsinghua.edu.cn)
Lu Fang , Graduate Scool in Shenzhen, Graduate Scool in Shenzhen, Tsinghua University, Shenzhen, Guangdong China (e-mail: fanglu@sz.tsinghua.edu.cn)
Qionghai Dai , Automation Department, beijing, beijing China (e-mail: qionghaida@tsinghua.edu.cn)
Tianyou Chai , Department of Automation, Northeastern University, 12434 Shenyang, Liaoning China (e-mail: tychai@mail.neu.edu.cn)

Predicting the Driver's Focus of Attention: the DR(eye)VE Project (Abstract)

Andrea Palazzi , Engineering, Universita degli Studi di Modena e Reggio Emilia Dipartimento di Ingegneria Enzo Ferrari, 204488 Modena, Modena Italy (e-mail: andrea.palazzi@unimore.it)
Davide Abati , Engineering, Universita degli Studi di Modena e Reggio Emilia Dipartimento di Ingegneria Enzo Ferrari, 204488 Modena, Modena Italy (e-mail: davide.abati@unimore.it)
Simone Calderara , DII, University of Modena and Reggio Emilia, Modena, MO Italy 41125 (e-mail: simone.calderara@unimore.it)
Francesco Solera , DIEF - Department of Engineering, University of Modena and Reggio Emilia, Modena, MO Italy 41125 (e-mail: francesco.solera@unimore.it)
Rita Cucchiara , DIEF, University of Modena and Reggio Emilia, Modena, MO Italy 41100 (e-mail: rita.cucchiara@unimore.it)

Density-Preserving Hierarchical EM Algorithm: Simplifying Gaussian Mixture Models for Approximate Inference (Abstract)

Lei Yu , Department of Computer Science, City University of Hong Kong, 53025 Kowloon Tong, Hong Kong Hong Kong (e-mail: leiyu6-c@my.cityu.edu.hk)
Tianyu Yang , Department of Computer Science, City University of Hong Kong, 53025 Kowloon Tong, Hong Kong Hong Kong (e-mail: tianyyang8-c@my.cityu.edu.hk)
Antoni B. Chan , Dept. of Computer Science, City University of Hong Kong, Kowloon Tong, n/a Hong Kong (e-mail: abchan@cityu.edu.hk)

Efficient Learning-Free Keyword Spotting (Abstract)

George Retsinas , Institute of Informatics and Telecommunications, National Centre for Scientific Research-Demokritos, 54572 Athens, Aghia Paraskevi Greece 153 10 (e-mail: georgeretsi@iit.demokritos.gr)
Georgios Louloudis , Institute of Informatics and Telecommunications, National Centre for Scientific Research-Demokritos, 54572 Athens, Aghia Paraskevi Greece (e-mail: louloud@iit.demokritos.gr)
Nikolaos Stamatopoulos , Institute of Informatics and Telecommunications, National Centre for Scientific Research-Demokritos, 54572 Athens, Aghia Paraskevi Greece (e-mail: nstam@iit.demokritos.gr)
Basilios Gatos , Institute of Informatics and Telecommunications, National Center for Scientific Research, Athens, - Greece (e-mail: bgat@iit.demokritos.gr)

lp-Box ADMM: A Versatile Framework for Integer Programming (Abstract)

Baoyuan Wu , Electrical Engineering and Computer Science, King Abdullah University of Science and Technology, 127355 Thuwal, Jeddah Saudi Arabia (e-mail: wubaoyuan1987@gmail.com)
Bernard Ghanem , Electrical Engineering and Computer Science, King Abdullah University of Science and Technology, Thuwal, Jeddah Saudi Arabia (e-mail: bernard.ghanem@kaust.edu.sa)

Differential Geometry in Edge Detection: accurate estimation of position, orientation and curvature (Abstract)

Benjamin B. Kimia , Engineering, Brown University, Providence, Rhode Island United States (e-mail: kimia@lems.brown.edu)
Xiaoyan Li , Engineering, Brown University, Providence, Rhode Island United States (e-mail: xiaoyan.li@vipl.ict.ac.cn)
Yuliang Guo , Engineering, Brown University, Providence, Rhode Island United States (e-mail: yuliang_guo@brown.edu)
Amir Tamrakar , Vision Technologies, SRI International, 5426 Menlo Park, California United States (e-mail: amir.tamrakar@sri.com)

Fine-tuning CNN Image Retrieval with No Human Annotation (Abstract)

Filip Radenovic , Visual Recognition Group, Ceske Vysoke Uceni Technicke v Praze, 48220 Praha, Czech Republic Czech Republic (e-mail: filip.radenovic@cmp.felk.cvut.cz)
Giorgos Tolias , Visual Recognition Group, Ceske Vysoke Uceni Technicke v Praze, 48220 Praha, Czech Republic Czech Republic (e-mail: giorgos.tolias@cmp.felk.cvut.cz)
Ondrej Chum , Visual Recognition Group, Ceske Vysoke Uceni Technicke v Praze, 48220 Praha, Czech Republic Czech Republic (e-mail: chum@cmp.felk.cvut.cz)

Salient Object Detection with Recurrent Fully Convolutional Networks (Abstract)

Linzhao Wang , School of Information and Communication Engineering, Dalian University of Technology, 12399 Dalian, Liaoning China (e-mail: linzertling@gmail.com)
Lijun Wang , Information and Communication Engineering, Dalian University of Technology, 12399 Dalian, Liaoning China 116024 (e-mail: xingkong19890806@gmail.com)
Huchuan Lu , School of Information and Comunicaiton Engineering, Dalian univ. of Tech., dalian, Liaoning China (e-mail: lhchuan@dlut.edu.cn)
Pingping Zhang , School of Information and Communication Engineering, Dalian University of Technology, 12399 Dalian, Liaoning China (e-mail: jssxzhpp@gmail.com)
Xiang Ruan , CEO, Tiwaki.Co., Ltd, Kusatsu, Shiga Japan (e-mail: ruanxiang@gmail.com)

Salient Subsequence Learning for Time Series Clustering (Abstract)

Qin Zhang , QCIS, University of Technology Sydney, Sydney, New South Wales Australia (e-mail: qin.zhang@student.uts.edu.au)
Jia Wu , Department of Computing, Macquarie University, Sydney, New South Wales Australia 2109 (e-mail: jia.wu@mq.edu.au)
Peng Zhang , Faculty of Engineering and Information Technology, University of Technology Sydney, 1994 Sydney, New South Wales Australia (e-mail: pengzhang04@gmail.com)
Guodong Long , QCIS, University of Technology, Sydney, Sydney, New South Wales Australia (e-mail: Guodong.Long@uts.edu.au)
Chengqi Zhang , Centre for quantum computation and intelligent systems, University of Technology, Sydney, Sydney, New South Wales Australia 2007 (e-mail: Chengqi.Zhang@uts.edu.au)

Opening the Black Box: Hierarchical Sampling Optimization for Hand Pose Estimation (Abstract)

Danhang Tang , Electrical and Electronic Engineering, Imperial College London, London, London United Kingdom of Great Britain and Northern Ireland SW7 2AZ (e-mail: danhang.tang@gmail.com)
Qi Ye , Electrical and Electronic Engineering, Imperial College London, 4615 London, London United Kingdom of Great Britain and Northern Ireland (e-mail: q.ye14@imperial.ac.uk)
Jonathan Taylor , PerceptiveIO, PerceptiveIO, San Francisco, California United States (e-mail: jtaylor@perceptiveio.com)
Shanxin Yuan , Electrical Engineering, Imperial College London, 4615 London, London United Kingdom of Great Britain and Northern Ireland (e-mail: s.yuan14@imperial.ac.uk)
Pushmeet Kohli , Electrical and Electronic Engineering, Microsoft Research, Cambridge, Cambridgeshire United Kingdom of Great Britain and Northern Ireland (e-mail: pushmeet@outlook.com)
Cem Keskin , perceptiveIO, perceptiveIO, San Francisco, California United States (e-mail: cem.kskn@gmail.com)
Tae-Kyun Kim , EEE, Imperial College, London, N/A United Kingdom of Great Britain and Northern Ireland (e-mail: tk.kim@imperial.ac.uk)
Jamie Shotton , Cambridge, Microsoft Research, Cambridge, Cambridgeshire United Kingdom of Great Britain and Northern Ireland CB3 0FB (e-mail: jamiesho@microsoft.com)

Globally-Optimal Inlier Set Maximisation for Camera Pose and Correspondence Estimation (Abstract)

Dylan John Campbell , College of Engineering and Computer Science, The Australian National University, Acton, Australian Capital Territory Australia (e-mail: dylan.campbell@anu.edu.au)
Lars Petersson , College of Engineering and Computer Science, The Australian National University, Acton, Australian Capital Territory Australia (e-mail: lars.petersson@anu.edu.au)
Laurent Kneip , School of Information Science and Technology, ShanghaiTech University, 387433 Pudong, Shanghai China (e-mail: lkneip@shanghaitech.edu.cn)
Hongdong Li , College of Engineering and Computer Science, The Australian National University, Acton, Australian Capital Territory Australia (e-mail: Hongdong.Li@anu.edu.au)

Safe Classification With Augmented Features (Abstract)

Chenping Hou , College of Science, National University of Defense Technology, Changsha, Hunan China (e-mail: hcpnudt@hotmail.com)
Ling-Li Zeng , College of Mechatronics and Automation, National University of Defense Technology, Changsha, Hunan China (e-mail: lingl.zeng@gmail.com)
Dewen Hu , Department of Automatic Control, College of Mechatronics and Automation, National University of Defense Technology, Changsha, Hunan China (e-mail: dwhu@nudt.edu.cn)

On Detection, Data Association and Segmentation for Multi-target Tracking (Abstract)

Yicong Tian , Computer Science, University of Central Florida, Orlando, Florida United States (e-mail: tyc.cong@gmail.com)
Afshin Dehghan , School of Electric Engineering and Computer Science, University of Central Florida, Orlando, Florida United States (e-mail: adehghan@cs.ucf.edu)
Mubarak Shah , Center for Research in Computer Vision, University of Central Florida, Orlando, Florida United States (e-mail: shah@crcv.ucf.edu)

Deep Metric Learning with BIER: Boosting Independent Embeddings Robustly (Abstract)

Michael Opitz , Institute for Computer Graphics and Vision, Graz University of Technology, Graz, Styria Austria (e-mail: michael.opitz@icg.tugraz.at)
Georg Waltner , Institute for Computer Graphics and Vision, Technische Universitat Graz, 27253 Graz, Steiermark Austria (e-mail: waltner@icg.tugraz.at)
Horst Possegger , Institute for Computer Graphics and Vision, Graz University of Technology, Graz, Styria Austria 8010 (e-mail: possegger@icg.tugraz.at)
Horst Bischof , Institut for Computer Graphics and Vision, Graz University of Technology, Graz, Styria Austria A-8010 (e-mail: bischof@icg.tugraz.at)

PsyPhy: A Psychophysics Driven Evaluation Framework for Visual Recognition (Abstract)

Brandon RichardWebster , Computer Science & Engineering, University of Notre Dame, Notre Dame, Indiana United States (e-mail: brichar1@nd.edu)
Samuel Anthony , Department of Psychology, Harvard University, Cambridge, Massachusetts United States (e-mail: santhony@wjh.harvard.edu)
Walter Scheirer , Computer Science & Engineering, University of Notre Dame, 6111 Notre Dame, Indiana United States (e-mail: walter.scheirer@nd.edu)

Outlier Detection for Robust Multi-dimensional Scaling (Abstract)

Leonid Blouvshtein , Computer Science, Tel Aviv University Blavatnik School of Computer Science, 208983 Tel Aviv, None Israel 69978 (e-mail: leonidbl91@gmail.com)
Daniel Cohen-Or , computer science, Tel-Aviv University, Tel-Aviv, Israel Israel 69978 (e-mail: dcor@tau.ac.il)

Deep Collaborative Embedding for Social Image Understanding (Abstract)

Zechao Li , School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu China 210094 (e-mail: zechao.li@njust.edu.cn)
Jinhui Tang , School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu China 210094 (e-mail: tangjh1981@acm.org)
Tao Mei , Internet Media Group, Microsoft Research Asia, Beijing, Beijing China 100190 (e-mail: tmei@live.com)

A comprehensive database for benchmarking imaging systems (PDF)

Karen Panetta , Department of Electrical and Computer Engineering, Tufts University, Medford, Massachusetts United States (e-mail: karen@ece.tufts.edu)
Qianwen Wan , Electrical Engineering, Tufts University, Medford, Massachusetts United States (e-mail: wendyqianwenwan@gmail.com)
Sos Agaian , Computer Science, City University of New York, New York, New York United States (e-mail: Sos.Agaian@csi.cuny.edu)
Srijith Rajeev , Department of Electrical and Computer Engineering, Tufts University, Medford, Massachusetts United States (e-mail: srijith.rajeev@tufts.edu)
Shreyas Kamath , Department of Electrical and Computer Engineering, Tufts University, Medford, Massachusetts United States (e-mail: skamat04@tufts.edu)
Rahul Rajendran , Department of Electrical and Computer Engineering, Tufts University, Medford, Massachusetts United States (e-mail: rahul.rajendran@tufts.edu)
Shishir Rao , Department of Electrical and Computer Engineering, Tufts University, Medford, Massachusetts United States (e-mail: shishir.rao@tufts.edu)
Aleksandra Kaszowska , Department of Psychology, Tufts University, Medford, Massachusetts United States (e-mail: aleksandra.kaszowska@tufts.edu)
Holly Taylor , Department of Psychology, Tufts University, Medford, Massachusetts United States (e-mail: holly.taylor@tufts.edu)
Arash Samani , Department of Electrical and Computer Engineering, Tufts University, Medford, Massachusetts United States (e-mail: samani@ieee.org)
Xin Yuan , Department of Electrical and Computer Engineering, Tufts University, Medford, Massachusetts United States (e-mail: Xin.Yuan@tufts.edu)

Incremental Learning Through Deep Adaptation (Abstract)

Amir Rosenfeld , EECS, York University, Toronto, Ontario Canada M3J 1P3 (e-mail: amir.rosenfeld@gmail.com)
John K. Tsotsos , Computer Science & Engineering, York University, Toronto, Ontario Canada (e-mail: tsotsos@cse.yorku.ca)

Distance Encoded Product Quantization for Approximate K-Nearest Neighbor Search in High-Dimensional Space (Abstract)

Jae-Pil Heo , Dept. of Software, Sungkyunkwan University, Suwon, Gyeonggi-do Korea (the Republic of) 16419 (e-mail: jaepilheo@gmail.com)
Zhe Lin , Advanced Technology Labs, Adobe Systems Incorporated, San Jose, California United States (e-mail: zlin@adobe.com)
Sung-Eui Yoon , Computer Science, KAIST, Korea Advanced Institute of Science and Technology, DaeJeon, Chungchung Korea, Republic of 305 701 (e-mail: sungeui@gmail.com)

Visual Dynamics: Stochastic Future Generation via Layered Cross Convolutional Networks (Abstract)

Tianfan Xue , Google Research, Google Inc, 93176 Mountain View, California United States (e-mail: tfxue@mit.edu)
Jiajun Wu , Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, Massachusetts United States (e-mail: jiajunwu@mit.edu)
Katherine Bouman , Harvard-Smithsonian Center for Astrophysics, Harvard University, Cambridge, Massachusetts United States (e-mail: klbouman@mit.edu)
William Freeman , Electrical Engineering and Computer Science, Massachusetts Institute of Technology, 2167 Cambridge, Massachusetts United States (e-mail: billf@mit.edu)

Image Deblurring with a Class-Specific Prior (Abstract)

Saeed Anwar , College of Engineering and Computer Science, Australian National University College of Engineering and Computer Science, 213523 Canberra, Australian Capital Territory Australia 02601 (e-mail: saeedanwarcse@gmail.com)
Cong Phuoc Huynh , Research School of Engineering, The Australian National University, Canberra, Australian Capital Territory Australia (e-mail: cong.huynh@nicta.com.au)
Fatih Porikli , Computer Vision, Mitsubishi Electric Research Labs, Cambridge, Massachusetts United States 02472 (e-mail: fatih.porikli@anu.edu.au)

Zero-Shot Learning - A Comprehensive Evaluation of the Good, the Bad and the Ugly (Abstract)

Yongqin Xian , Computer Vision and Multimodal Computing, Max Planck Institute Informatik, Saarbruecken, Saarland Germany (e-mail: yxian@mpi-inf.mpg.de)
Christoph H. Lampert , Computer Vision and Machine Learning Group, IST Austria, Klosterneuburg, Austria (e-mail: chl@ist.ac.at)
Bernt Schiele , D2, MPI Informatics, Saabrucken, Saarland Germany (e-mail: schiele@mpi-inf.mpg.de)
Zeynep Akata , D2, Max Planck Institute for Informatics, Saarbrucken, Saarland Germany 66123 (e-mail: akata@mpi-inf.mpg.de)

Packing Convolutional Neural Networks in the Frequency Domain (Abstract)

Yunhe Wang , School of Electrical Engineering and Computer Science, Peking University, 12465 Beijing, Beijing China (e-mail: wangyunhe@pku.edu.cn)
Chang Xu , Engineering and Information Technologies, University of Sydney, Sydney, New South Wales Australia (e-mail: changxu1989@gmail.com)
Chao Xu , Key Laboratory of Machine Perception (Ministry of Education), Peking University, Beijing, Beijing China (e-mail: xuchao@cis.pku.edu.cn)
Dacheng Tao , Engineering and Information Technologies, University of Sydney, 4334 Sydney, New South Wales Australia (e-mail: dacheng.tao@sydney.edu.au)

Solving Square Jigsaw Puzzle by Hierarchical Loop Constraints (Abstract)

Kilho Son , Vision and Learning Laboratory, SRI International, 5426 Princeton, New Jersey United States (e-mail: kilho.son@gmail.com)
James Hays , Interactive Computing, Georgia Institute of Technology, 1372 Atlanta, Georgia United States 30332-0002 (e-mail: hays@gatech.edu)
David B. Cooper , School of Engineering, Brown University, Providence, Rhode Island United States 02912 (e-mail: davidbencooper@gmail.com)

Scattering Networks for Hybrid Representation Learning (Abstract)

Edouard Oyallon , Centre de Vision Numérique, CentraleSupelec, 435940 Gif-sur-Yvette, Île de france France (e-mail: edouard.oyallon@centralesupelec.fr)
Sergey Zagoruyko , Paris, Ecole des Ponts ParisTech, 52835 Marne-la-Vallee, Ile-de-France France (e-mail: sergey.zagoruyko@enpc.fr)
Gabriel Huang , CS & OR, Université de Montréal, Montréal, Quebec Canada (e-mail: gabriel.huang@umontreal.ca)
Nikos Komodakis , Paris, Ecole des Ponts ParisTech, 52835 Marne-la-Vallee, Ile-de-France France (e-mail: nikos.komodakis@enpc.fr)
Simon Lacoste-Julien , CS & OR, Université de Montréal, Montréal, Quebec Canada (e-mail: slacoste@iro.umontreal.ca)
Matthew B. Blaschko , Department of Electrical Engineering (ESAT), KU Leuven, Leuven, Flemish Brabant Belgium (e-mail: matthew.blaschko@esat.kuleuven.be)
Eugene Belilovsky , CS & OR, Université de Montréal, Montréal, Quebec Canada (e-mail: eugene.belilovsky@inria.fr)

Dominant Sets for “Constrained” Image Segmentation (Abstract)

Eyasu Zemene Mequanint , Computer Science, Universita Ca Foscari, 19047 Venezia, Venezia Italy 30172 (e-mail: eyasu201011@gmail.com)
Leulseged Tesfaye Alemu , DAIS, Universita Ca' Foscari, 19047 Venezia, VENEZIA Italy 30123 (e-mail: leule24@gmail.com)
Marcello Pelillo , Computer Science, Universita Ca Foscari, 19047 Venezia, Venezia Italy (e-mail: pelillo@unive.it)

Large-Scale Low-Rank Matrix Learning with Nonconvex Regularizers (Abstract)

quanming yao , CSE, Hong Kong University of Science and Technology, 58207 Kowloon, hong kong Hong Kong (e-mail: quanmingyao@gmail.com)
James. T. Kwok , CSE, HKUST, HK, HK Hong Kong (e-mail: jamesk@cse.ust.hk)
Tai-Feng Wang , Internet Economics & Computational Advertising Group, Microsoft Research Asia, Beijing, Beijing China (e-mail: taifengw@microsoft.com)
Tie-Yan Liu , Web Search and Mining Group, Microsoft Research Asia, Beijing, Beijing China 100080 (e-mail: tie-yan.liu@microsoft.com)

StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks (Abstract)

Han Zhang , Computer Science, Rutgers The State University of New Jersey, 242612 New Brunswick, New Jersey United States 08901-8554 (e-mail: zhanghan8788@gmail.com)
Tao Xu , Computer Science & Engineering, Lehigh University, Bethlehem, Pennsylvania United States 18015 (e-mail: lehigh.tao@gmail.com)
Hongsheng Li , Electronic Engineering, The Chinese University of Hong Kong, Shatin, N.T. Hong Kong (e-mail: hsli@ee.cuhk.edu.hk)
Shaoting Zhang , Computer Science, UNC Charlotte, Char, North Carolina United States 28027 (e-mail: shaoting@cs.rutgers.edu)
Xiaogang Wang , Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, Hong Kong Hong Kong (e-mail: xgwang@ee.cuhk.edu.hk)
Xiaolei Huang , Computer Science and Engineering, Lehigh University, Bethlehem, Pennsylvania United States 18015 (e-mail: xih206@lehigh.edu)
Dimitris N. Metaxas , Computer Science, Rutgers The State University of New Jersey, Piscataway, New Jersey United States 08854-8019 (e-mail: dnm@cs.rutgers.edu)

ThiNet: Pruning CNN Filters for a Thinner Net (Abstract)

Jian-Hao Luo , Dept of Computer Science and Technology, Nanjing University, Nanjing, Jiangsu China (e-mail: luojh@lamda.nju.edu.cn)
Hao Zhang , Nanjing University, National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu China (e-mail: zhangh@lamda.nju.edu.cn)
Hong-Yu Zhou , Dept of Computer Science and Technology, Nanjing University, Nanjing, Jiangsu China (e-mail: zhouhy@lamda.nju.edu.cn)
Chen-Wei Xie , Dept of Computer Science and Technology, Nanjing University, Nanjing, Jiangsu China (e-mail: xiecw@lamda.nju.edu.cn)
Jianxin Wu , Dept of Computer Science and Technology, Nanjing University, Nanjing, Jiangsu China (e-mail: wujx2001@gmail.com)
Weiyao Lin , Electronic Engineering, Shanghai Jiao Tong University, Shanghai, ShangHai China (e-mail: wylin@sjtu.edu.cn)

Predicting Head Movement in Panoramic Video: A Deep Reinforcement Learning Approach (Abstract)

Mai Xu , School of Electronic and Information Engineering, Beihang Univ., Beijing, Beijing China (e-mail: MaiXu@buaa.edu.cn)
Yuhang Song , School of Electronic and Information Engineering, Beihang Univ., Beijing, Beijing China (e-mail: yuhangsong2017@gmail.com)
Jianyi Wang , School of Electronic and Information Engineering, Beihang Univ., Beijing, Beijing China (e-mail: IceClearWJY@buaa.edu.cn)
MingLang Qiao , School of Electronic and Information Engineering, Beihang Univ., Beijing, Beijing China (e-mail: MinglangQiao@buaa.edu.cn)
Liangyu Huo , School of Electronic and Information Engineering, Beihang Univ., Beijing, Beijing China (e-mail: huoliangyu@buaa.edu.cn)
Zulin Wang , EE, Beihang University, Beijing, Beijing China (e-mail: wzulin@buaa.edu.cn)

Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning (Abstract)

Takeru Miyato , Research and Development, Preferred Networks, Inc., Chiyoda-ku, Tokyo Japan (e-mail: takeru.miyato@gmail.com)
Shin-Ichi Maeda , Informatics, Kyoto University, Sakyo-ku, Kyoto Japan (e-mail: ichi@preferred.jp)
Shin Ishii , Informatics, Kyoto University, Sakyo-ku, Kyoto Japan (e-mail: ishii@i.kyoto-u.ac.jp)
Masanori Koyama , Mathematics, Ritsumeikan University, Kusatsu, Kyoto Japan (e-mail: mkoyama@fc.ritsumei.ac.jp)

A Kronecker Product Model for Repeated Pattern Detection on 2D Urban Images (Abstract)

Juan Liu , Research, Google Inc, 93176 New York, New York United States (e-mail: juanliu.ustc@gmail.com)
Emmanouil Psarakis , Computer Engineering & Informatics, Patras, Rio Greece (e-mail: psarakis@ceid.upatras.gr)
Yang Feng , Yang Feng, Columbia University, New York, New York United States 10027 (e-mail: yang.feng@columbia.edu)
Ioannis Stamos , Computer Science, Hunter College of CUNY, New York, New York United States 10021 (e-mail: istamos@hunter.cuny.edu)

Interpreting Deep Visual Representations via Network Dissection (Abstract)

Bolei Zhou , EECS, MIT, Cambridge, Massachusetts United States (e-mail: zhoubolei@gmail.com)
David Bau , EECS, MIT, Cambridge, Massachusetts United States (e-mail: davidbau@mit.edu)
Aude Oliva , CSAIL, CSAIL, Cambridge, Massachusetts United States (e-mail: oliva@mit.edu)
Antonio Torralba , EECS, MIT, Cambridge, Massachusetts United States (e-mail: torralba@mit.edu)

Max-Margin Majority Voting for Learning from Crowds (Abstract)

Tian Tian , Computer Science and Technology, Tsinghua University, 12442 Beijing, Beijing China (e-mail: rossowhite@163.com)
Jun Zhu , Computer Science and Technology, Tsinghua University, 12442 Beijing, Beijing China (e-mail: dcszj@mail.tsinghua.edu.cn)
You Qiaoben , Computer Science and Technology, Tsinghua University, 12442 Beijing, Beijing China (e-mail: qby_222@126.com)

Fast Multi-Instance Multi-Label Learning (Abstract)

Sheng-Jun Huang , College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, 47854 Nanjing, Jiangsu China (e-mail: huangsj@nuaa.edu.cn)
Wei Gao , National Key Laboratory of Novel Software Technology, Nanjing University, Nanjing, Jiangsu China (e-mail: gaow@lamda.nju.edu.cn)
Zhi-Hua Zhou , National Key Lab for Novel Software Technology, Nanjing University, Nanjing, Jiangsu China (e-mail: zhouzh@lamda.nju.edu.cn)

Generalizable Data-free Objective for Crafting Universal Adversarial Perturbations (Abstract)

Konda Reddy Mopuri , Computational and Data Sciences, Indian Institute of Science, Bangalore, Karnataka India (e-mail: kondamopuri@iisc.ac.in)
Aditya Ganeshan , CDS, Indian Institute of Science, Bangalore, Karnataka India 560012 (e-mail: adityaganeshan@gmail.com)
Venkatesh Babu Radhakrishnan , Department of Computational and Data Sciences, Indian Institute of Science, BANGALORE, Karnataka India 560012 (e-mail: venky@iisc.ac.in)

Efficient Training for Positive Unlabeled Learning (Abstract)

Emanuele Sansone , Department of Information Engineering and Computer Science, Universita degli Studi di Trento, 19034 Trento, Trento Italy (e-mail: e.sansone@unitn.it)
Francesco G.B. De Natale , University of Trento, Universita degli Studi di Trento, 19034 Trento, Trento Italy (e-mail: francesco.denatale@unitn.it)
Zhi-Hua Zhou , National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu Pronvince China 210093 (e-mail: zhouzh@nju.edu.cn)

Cross-Generation Kinship Verification with Sparse Discriminative Metric (Abstract)

Shuyang Wang , Electrical & Computer Engineering, Northeastern University, 1848 Boston, Massachusetts United States (e-mail: wangshuy1991@gmail.com)
Zhengming Ding , Electrical & Computer Engineering, Northeastern University, 1848 Boston, Massachusetts United States (e-mail: allanding@ece.neu.edu)
Yun Fu , ECE, Northeastern University, Boston, Massachusetts United States (e-mail: yunfu@ece.neu.edu)

A Generic Multi-Projection-Center Model and Calibration Method for Light Field Cameras (Abstract)

Qi Zhang , School of Computer Science, Northwestern Polytechnical University, Xi'an, Shaanxi China (e-mail: nwpuqzhang@gmail.com)
Chunping Zhang , School of Computer Science, Northwestern Polytechnical University, 26487 Xi'an, Shaanxi China (e-mail: 724495506@qq.com)
Jinbo Ling , School of Computer Science, Northwestern Polytechnical University, 26487 Xi'an, Shaanxi China (e-mail: 312620756@qq.com)
Qing Wang , School of Computer Science, Northwestern Polytechnical University, Xi'an, Shaanxi China (e-mail: qwang@nwpu.edu.cn)
Jingyi Yu , School of Information Science and Technology, ShanghaiTech University, 387433 Shanghai, Shanghai China (e-mail: yu@eecis.udel.edu)

Ticker: An Adaptive Single-Switch Text Entry Method for Visually Impaired Users (Abstract)

Emli-Mari Nel , Research, Inference Engine, Stellenbosch, Western Cape South Africa (e-mail: emlimari.nel@gmail.com)
Per Ola Kristensson , Engineering, University of Cambridge, Cambridge, Cambridgeshire United Kingdom of Great Britain and Northern Ireland (e-mail: pok21@cam.ac.uk)
David MacKay , Engineering, University of Cambridge, 2152 Cambridge, Cambridgeshire United Kingdom of Great Britain and Northern Ireland (e-mail: djcm1@cam.ac.uk)

Convolutional neural network architecture for geometric matching (Abstract)

Ignacio Rocco , Departement d'Informatique, INRIA / ENS, Paris, Ile de France France (e-mail: ignacio.rocco@inria.fr)
Relja Arandjelovic , Research, DeepMind, London, England United Kingdom of Great Britain and Northern Ireland (e-mail: relja@google.com)
Josef Sivic , Departement d'Informatique, INRIA / ENS, Paris, Ile de France France (e-mail: Josef.Sivic@ens.fr)

Flow Fields: Dense Correspondence Fields for Highly Accurate Large Displacement Optical Flow Estimation (PDF)

Christian Bailer , Augmented Vision, Deutsches Forschungszentrum fur Kunstliche Intelligenz GmbH, 40120 Kaiserslautern, Rheinland-Pfalz Germany 67663 (e-mail: christian.bailer@dfki.de)
Bertram Taetz , Augmented Vision, Deutsches Forschungszentrum fur Kunstliche Intelligenz GmbH, 40120 Kaiserslautern, Rheinland-Pfalz Germany (e-mail: bertram.taetz@dfki.de)
Didier Stricker , Augmented Vision, Deutsches Forschungszentrum fur Kunstliche Intelligenz GmbH, 40120 Kaiserslautern, Rheinland-Pfalz Germany (e-mail: didier.stricker@dfki.de)

Robust Visual Tracking via Hierarchical Convolutional Features (Abstract)

Chao Ma , Computer Science, Adelaide, South Australia Australia (e-mail: c.ma@adelaide.edu.au)
Jia-Bin Huang , Electrical and Computer Engineering, Virginia Tech, Blacksburg, Virginia United States (e-mail: jbhuang@vt.edu)
Xiaokang Yang , Institute of Image Communication and Network Engineering, Shanghai, Shanghai China (e-mail: xkyang@sjtu.edu.cn)
Ming-Hsuan Yang , EECS, University of California at Merced, Merced, California United States 95344 (e-mail: mhyang@ucmerced.edu)

Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks (Abstract)

Wei-Sheng Lai , Department of EECS, University of California Merced, 33244 Merced, California United States (e-mail: wlai24@ucmerced.edu)
Jia-Bin Huang , Electrical and Computer Engineering, Virginia Tech, Blacksburg, Virginia United States (e-mail: jbhuang@vt.edu)
Narendra Ahuja , Electrical and Computer Engineering, University of Illinois, Urbana-Champaign, Urbana, Illinois United States (e-mail: n-ahuja@illinois.edu)
Ming-Hsuan Yang , EECS, University of California at Merced, Merced, California United States 95344 (e-mail: mhyang@ucmerced.edu)

Early Action Prediction by Soft Regression (Abstract)

Jian-Fang Hu , School of Data and Computer Science, Sun Yat-Sen University, Guangzhou, Guangdong China (e-mail: hujianf5@mail.sysu.edu.cn)
Wei-Shi Zheng , Department of Computer Science, SUN YAT-SEN University, Guangzhou, Guangdong China (e-mail: wszheng@ieee.org)
Lianyang Ma , Tencent AI Lab, Beijing, Beijing China (e-mail: leonlyma@tencent.com)
Gang Wang , School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore Singapore (e-mail: gangwang6@gmail.com)
Jian-Huang Lai , School of Data and Computer Science, Sun Yat-sen University, Guangzhou, Guangdong China 510275 (e-mail: stsljh@mail.sysu.edu.cn)
Jianguo Zhang , School of Science and Engineering (Computing), Londun, Londun United Kingdom of Great Britain and Northern Ireland (e-mail: j.n.zhang@dundee.ac.uk)

Pixel Objectness: Learning to Segment Generic Objects Automatically in Images and Videos (Abstract)

Bo Xiong , Computer Science, University of Texas at Austin, 12330 Austin, Texas United States 78712-1139 (e-mail: bxiong@cs.utexas.edu)
Suyog Jain , Computer Sciences, University of Texas at Austin College of Natural Sciences, 118710 Austin, Texas United States (e-mail: suyog@cs.utexas.edu)
Kristen Grauman , Computer Sciences, University of Texas at Austin, Austin, Texas United States 78712 (e-mail: grauman@cs.utexas.edu)

Hierarchical binary CNNs for landmark localization with limited resources (PDF)

Adrian Bulat , Computer Vision Laboratory, The University of Nottingham, Nottingham, Nottinghamshire United Kingdom of Great Britain and Northern Ireland (e-mail: adrian.bulat@nottingham.ac.uk)
Yorgos Tzimiropoulos , Computer Vision Laboratory, University of Nottingham School of Computer Science, 200483 Nottingham, Nottinghamshire United Kingdom of Great Britain and Northern Ireland (e-mail: yorgos.tzimiropoulos@nottingham.ac.uk)

Personalized Saliency and Its Prediction (Abstract)

Yanyu Xu , SIST, ShanghaiTech University, 387433 Shanghai, Shanghai China (e-mail: xuyy2@shanghaitech.edu.cn)
Shenghua Gao , ShanghaiTech University, ShanghaiTech University, Shanghai, Shanghai China (e-mail: gaoshh@shanghaitech.edu.cn)
Junru Wu , SIST, ShanghaiTech University, shanghai, Shanghai China (e-mail: wujr1@shanghaitech.edu.cn)
Nianyi Li , Computer and Information Sciences, University of Delaware, Newark, Delaware United States 19716 (e-mail: nianyi@udel.edu)
Jingyi Yu , EECS, University of Delaware, Newark, Delaware United States (e-mail: yu@eecis.udel.edu)

Semi-supervised Domain Adaptation by Covariance Matching (Abstract)

Limin Li , Mathematics, Xi'an Jiaotong University, Xi'an, Shaanxi China (e-mail: liminli@mail.xjtu.edu.cn)
Zhenyue Zhang , Depart of Mathematics, Zhejiang University, Hangzhou, Zhejiang China 310027 (e-mail: zyzhang@zju.edu.cn)

Video Imprint (Abstract)

Zhanning Gao , Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an, Shaanxi China (e-mail: zhanninggao@gmail.com)
Le Wang , Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an, Shaanxi China 710049 (e-mail: lewang@mail.xjtu.edu.cn)
Nebojsa Jojic , Microsoft Research, Microsoft Corporation, Redmond, Washington United States (e-mail: jojic@microsoft.com)
Zhenxing Niu , Machine Intelligence Technology, Alibaba Group, Hangzhou, Zhejiang China (e-mail: zhenxing.nzx@alibaba-inc.com)
Nanning Zheng , Institute of Artificial Intelligence and Robotics, Xi'anJiaotongUniv, Xi'an, Shaanxi China (e-mail: nnzheng@mail.xjtu.edu.cn)
Gang Hua , Microsoft Research, Microsoft Corp, 6834 Redmond, Washington United States 98073-9715 (e-mail: ganghua@gmail.com)

Semi-Supervised Video Object Segmentation with Super-Trajectories (Abstract)

Wenguan Wang , Department of Computer Science, Beijing Institute of Technology, Beijing, Beijing China (e-mail: wenguanwang@bit.edu.cn)
Jianbing Shen , Department of Computer Science, Beijing Institute of Technology, Beijing, Beijing China (e-mail: shenjianbing@bit.edu.cn)
Fatih Porikli , Computer Vision, Mitsubishi Electric Research Labs, Cambridge, Massachusetts United States 02472 (e-mail: fatih.porikli@anu.edu.au)
Ruigang Yang , Computer Science, University of Kentucky, Lexington, Kentucky United States 40507 (e-mail: ryang@cs.uky.edu)

Real-time 3D Hand Pose Estimation with 3D Convolutional Neural Networks (Abstract)

Liuhao Ge , Interdisciplinary Graduate School, Nanyang Technological University, 54761 Singapore, Singapore Singapore (e-mail: ge0001ao@e.ntu.edu.sg)
Hui Liang , Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore, Singapore Singapore (e-mail: hulia@amazon.com)
Junsong Yuan , Department of Computer Science and Engineering, University at Buffalo - The State University of New York, 12292 Buffalo, New York United States (e-mail: jsyuan@buffalo.edu)
Daniel Thalmann , VRlab, EPFL, Lausanne, VD Switzerland (e-mail: daniel.thalmann@epfl.ch)

Hyperspectral Light Field Stereo Matching (Abstract)

Kang Zhu , School of Information Science and Technology, ShanghaiTech University, 387433 Shanghai, Shanghai China 201210 (e-mail: zhukang@shanghaitech.edu.cn)
Yujia Xue , Department of Research and Development, Plex-VR, Shanghai, Shanghai China (e-mail: yujia.xue@plex-vr.com)
Qiang Fu , School of Information Science and Technology, ShanghaiTech University, 387433 Shanghai, Shanghai China (e-mail: fuqiangx@outlook.com)
Sing Bing Kang , Microsoft Research, Microsoft Corporation, Redmond, Washington United States 98052-6399 (e-mail: sbkang@microsoft.com)
Xilin Chen , Institute of Computing Technology, Chinese Academy of Sciences, Beijing, Beijing China 100080 (e-mail: xlchen@ict.ac.cn)
Jingyi Yu , Department of Computer and Information Sciences, University of Delaware, Newark, Delaware United States (e-mail: yu@eecis.udel.edu)

End-to-end policy learning for active visual categorization (Abstract)

Dinesh Jayaraman , Computer Science, UT Austin, Austin, Texas United States (e-mail: dineshj@cs.utexas.edu)
Kristen Grauman , Computer Sciences, University of Texas at Austin, Austin, Texas United States 78712 (e-mail: grauman@cs.utexas.edu)

Joint Active Learning with Feature Selection via CUR Matrix Decomposition (Abstract)

Changsheng Li , University of Electronic Science and Technology of China, Chengdu, Chengdu China (e-mail: changsheng_li_507@hotmail.com)
Xiangfeng Wang , East China Normal University, Shanghai, Shanghai China (e-mail: xfwang@sei.ecnu.edu.cn)
Weishan Dong , Baidu Search, Beijing, Beijing China (e-mail: dongweis@cn.ibm.com)
Junchi Yan , Shanghai Jiao Tong University, Shanghai, Shanghai China (e-mail: yanesta13@163.com)
Qingshan Liu , College of Information and Control, Nanjing University of Information Science and Technology, Nanjing, Jiangsu China 210014 (e-mail: qsliu@nuist.edu.cn)
Hongyuan Zha , School of Computational Science and Engineering, Georgia Tech, Atlanta, Georgia United States 30332 (e-mail: zha@cc.gatech.edu)

Generative Zero-Shot Learning via Low-Rank Embedded Semantic Dictionary (Abstract)

Zhengming Ding , Electrical and Computer Engineering, Northeastern University, Boston, Massachusetts United States (e-mail: allanding@ece.neu.edu)
Ming Shao , Department of Computer and Information Science, University of Massachusetts Dartmouth, Dartmouth, Massachusetts United States (e-mail: mshao@umassd.edu)
Yun Fu , ECE, Northeastern University, Boston, Massachusetts United States (e-mail: yunfu@ece.neu.edu)

Nonlinear Asymmetric Multi-Valued Hashing (Abstract)

Cheng Da , National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, Beijing China (e-mail: cheng.da@nlpr.ia.ac.cn)
Gaofeng Meng , Chinese Academy of Sciences, Institution of Automation, Beijing, Beijing China (e-mail: gfmeng@nlpr.ia.ac.cn)
Shiming Xiang , Chinese Academy of Sciences, Institution of Automation, Beijing, Beijing China (e-mail: smxiang@nlpr.ia.ac.cn)
Kun Ding , National Laboratory of Pattern Recognition, Institute of Automation, Beijing, Beijing China 100190 (e-mail: kding@nlpr.ia.ac.cn)
Shibiao Xu , National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, Beijing China (e-mail: shibiao.xu@nlpr.ia.ac.cn)
Qing Yang , National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, Beijing China (e-mail: qyang@nlpr.ia.ac.cn)
Chunhong Pan , National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, Beijing China (e-mail: chpan@nlpr.ia.ac.cn)

Temporal Segment Networks for Action Recognition in Videos (Abstract)

Limin Wang , Computer Science and Technology, Nanjing University, Nanjing, Jiangsu China (e-mail: lmwang.nju@gmail.com)
Yuanjun Xiong , Information Engineering, The Chinese University of Hong Kong, Hong Kong, Hong Kong Hong Kong (e-mail: yjxiong@ie.cuhk.edu.hk)
Zhe Wang , Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong China (e-mail: buptwangzhe2012@gmail.com)
Yu Qiao , Multimedia, SIAT, Shenzhen, Guangdong China (e-mail: yu.qiao@siat.ac.cn)
Dahua Lin , Information Engineering, The Chinese University of Hong Kong, Hong Kong, Hong Kong Hong Kong (e-mail: dhlin@ie.cuhk.edu.hk)
Xiaoou Tang , Department of Information Engineering, The Chinese University of Hong Kong, Shatin, NT Hong Kong NT (e-mail: xtang@ie.cuhk.edu.hk)
Luc Van Gool , Computer Vision Laboratory, ETH Zurich, Zurich, Zurich Switzerland (e-mail: vangool@vision.ee.ethz.ch)

Discriminant Functional Learning of Color Features for the Recognition of Facial Action Units and their Intensities (Abstract)

Fabian Benitez-Quiroz , electrical and computer eng., The Ohio State University, Columbus, Ohio United States 43210 (e-mail: benitez-quiroz.1@osu.edu)
Ramprakash Srinivasan , Electrical & Computer Eng, Ohio State University, Columbus, Ohio United States (e-mail: srinivasan.134@buckeyemail.osu.edu)
Aleix M. Martinez , Electrical & Computer Eng, Ohio State University, Columbus, Ohio United States 43210 (e-mail: aleix@ece.osu.edu)

Transferable Representation Learning with Deep Adaptation Networks (Abstract)

Mingsheng Long , School of Software, Tsinghua University, Beijing, Beijing China (e-mail: mingsheng@tsinghua.edu.cn)
Yue Cao , Tsinghua University, School of Software, Beijing, Beijing China 100084 (e-mail: yue-cao14@mails.tsinghua.edu.cn)
Zhangjie Cao , School of Software, Tsinghua University, 12442 Beijing, Beijing China (e-mail: caozj14@mails.tsinghua.edu.cn)
Jianmin Wang , Tsinghua University, School of Software, Beijing, Beijing China 100084 (e-mail: jimwang@tsinghua.edu.cn)
Michael I. Jordan , Computer Science, University of California, Berkeley, Berkeley, California United States 94720-1776 (e-mail: jordan@cs.berkeley.edu)

Height-from-Polarisation with Unknown Lighting or Albedo (PDF)

William Smith , Computer Science, The University of York, York, North Yorkshire United Kingdom of Great Britain and Northern Ireland YO10 5GH (e-mail: william.smith@york.ac.uk)
Ravi Ramamoorthi , Computer Science Department, University of California, Berkeley, Berkeley, California United States 94720-1776 (e-mail: ravir@cs.ucsd.edu)
Silvia Tozza , Department of Mathematics, Sapienza - Universita di Roma, Rome, Lazio Italy (e-mail: tozza@mat.uniroma1.it)

Material Classification from Time-of-Flight Distortions (PDF)

Kenichiro Tanaka , Graduate School of Science and Technology, Nara Institute of Science and Technology, 12708 Ikoma, Nara Japan (e-mail: ktanaka@is.naist.jp)
Yasuhiro Mukaigawa , Graduate School of Science and Technology, NAIST, Ikoma, Nara Japan (e-mail: mukaigawa@is.naist.jp)
Takuya Funatomi , Information Science, NAIST, Ikoma, Nara Japan (e-mail: funatomi@is.naist.jp)
Hiruyuki Kubo , Graduate School of Information Science, Nara Institute of Science and Technology, Ikoma, Nara Japan (e-mail: hkubo@is.naist.jp)
Yasuyuki Matsushita , Graduate School of Information Science and Technology, Osaka University, Suita, Osaka Japan (e-mail: yasumat@ist.osaka-u.ac.jp)
Yasushi Yagi , Institute of Scientific and Industrial Research, Osaka University, Ibaraki, Osaka Japan (e-mail: yagi@am.sanken.osaka-u.ac.jp)

Segmentation of Laser Point Clouds in Urban Areas by a Modified Normalized Cut Method (Abstract)

Avishek Dutta , Vermessung, Informatik und Mathematik, Hochschule fur Technik Stuttgart, 38940 Stuttgart, Baden-Wuerttemberg Germany 70174 (e-mail: avishek.dutta@hft-stuttgart.de)
Johannes Engels , Vermessung, Informatik und Mathematik, Hochschule fur Technik Stuttgart, 38940 Stuttgart, Baden-Wuerttemberg Germany (e-mail: johannes.engels@hft-stuttgart.de)
Michael Hahn , Vermessung, Informatik und Mathematik, Hochschule fur Technik Stuttgart, 38940 Stuttgart, Baden-Wuerttemberg Germany (e-mail: michael.hahn@hft-stuttgart.de)

Motion Segmentation via Generalized Curvatures (Abstract)

Robert Arn , Mathematics, Colorado State University, 3447 Fort Collins, Colorado United States (e-mail: astroarn@gmail.com)
Pradyumna Narayana , Computer Science, Colorado State University, Fort Collins, Colorado United States (e-mail: prady@cs.colostate.edu)
Bruce Draper , Computer Science, Colorado State University, Fort Collins, Colorado United States (e-mail: draper@cs.colostate.edu)
Tegan Emerson , Mathematics, Colorado State University, 3447 Fort Collins, Colorado United States (e-mail: teganemerson@gmail.com)
Michael Kirby , Mathematics, Colorado State University, Fort Collins, Colorado United States 80523 (e-mail: kirby@math.colostate.edu)
Chris Peterson , Mathematics, Colorado State University, 3447 Fort Collins, Colorado United States (e-mail: peterson@math.colostate.edu)

Order-preserving Optimal Transport for Distances between Sequences (Abstract)

Bing Su , Institute of Software, Institute of Software Chinese Academy of Sciences, 53036 Beijing, Beijing China (e-mail: subingats@gmail.com)
Gang Hua , Computer Science, Stevens Institute of Technology, Hoboken, New Jersey United States 07030 (e-mail: ganghua@gmail.com)

Estimating the Number of Correct Matches Using Only Spatial Order (Abstract)

Lior Talker , information systems, University of Haifa Faculty of Natural Sciences, 123474 Haifa, Israel Israel (e-mail: ltalke01@campus.haifa.ac.il)
Yael Moses , Computer Science, Interdisciplinary Center, Herzeliya, Israel Israel 46150 (e-mail: yael@idc.ac.il)
Ilan Shimshoni , Dept. of Information Systems, University of Haifa, Haifa, Israel Israel 31905 (e-mail: ishimshoni@mis.haifa.ac.il)

Capturing the Geometry of Object Categories from Video Supervision (Abstract)

David Novotny , Engineering Science, University of Oxford, Oxford, Oxfordshire United Kingdom of Great Britain and Northern Ireland OX1 3PJ (e-mail: david@robots.ox.ac.uk)
Diane Larlus , Computer Vision Group, Naver Labs Europe, 84341 Meylan, Auvergne-Rhône-Alpes France (e-mail: diane.larlus@naverlabs.com)
Andrea Vedaldi , Engineering Science, Oxford University, Oxford, Oxfordshire United Kingdom of Great Britain and Northern Ireland OX13PJ (e-mail: vedaldi@robots.ox.ac.uk)

Multivariate mixture model for myocardial segmentation combining multi-source images (Abstract)

Xiahai Zhuang , School of Data Science, Fudan University, 12478 Shanghai, Shanghai China (e-mail: zhuangxiahai@163.com)

A Novel Geometric Framework on Gram Matrix Trajectories for Human Behavior Understanding (Abstract)

Anis Kacem , Computer science, IMT Lille-Douai, VILLENEUVE D ASCQ, Nord pas de calais France (e-mail: anis.kacem@telecom-lille.fr)
Mohamed Daoudi , Computer science, IMT Lille-Douai, VILLENEUVE D ASCQ, Nord pas de calais France (e-mail: mohamed.daoudi@univ-lille1.fr)
Boulbaba Ben Amor , Computer science, IMT Lille-Douai, VILLENEUVE D ASCQ, Nord pas de calais France (e-mail: boulbaba.benamor@telecom-lille.fr)
Stefano Berretti , Information Engineering, University of Firenze, Firenze, Tuscany Italy 50139 (e-mail: stefano.berretti@unifi.it)
Juan Carlos Alvarez-Paiva , Mathematics, Universite de Lille 1 UFR de Mathematiques, 214049 Villeneuve d'Ascq, Nord-Pas de Calais France (e-mail: juan-carlos.alvarez-paiva@math.univ-lille1.fr)

Anticipating Where People Will Look Using Adversarial Networks (Abstract)

Mengmi Zhang , Eletrical and Computer Engineering, National University of Singapore, singapore, singapore Singapore 117583 (e-mail: a0091624@u.nus.edu)
Keng Teck Ma , Astar, Institute for Infocomm Research, 68705 Singapore, Singapore Singapore (e-mail: makt@i2r.a-star.edu.sg)
Joohwee Lim , I2R, astar, Institute for Infocomm Research, Singapore, Singapore Singapore (e-mail: joohwee@i2r.a-star.edu.sg)
Qi Zhao , Department of Computer Science and Engineering, University of Minnesota, Twin Cities, Twin Cities, Minnesota United States (e-mail: qzhao@cs.umn.edu)
Jiashi Feng , ECE, National University of Singapore, 37580 Singapore, Singapore Singapore (e-mail: elefjia@nus.edu.sg)

On the Effectiveness of Least Squares Generative Adversarial Networks (Abstract)

Xudong Mao , Computer Science, City University of Hong Kong College of Science and Engineering, 121844 Kowloon, Kowloon Hong Kong (e-mail: xudong.xdmao@gmail.com)
Qing Li , Department of Computer Science, City University of Hong Kong, Hong Kong, HKSAR China 000000 (e-mail: itqli@cityu.edu.hk)
Haoran Xie , Department of Computer Science, City University of Hong Kong, Kowloon, Hong Kong Hong Kong (e-mail: hrxie2@gmail.com)
Raymond Yiu Keung Lau , Information Systems, City University of Hong Kong, Kowloon, Kowloon Hong Kong 0000 (e-mail: raylau@cityu.edu.hk)
Zhen Wang , Automation, Northwestern Polytechnical University, 26487 Xi'an, Shannxi China 710072 (e-mail: zhenwang0@gmail.com)
Stephen Paul Smolley , CodeHatch, CodeHatch Corp., Edmonton, Alberta Canada (e-mail: steve@codehatch.com)

Holistic CNN Compression via Low-rank Decomposition with Knowledge Transfer (Abstract)

Shaohui Lin , Cognitive Science, Xiamen University, Xiamen, Fujian China (e-mail: shaohuilin007@gmail.com)
Rongrong Ji , Cognitive Science, Xiamen University, Xiamen, Fujian China 361005 (e-mail: rrji@xmu.edu.cn)
Chao Chen , Cognitive Science, Xiamen University, Xiamen, Fujian China (e-mail: catInMud@stu.xmu.edu.cn)
Dacheng Tao , School of Information Technologies, University of Technology, Sydney, Sydney, New South Wales Australia (e-mail: Dacheng.Tao@uts.edu.au)
Jiebo Luo , Department of Computer Science, University of Rochester, Rochester, New York United States 14627 (e-mail: jluo@cs.rochester.edu)

Semi-Calibrated Photometric Stereo (Abstract)

DongHyeon Cho , Electrical Engineering, KAIST, Daejeon, Daejeon Korea (the Republic of) (e-mail: cdh12242@gmail.com)
Yasuyuki Matsushita , Graduate School of Information Science and Technology, Osaka University, Osaka, Osaka Japan (e-mail: yasumat@ist.osaka-u.ac.jp)
Yu Wing Tai , youtu research lab, Tencent, HongKong, HongKong Hong Kong (e-mail: yuwing@gmail.com)
In So Kweon , Electrical Engineering, KAIST, Daejeon, Daejeon Korea (the Republic of) (e-mail: iskweon@kaist.ac.kr)

Denoising Prior Driven Deep Neural Network for Image Restoration (Abstract)

Weisheng Dong , School of Electronic Engineering, Xidian University, 47905 Xian, Shaanxi China 710071 (e-mail: wsdong@mail.xidian.edu.cn)
Peiyao Wang , School of Electronic Engineering, Xidian University, 47905 Xian, Shaanxi China (e-mail: peiyw_xdxs@163.com)
Wotao Yin , Department of Mathematics, University of California, Los Angeles, Los Angeles, California United States (e-mail: wotaoyin@math.ucla.edu)
Guangming Shi , School of Electronic Engineering, Xidian University, Xi'an, Shaanxi China (e-mail: gmshi@xidian.edu.cn)

Visual Permutation Learning (Abstract)

Rodrigo Santa Cruz , Research School of Computer Science, The Australian National University, Canberra, Australian Capital Territory Australia 2601 (e-mail: rodrigo.santacruz@anu.edu.au)
Basura Fernando , Research School Of Engineering, The Australian National University, Canberra, Australian Capital Territory Australia (e-mail: basura.fernando@anu.edu.au)
Anoop Cherian , Research, Mitsubishi Electric Research Laboratories, 340008 Cambridge, Massachusetts United States (e-mail: anoop.cherian@anu.edu.au)
Stephen Gould , Research School of Computer Science, Australian National University, Canberra, Australian Capital Territory Australia 0200 (e-mail: stephen.gould@anu.edu.au)

First-Person Activity Forecasting from Video with Online Inverse Reinforcement Learning (Abstract)

Nicholas Rhinehart , Robotics Institute, Carnegie Mellon University, 6612 Pittsburgh, Pennsylvania United States 15213-3815 (e-mail: nrhineha@cs.cmu.edu)
Kris Kitani , Robotics Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania United States (e-mail: kkitani@cs.cmu.edu)

Hyperspectral recovery from RGB images using Gaussian Processes (Abstract)

NAVEED AKHTAR , Computer Science and Software Engineering, The University of Western Australia, Crawley, Western Australia Australia 6009 (e-mail: navid.915@gmail.com)
Ajmal S. Mian , Computer Science, The University of Western Australia, Perth, Western Australia Australia 6009 (e-mail: ajmal.mian@uwa.edu.au)

Rank Minimization for Snapshot Compressive Imaging (Abstract)

Yang Liu , Automation Department, Tsinghua University, 12442 Beijing, Beijing China 100084 (e-mail: y-liu16@mails.tsinghua.edu.cn)
Xin Yuan , Nokia Bell Labs, Nokia Bell Labs, Murray Hill, New Jersey United States (e-mail: xyuan@bell-labs.com)
Jinli Suo , Automation Department, Tsinghua University, Beijing, Beijing China (e-mail: jlsuo@tsinghua.edu.cn)
David Brady , Department of Electrical and Computer Engineering, Duke University, Durham, North Carolina United States (e-mail: David.Brady@duke.edu)
Qionghai Dai , Automation Department, Tsinghua University, Beijing, Beijing China (e-mail: qhdai@tsinghua.edu.cn)

Shallowing Deep Networks: Layer-wise Pruning based on Feature Representations (Abstract)

Shi Chen , Department of Computer Science and Engineering, University of Minnesota System, 311816 Minneapolis, Minnesota United States (e-mail: chen4595@umn.edu)
Qi Zhao , Department of Computer Science and Engineering, University of Minnesota, Twin Cities, Twin Cities, Minnesota United States (e-mail: qzhao@cs.umn.edu)

SPFTN: A Joint Learning Framework for Localizing and Segmenting Objects in Weakly Labeled Videos (Abstract)

Dingwen Zhang , School of Automation, Northwestern Polytechnical University, Xi'an, Shaanxi China (e-mail: zdw2006yyy@mail.nwpu.edu.cn)
Junwei Han , School of Automation, Northwestern Polytechnical University, Xi'an, Shaanxi China (e-mail: junweihan2010@gmail.com)
Le Yang , School of Automation, Xi'an, Shaanxi China (e-mail: nwpuyangle@gmail.com)
Dong Xu , School of Electrical and Information Engineering, The University of Sydney, Sydney, New South Wales Australia 2006 (e-mail: dong.xu@sydney.edu.au)

Detecting Coherent Groups in Crowd Scenes by Multiview Clustering (Abstract)

Qi Wang , School of Computer Science, Unmanned System Research Institute, Optical Imagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, 26487 Xi'an, shaanxi China (e-mail: crabwq@gmail.com)
Mulin Chen , School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, 26487 Xi'an, Shaanxi China (e-mail: chenmulin001@gmail.com)
Feiping Nie , School of Computer Science, Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, 26487 Xi'an, Shaanxi China (e-mail: feipingnie@gmail.com)
Xuelong Li , Center for Center for Optical Imagery Analysis and Learning (OPTIMAL), Xi'an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi'an, Shaanxi China (e-mail: xuelong_li@opt.ac.cn)

Motion Segmentation & Multiple Object Tracking by Correlation Co-Clustering (Abstract)

Margret Keuper , Business Informatics and Mathematics, University of Mannheim, Mannheim, BW Germany (e-mail: keuper@informatik.uni-freiburg.de)
Siyu Tang , -, Max-Planck-Institut fur Intelligente Systeme, 28325 Tuebingen, Baden-Württemberg Germany (e-mail: stang@tuebingen.mpg.de)
Bjorn Andres , SEAS, Harvard University, Cambridge, Massachusetts United States (e-mail: bjoern@andres.sc)
Thomas Brox , Computer Science, University of Freiburg, Freiburg, Baden-Wuerttemberg Germany (e-mail: brox@cs.uni-freiburg.de)
Bernt Schiele , computer science, MPI Informatics, Saabrücken, Saarland Germany (e-mail: schiele@mpi-inf.mpg.de)

PCL: Proposal Cluster Learning for Weakly Supervised Object Detection (Abstract)

Peng Tang , School of Electronic Information and Communications, Huazhong University of Science and Technology, 12443 Wuhan, Hubei China (e-mail: pengtang@hust.edu.cn)
Xinggang Wang , School of Electronic Information and Communications, Huazhong University of Science and Technology, 12443 Wuhan, Hubei China (e-mail: xgwang@hust.edu.cn)
Song Bai , Department of Engineering Science, University of Oxford, Oxford, Oxford United Kingdom of Great Britain and Northern Ireland (e-mail: songbai.site@gmail.com)
Wei Shen , School of Communication and Information Engineering, Shanghai University, 34747 Shanghai, HuBei China (e-mail: shenwei1231@gmail.com)
Xiang Bai , School of Electronic Information and Communications, HUST, Wuhan, Hubei China (e-mail: xbai@hust.edu.cn)
Wenyu Liu , School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, HuBei China (e-mail: liuwy@hust.edu.cn)
Alan Loddon Yuille , Department of Computer Science, Johns Hopkins University, 1466 Baltimore, Maryland United States (e-mail: alan.l.yuille@gmail.com)

Approximate Fisher Information Matrix to Characterise the Training of Deep Neural Networks (Abstract)

Zhibin Liao , School of Computer Science, University of Adelaide Faculty of Engineering Computer and Mathematical Sciences, 95556 Adelaide, South Australia Australia (e-mail: zhibin.liao89@gmail.com)
Tom Drummond , ECSE, Monash University, Clayton, Victoria Australia (e-mail: Tom.Drummond@monash.edu)
Ian Reid , Department of Engineering Science, University of Oxford, Oxford, Oxon United Kingdom of Great Britain and Northern Ireland OX1 3PJ (e-mail: ian.reid@adelaide.edu.au)
Gustavo Carneiro , Department of Computer Science, University of Adelaide Faculty of Engineering Computer and Mathematical Sciences, 95556 Adelaide, South Australia Australia (e-mail: gustavo.carneiro@adelaide.edu.au)

Neural Machine Translation with Deep Attention (Abstract)

Biao Zhang , Software School of Xiamen University, Xiamen University, 12466 Xiamen, Fujian China 361005 (e-mail: zb@stu.xmu.edu.cn)
Deyi Xiong , Soochow University, Suzhou, Jiangsu China (e-mail: dyxiong@suda.edu.cn)
Jinsong Su , Software School of Xiamen University, Xiamen, Fujian China (e-mail: jssu@xmu.edu.cn)

Learning Compact Features for Human Activity Recognition via Probabilistic First-Take-All (Abstract)

Jun Ye , Computer Science, University of Central Florida, Orlando, Florida United States (e-mail: jye@cs.ucf.edu)
Guojun Qi , Computer Science, University of Central Florida, 6243 Orlando, Florida United States (e-mail: guojun.qi@ucf.edu)
Naifan Zhuang , Computer Science, university of central florida, Orlando, Florida United States (e-mail: zhuangnaifan@knights.ucf.edu)
Hao Hu , Departrment of Computer Science, University of Central Florida, 6243 Orlando, Florida United States 32816-2368 (e-mail: hao_hu@knights.ucf.edu)
Kien A. Hua , Electrical Engineering & Computer Science, University of Central Florida, Orladno, Florida United States (e-mail: kienhua@eecs.ucf.edu)

High-Fidelity Monocular Face Reconstruction based on an Unsupervised Model-based Face Autoencoder (Abstract)

Ayush Tewari , Computer Graphics, Max-Planck-Institut fur Informatik, 28323 Saarbrucken, Saarland Germany 66123 (e-mail: atewari@mpi-inf.mpg.de)
Michael Zollhoefer , Computer Graphics, Stanford University, Stanford, California United States (e-mail: zollhoefer@cs.stanford.edu)
Florian Bernard , Computer Graphics, Max-Planck-Institut fur Informatik, 28323 Saarbrucken, Saarland Germany (e-mail: f.bernardpi@gmail.com)
Pablo Garrido , Imaging Science Lab, Technicolor Rennes Research and Innovation, 399444 Cesson Sevigne, Bretagne France (e-mail: pablo.garrido.adrian@gmail.com)
Hyeongwoo Kim , Computer Graphics, Max Planck Institute for Informatics, Saarbruecken, Saarland Germany (e-mail: hyeongwoo.kim@mpi-inf.mpg.de)
Patrick Perez , Imaging Science Lab, Technicolor Rennes Research and Innovation, 399444 Cesson Sevigne, Bretagne France (e-mail: Patrick.Perez@technicolor.com)
Christian Theobalt , Graphics, Vision and Video, Max-Planck-Institut Informatik, Saarbruecken, Saarland Germany (e-mail: theobalt@mpi-inf.mpg.de)

Persistence Paths and Signature Features in Topological Data Analysis (Abstract)

Ilya Chevyrev , Mathematical Institute, University of Oxford Mathematical Physical and Life Sciences Division, 98592 Oxford, Oxfordshire United Kingdom of Great Britain and Northern Ireland OX1 3PD (e-mail: chevyrev@maths.ox.ac.uk)
Vidit Nanda , Mathematical Institute, University of Oxford Mathematical Physical and Life Sciences Division, 98592 Oxford, Oxfordshire United Kingdom of Great Britain and Northern Ireland (e-mail: nanda@maths.ox.ac.uk)
Harald Oberhauser , Mathematics, University of Oxford Mathematical Physical and Life Sciences Division, 98592 Oxford, Oxfordshire United Kingdom of Great Britain and Northern Ireland OX2 6GG (e-mail: oberhauser@maths.ox.ac.uk)

Flexible High-Dimensional Unsupervised Learning with Missing Data (Abstract)

Yuhong Wei , Mathematics and Statistics, McMaster University, Hamilton, Ontario Canada (e-mail: weiy38@math.mcmaster.ca)
Yang Tang , Mathematics and Statistics, McMaster University, Hamilton, Ontario Canada (e-mail: yang.tang@math.mcmaster.ca)
Paul David McNicholas , Mathematics and Statistics, McMaster University, Hamilton, Ontario Canada (e-mail: mcnicholas@math.mcmaster.ca)

Bayesian Neural Networks with Weight Sharing Using Dirichlet Processes (Abstract)

Wolfgang Roth , Signal Processing and Speech Communication Lab, Technische Universitat Graz, 27253 Graz, Styria Austria (e-mail: roth@tugraz.at)
Franz Pernkopf , Institute of Signal Processing and Speech Communication, Graz University of Technology, Graz, Styria Austria 8010 (e-mail: pernkopf@tugraz.at)

Visibility Constrained Generative Model for Depth-based 3D Facial Pose Tracking (Abstract)

Lu Sheng , Electronic Engineering, The Chinese University of Hong Kong, Hong Kong, Hong Kong Hong Kong (e-mail: lsheng@ee.cuhk.edu.hk)
Jianfei Cai , School of Computer Engineering, Nanyang Technological University, Singapore, Singapore Singapore (e-mail: asjfcai@ntu.edu.sg)
Tat-Jen Cham , School of Computer Engineering, Nanyang Technological University, Singapore, Singapore Singapore 639798 (e-mail: astjcham@ntu.edu.sg)
Vladimir Pavlovic , SEQAM Lab, Rutgers University, Piscataway, New Jersey United States 08854 (e-mail: vladimir@cs.rutgers.edu)
KingNgi Ngan , Electronic Engineering, The Chinese University of Hong Kong, Hong Kong, Hong Kong Hong Kong (e-mail: knngan@ee.cuhk.edu.hk)

Generalized Latent Multi-View Subspace Clustering (Abstract)

Changqing Zhang , School of Computer Science and Technology, Tianjin University, Tianjin, Tianjin China (e-mail: zhangchangqing@tju.edu.cn)
Huazhu Fu , Institute for Infocomm Research, Agency for Science, Technology and Research, Singapore, Singapore Singapore (e-mail: huazhufu@gmail.com)
Qinghua Hu , Computer Science and Technology, Tianjin University, Tianjin, Tianjin China (e-mail: huqinghua@tju.edu.cn)
Xiaochun Cao , State Key Laboratory of Information Security, Institute of Information Engineering, Chinese Academy of Sciences, Beijing, Beijing China (e-mail: caoxiaochun@iie.ac.cn)
Yuan Xie , Institute of Automation, Chinese Academy of Sciences, beijing, beijing China (e-mail: yuan.xie@ia.ac.cn)
Dacheng Tao , Faculty of Engineering and Information Technology, University of Technology, Sydney, Ultimo, New South Wales Australia (e-mail: dacheng.tao@gmail.com)
Dong Xu , School of Electrical and Information Engineering, The University of Sydney, Sydney, New South Wales Australia (e-mail: dong.xu@sydney.edu.au)

Sparse One-Grab Sampling with Probabilistic Guarantees (Abstract)

Maryam Jaberi , Computer Science, University of Central Florida, 6243 Orlando, Florida United States 32816-2362 (e-mail: mjaberi@cs.ucf.edu)
Marianna Pensky , Mathematics, University of Central Florida, 6243 Orlando, Florida United States (e-mail: marianna.pensky@ucf.edu)
Hassan Foroosh , Computer Science, University of Central Florida, Orlando, Florida United States 32816 (e-mail: foroosh@cs.ucf.edu)

Efficient Inter-Geodesic Distance Computation and Fast Classical Scaling (Abstract)

Gil Shamai , Electrical Engineering, Technion, Haifa, Israel Israel 32000 (e-mail: gil.shamai@gmail.com)
Michael Zibulevsky , Computer Science, Technion, Haifa, Israel Israel (e-mail: mzib@cs.technion.ac.il)
Ron Kimmel , Computer Science, Technion Israel Institute of Technology, Haifa, Israel Israel (e-mail: ron@cs.technion.ac.il)

Pictionary-style word-guessing on hand-drawn object sketches: dataset, analysis and deep network models (Abstract)

Ravi Kiran Sarvadevabhatla , Computational and Data Sciences, Indian Institute of Science, 29120 BANGALORE, KARNATAKA India 560012 (e-mail: ksravi@iisc.ac.in)
Shiv Surya , Computational and Data Sciences, Indian Institute of Science, 29120 Bangalore, Karnataka India 560012 (e-mail: shiv.surya314@gmail.com)
Trisha Mittal , Information Technology, International Institute of Information Technology, Bangalore, Bangalore, Karnataka India (e-mail: mittaltrisha22@gmail.com)
Venkatesh Babu Radhakrishnan , Department of Computational and Data Sciences, Indian Institute of Science, BANGALORE, Karnataka India 560012 (e-mail: venky@iisc.ac.in)

Discrete-Continuous Transformation Matching for Dense Semantic Correspondence (Abstract)

Seungryong Kim , the School of Electrical and Electronic Engineering, Yonsei University, Seoul, Seodaemun-Gu Korea (the Republic of) (e-mail: srkim89@yonsei.ac.kr)
Dongbo Min , the Department of Computer Science and Engineering, Chungnam National University, Korea, Daejeon Korea (the Republic of) (e-mail: dbmin99@gmail.com)
Stephen Lin , Internet Graphics group, Microsoft Research Asia, Beijing, Beijing China 100080 (e-mail: stevelin@microsoft.com)
Kwanghoon Sohn , the School of Electrical and Electronic Engineering, Yonsei University, Seoul, Seodaenum-Gu Korea (the Republic of) (e-mail: khsohn@yonsei.ac.kr)

Runtime Network Routing for Efficient Image Classification (Abstract)

Yongming Rao , Department of Automation, Tsinghua University, 12442 Beijing, Beijing China (e-mail: raoyongming95@gmail.com)
Jiwen Lu , Department of Automation, Tsinghua University, Beijing, Beijing China (e-mail: lujiwen@tsinghua.edu.cn)
Ji Lin , Department of Automation, Tsinghua University, 12442 Beijing, Beijing China (e-mail: lin-j14@mails.tsinghua.edu.cn)
Jie Zhou , Department of Automation, Tsinghua University, Beijing, Beijing China 100084 (e-mail: jzhou@tsinghua.edu.cn)

Robust Kronecker Component Analysis (Abstract)

Mehdi Bahri , Department of Computing, Imperial College London, London, Greater London United Kingdom of Great Britain and Northern Ireland SW7 2RH (e-mail: mehdi.bahri15@imperial.ac.uk)
Yannis Panagakis , Computing, Imperial College London, London, Greater London United Kingdom of Great Britain and Northern Ireland (e-mail: i.panagakis@imperial.ac.uk)
Stefanos P. Zafeiriou , Computing, Imperial College London, London, London United Kingdom of Great Britain and Northern Ireland SW7 2AZ (e-mail: s.zafeiriou@imperial.ac.uk)

Context-Aware Query Selection for Active Learning in Event Recognition (Abstract)

Mahmudul Hasan , Computer Science and Engineering, University of California, Riverside, Riverside, California United States 92507 (e-mail: mhasa004@ucr.edu)
Sujoy Paul , Electrical and Computer Engineering, University of California Riverside, 8790 Riverside, California United States (e-mail: spaul003@ucr.edu)
Anastasios I. Mourikis , Electrical and Computer Engineering, University of California Riverside, 8790 Riverside, California United States (e-mail: mourikis@ee.ucr.edu)
Amit K. Roy-Chowdhury , Electrical Engineering, University of California, Riverside, Riverside, California United States 92521 (e-mail: amitrc@ee.ucr.edu)

Richer Convolutional Features for Edge Detection (Abstract)

Yun Liu , CCCE & CS, Nankai University, 12538 Tianjin, Tianjin China (e-mail: nk12csly@mail.nankai.edu.cn)
Ming-Ming Cheng , College of Computer and Control, Nankai University, Tianjin, Tianjin China (e-mail: cmm@nankai.edu.cn)
Xiaowei Hu , Computer Science, Nankai University, 12538 Tianjin, Tianjin China 300071 (e-mail: xiaowei.hu@mail.nankai.edu.cn)
Jia-Wang Bian , Computer Science, Nankai University, 12538 Tianjin, Tianjin China (e-mail: jiawang.bian@gmail.com)
Le Zhang , Advanced Digital Sciences Center, Advanced Digital Sciences Center at Illinois, 503209 Singapore, Singapore Singapore (e-mail: zhang.le@adsc.com.sg)
Xiang Bai , Dept. of Electronics and Information Engineering, HUST, Wuhan, Hubei China (e-mail: xbai@hust.edu.cn)
Jinhui Tang , School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu China (e-mail: jinhuitang@njust.edu.cn)

Late Fusion Incomplete Multi-view Clustering (Abstract)

Xinwang Liu , School of Computer, National University of Defense Technology, 58294 Changsha, Hunan China 410073 (e-mail: xinwangliu@nudt.edu.cn)
Xinzhong Zhu , College of Mathematics, Physics and Information Engineering, Zhejiang Normal University, 66344 Jinhua, Zhejiang China (e-mail: zxz@zjnu.edu.cn)
Miaomiao Li , Department of Computer, Changsha College, Changsha, HUNAN China (e-mail: miaomiaolinudt@gmail.com)
Lei Wang , School of Computer Science and Software Engineering, University of Wollongong, 2522, New South Wales Australia (e-mail: leiw@uow.edu.au)
Chang Tang , School of Computer Science, China University of Geosciences, Wuhan, Hubei China (e-mail: tangchang@cug.edu.cn)
Jianping Yin , School of Computer Science, Dongguan University of Technology, 74549 Dongguan, Guangdong China (e-mail: jpyin@dgut.edu.cn)
Dinggang Shen , Department of Radiology, UNC Chapel Hill, Chapel Hill, North Carolina United States (e-mail: dgshen@med.unc.edu)
Huaimin Wang , School of Computer, National University of Defense Technology, Changsha, Hunan China (e-mail: whm_2@163.com)
Wen Gao , CS, Peking University, Beijing, Beijing China (e-mail: wgao@pku.edu.cn)

Cooperative Learning of Descriptor and Generator Networks (Abstract)

Jianwen Xie , Statistics, University of California Los Angeles, 8783 Los Angeles, California United States (e-mail: jianwen@ucla.edu)
Yang Lu , Statistics, UCLA, Los Angeles, California United States (e-mail: yanglv@ucla.edu)
Ruiqi Gao , Statistics, UCLA, Los Angeles, California United States (e-mail: ruiqigao@ucla.edu)
Song-Chun Zhu , Statistics and Computer Science, University of California, Los Angeles, Los Angeles, California United States 90095 (e-mail: sczhu@stat.ucla.edu)
Ying Nian Wu , Statistics, UCLA, Los Angeles, California United States 90095 (e-mail: ywu@stat.ucla.edu)

Person Recognition in Personal Photo Collections (Abstract)

Seong Joon Oh , Clova ML, LINE Corporation, Seongnam, Gyeonggi Korea (the Republic of) (e-mail: coallaoh@gmail.com)
Rodrigo Benenson , Google Research, Google Zürich, Zürich, Zürich Switzerland (e-mail: rodrigo.benenson@gmail.com)
Mario Fritz , Faculty, CISPA Helmholtz Center i.G., Saarbrücken, Saarland Germany (e-mail: fritz@cispa.saarland)
Bernt Schiele , Computer Vision and Multimodal Computing, MPI Informatics, Saabrücken, Saarland Germany (e-mail: schiele@mpi-inf.mpg.de)

Numerical Quadrature for Probabilistic Policy Search (Abstract)

Julia Vinogradska , Bosch Center for Artificial Intelligence, Bosch Center for Artificial Intelligence, Renningen, Baden-Württemberg Germany (e-mail: julia.vinogradska@de.bosch.com)
Bastian Bischoff , Bosch Center for Artificial Intelligence, Renningen, BW Germany (e-mail: bastian.bischoff@de.bosch.com)
Jan Achterhold , Bosch Center for Artificial Intelligence, Renningen, BW Germany (e-mail: mail@janachterhold.de)
Torsten Koller , Bosch Center for Artificial Intelligence, Renningen, BW Germany (e-mail: Koller.Torsten@web.de)
Jan Peters , Fachbereich Informatik, Intelligent Autnonomous Systems, TU Darmstadt, Darmstadt, Hessen Germany (e-mail: mail@jan-peters.net)

iDeLog: Iterative Dual Spatial and Kinematic Extraction of Sigma-Lognormal Parameters (Abstract)

Miguel A. A. Ferrer , Señales y comunicaciones, Universidad de Las Palmas de Gran Canaria, Las Palmas de Gran Canaria, Las Palmas Spain E35017 (e-mail: mferrer@dsc.ulpgc.es)
Moises Diaz , Instituto Universitario para el Desarrollo Tecnológico y la Innovación en Comunicaciones, Universidad de Las Palmas de Gran Canaria, Las Palmas de Gran Canaria, Las Palmas Spain 35017 (e-mail: mdiazc@unidam.es)
Cristina A. Carmona , Instituto Universitario para el Desarrollo Tecnológico y la Innovación en Comunicaciones, Universidad de Las Palmas de Gran Canaria, Las Palmas de Gran Canaria, Las Palmas Spain 35017 (e-mail: ccarmona@idetic.eu)
Rejean Plamondon , Laboratoire Scribens, Ecole Polytechnique, Montreal Quebec, Quebec Canada H3C 3A7 (e-mail: rejean.plamondon@polymtl.ca)

Inverse Visual Question Answering: A New Benchmark and VQA Diagnosis Tool (Abstract)

Feng Liu , School of Automation, Southeast University, 12579 Nanjing, Jiangsu China 210096 (e-mail: liufeng@seu.edu.cn)
Tao Xiang , EECS, Queen Mary, University of London, London, London United Kingdom of Great Britain and Northern Ireland (e-mail: t.xiang@qmul.ac.uk)
Timothy M. Hospedales , EECS, Queen Mary, University of London, London, London United Kingdom of Great Britain and Northern Ireland (e-mail: t.hospedales@ed.ac.uk)
Wankou Yang , School of Automation, Southeast University, Nanjing, Jiangsu China (e-mail: wkyang@seu.edu.cn)
Changyin Sun , School of Automation, Southeast University, 12579 Nanjing, Jiangsu China (e-mail: cysun@seu.edu.cn)

Single Image Dehazing Using Haze-Lines (Abstract)

Dana Berman , School of Electrical Engineering, Tel Aviv University, Tel Aviv, Israel Israel (e-mail: dana.menaker@gmail.com)
Tali Treibitz , Leon H. Charney School of Marine Sciences, University of Haifa, Haifa, Israel Israel (e-mail: ttreibitz@univ.haifa.ac.il)
Shai Avidan , School of Electrical Engineering, Tel Aviv University, Tel Aviv, Israel Israel (e-mail: avidan@eng.tau.ac.il)

Adversarial Action Prediction Networks (Abstract)

Yu Kong , College of Computing and Information Sciences, Rochester Institute of Technology, 6925 Rochester, New York United States (e-mail: yu.kong@rit.edu)
Zhiqiang Tao , Electrical and Computer Engineering, Northeastern University, Boston, Massachusetts United States (e-mail: zqtao@ece.neu.edu)
Yun Fu , ECE, Northeastern University, Boston, Massachusetts United States (e-mail: yunfu@ece.neu.edu)

Deep Variational and Structural Hashing (Abstract)

Venice Erin Liong , Interdisciplinary Graduate School, Nanyang Technological University, Singapore, Singapore Singapore (e-mail: veniceer001@e.ntu.edu.sg)
Jiwen Lu , Department of Automation, Tsinghua University, Beijing, Beijing China 100084 (e-mail: lujiwen@tsinghua.edu.cn)
Ling-Yu Duan , Institute of Digital Media, Peking University, Beijing, Beijing China (e-mail: lingyu@pku.edu.cn)
Yappeng Tan , School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore Singapore (e-mail: EYPTan@ntu.edu.sg)

The Lovász Hinge: A Novel Convex Surrogate for Submodular Losses (Abstract)

Jiaqian Yu , SAIT China lab, Samsung R&D Institute China-Beijing, Beijing, Beijing China (e-mail: jiaqian.yu@centralesupelec.fr)
Matthew B. Blaschko , Department of Electrical Engineering (ESAT), KU Leuven, Leuven, Flemish Brabant Belgium (e-mail: matthew.blaschko@esat.kuleuven.be)

ADMM-CSNet: A Deep Learning Approach for Image Compressive Sensing (Abstract)

Yan Yang , Institute for Information and System Sciences, Xi'an Jiaotong University, 12480 Xi'an, Shaanxi China 710049 (e-mail: yangyan92@stu.xjtu.edu.cn)
Jian Sun , School of Science, Xi'an Jiaotong University, Xi'an, Shaanxi China 710049 (e-mail: jiansun@mail.xjtu.edu.cn)
HUIBIN LI , School of Mathematics and Statistics, Xi'An JiaoTong University, XI AN, SHAAN XI China (e-mail: huibinli@mail.xjtu.edu.cn)
Zongben Xu , Institute for Information and System Sciences, Xi'an Jiaotong University, 12480 Xi'an, Shaanxi China 710049 (e-mail: zbxu@mail.xjtu.edu.cn)

Mutually Guided Image Filtering (Abstract)

Xiaojie Guo , State Key Lab of Information Security, Institute of Information Engineering, Chinese Academy of Sciences, Beijing, Beijing China (e-mail: xj.max.guo@gmail.com)
Yu Li , ADSC, Advanced Digital Sciences Center, Singapore, Singapore Singapore (e-mail: ian.li.liyu@gmail.com)
Jiayi Ma , Electronic Information School, Wuhan University, 12390 Wuhan, Hubei China 430072 (e-mail: jyma2010@gmail.com)
Haibin Ling , Computer and Information Sciences, Temple University, Philadelphia, Pennsylvania United States (e-mail: hbling@temple.edu)

Image and Sentence Matching via Semantic Concepts and Order Learning (Abstract)

Yan Huang , National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, Bejing China (e-mail: yhuang@nlpr.ia.ac.cn)
Qi Wu , School of Computer Science, The University of Adelaide, Adelaide, South Australia Australia (e-mail: qi.wu01@adelaide.edu.au)
Wei Wang , Institute of Automation, Chinese Academy of Sciences, Beijing, Beijing China (e-mail: wangwei@nlpr.ia.ac.cn)
Liang Wang , Institute of Automation, Chinese Academy of Sciences, Beijing, Beijing China (e-mail: wangliang@nlpr.ia.ac.cn)

Open Set Domain Adaptation for Image and Action Recognition (Abstract)

Pau Panareda Busto , Computer Vision Group, University Bonn, Bonn, North Rhine-Westphalia Germany (e-mail: s6papana@uni-bonn.de)
Ahsan Iqbal , Computer Vision Group, University Bonn, Bonn, North Rhine-Westphalia Germany (e-mail: iqbalm@iai.uni-bonn.de)
Juergen Gall , Computer Vision Group, University of Bonn, Bonn, North Rhine-Westphalia Germany (e-mail: gall@iai.uni-bonn.de)

Face-from-Depth for Head Pose Estimation on Depth Images (Abstract)

Guido Borghi , DIEF, Universita degli Studi di Modena e Reggio Emilia Dipartimento di Ingegneria Enzo Ferrari, 204488 Modena, Modena Italy 41125 (e-mail: guido.borghi@unimore.it)
Matteo Fabbri , DIEF, Universita degli Studi di Modena e Reggio Emilia Dipartimento di Ingegneria Enzo Ferrari, 204488 Modena, Emilia-Romagna Italy (e-mail: matteo.fabbri@unimore.it)
Roberto Vezzani , DIEF, Universita degli Studi di Modena e Reggio Emilia Dipartimento di Ingegneria Enzo Ferrari, 204488 Modena, Emilia-Romagna Italy (e-mail: roberto.vezzani@unimore.it)
simone calderara , DII, University of Modena and Reggio Emilia, Modena, MO Italy 41125 (e-mail: simone.calderara@unimore.it)
Rita Cucchiara , DIEF, University of Modena and Reggio Emilia, Modena, MO Italy 41100 (e-mail: rita.cucchiara@unimore.it)

A Region-based Gauss-Newton Approach to Real-Time Monocular Multiple Object Tracking (Abstract)

Henning Tjaden , Computer Science, Hochschule RheinMain, 38948 Wiesbaden, Hessen Germany (e-mail: henning.tjaden@hs-rm.de)
Ulrich Schwanecke , Computer Science, RheinMain University of Applied Science, Wiesbaden, Hessen Germany (e-mail: ulrich.schwanecke@hs-rm.de)
Elmar Schomer , Computer Science, University Mainz, Mainz, RLP Germany (e-mail: schoemer@uni-mainz.de)
Daniel Cremers , Department of Computer Science, TU München, Munich, Bayern Germany 85748 (e-mail: cremers@tum.de)

Joint Face Alignment and 3D Face Reconstruction with Application to Face Recognition (Abstract)

Feng Liu , College of Computer Science, Sichuan University, 12530 Chengdu, Sichuan China (e-mail: liuf1989@yeah.net)
Qijun Zhao , College of Computer Science, Chengdu, Sichuan China (e-mail: qjzhao@scu.edu.cn)
xiaoming Liu , Computer Science and Engineering, Michigan State University, Okemos, Michigan United States 48864 (e-mail: liuxm@cse.msu.edu)
Dan Zeng , College of Computer Science, Chengdu, Sichuan China (e-mail: zengdan_scu@126.com)

Deep Neural Network Compression by In-Parallel Pruning-Quantization (Abstract)

Frederick Tung , Computing Science, Simon Fraser University, 1763 Burnaby, British Columbia Canada (e-mail: ftung@sfu.ca)
Greg Mori , Computing Science, Simon Fraser University, Burnaby, British Columbia Canada V5A 1S6 (e-mail: mori@cs.sfu.ca)

Learning Reasoning-Decision Networks for Robust Face Alignment (Abstract)

Hao Liu , Information Engineering, Ningxia University, Yinchuan, Ningxia China 750021 (e-mail: liuhao@nxu.edu.cn)
Jiwen Lu , Department of Automation, Tsinghua University, Beijing, Beijing China 100084 (e-mail: lujiwen@tsinghua.edu.cn)
Minghao Guo , Department of Automation, Tsinghua University, 12442 Beijing, Beijing China (e-mail: gmh14@mails.tsinghua.edu.cn)
Suping Wu , School of Information Engineering, Ningxia University, 56693 Yinchuan, Ningxia China (e-mail: pswuu@nxu.edu.cn)
Jie Zhou , Department of Automation, Tsinghua University, Beijing, Beijing China 100084 (e-mail: jzhou@tsinghua.edu.cn)

Baselines Extraction from Curved Document Images via Slope Fields Recovery (Abstract)

Gaofeng MENG , Chinese Academy of Sciences, Institution of Automation, Beijing, Beijing China (e-mail: gfmeng@nlpr.ia.ac.cn)
Chunhong Pan , National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, Beijing China (e-mail: chpan@nlpr.ia.ac.cn)
Shiming XIANG , Chinese Academy of Sciences, Institution of Automation, Beijing, Beijing China (e-mail: smxiang@nlpr.ia.ac.cn)
Ying Wu , EECS, Northwestern University, Evanston, Illinois United States (e-mail: yingwu@eecs.northwestern.edu)

Unsupervised Person Re-identification by Deep Asymmetric Metric Embedding (Abstract)

Hong-Xing Yu , School of Data and Computer Science, SUN YAT-SEN University, Guangzhou, Guangdong China (e-mail: xKoven@gmail.com)
Ancong Wu , School of Electronic Information and Technology, SUN YAT-SEN University, Guangzhou, Guangdong China (e-mail: wuancong@mail2.sysu.edu.cn)
Wei-Shi Zheng , Department of Computer Science, SUN YAT-SEN University, Guangzhou, Guangdong China (e-mail: wszheng@ieee.org)

The whole is more than its parts? From explicit to implicit pose normalization (PDF)

Marcel Simon , Department of Mathematics and Computer Science, Friedrich-Schiller-Universitat Jena, 9378 Jena, Thuringia Germany 07743 (e-mail: marcel.simon@uni-jena.de)
Erik Rodner , Computer Vision Group, University of Jena, Jena, Thuringia Germany 07743 (e-mail: Erik.Rodner@uni-jena.de)
Trevor Darrell , EECS / ICSI, UC Berkeley, berkeley, California United States 94704 (e-mail: trevor@eecs.berkeley.edu)
Joachim Denzler , Department of Mathematics and Computer Science, Friedrich-Schiller-University Jena, Jena, Thuringia Germany (e-mail: joachim.denzler@uni-jena.de)

Tracking-by-Fusion via Gaussian Process Regression Extended to Transfer Learning (Abstract)

Jin Gao , CAS Center for Excellence in Brain Science and Intelligence Technology, National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, Beijing China (e-mail: jin.gao@nlpr.ia.ac.cn)
Qiang Wang , CAS Center for Excellence in Brain Science and Intelligence Technology, National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, Beijing China (e-mail: qiang.wang@nlpr.ia.ac.cn)
Junliang Xing , CAS Center for Excellence in Brain Science and Intelligence Technology, National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, Beijing China (e-mail: jlxing@nlpr.ia.ac.cn)
Haibin Ling , Department of Computer and Information Sciences, Temple University, Philadelphia, Pennsylvania United States (e-mail: hbling@temple.edu)
Weiming Hu , CAS Center for Excellence in Brain Science and Intelligence Technology, National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, Beijing China 100080 (e-mail: wmhu@nlpr.ia.ac.cn)
Stephen John Maybank , Computer Science and Information Systems, Birkbeck College, London, Berkshire United Kingdom of Great Britain and Northern Ireland WC1E 7HX (e-mail: sjmaybank@dcs.bbk.ac.uk)

A Hybrid RNN-HMM Approach for Weakly Supervised Temporal Action Segmentation (PDF)

Hilde Kuehne , Computer Vision Group, University of Bonn, Bonn, NRW Germany (e-mail: kuehne@iai.uni-bonn.de)
Alexander Richard , Computer Vision Group, University of Bonn, Bonn, NRW Germany (e-mail: richard@iai.uni-bonn.de)
Juergen Gall , Computer Vision Group, University of Bonn, Bonn, NRW Germany (e-mail: gall@iai.uni-bonn.de)

Photometric Stereo in Participating Media Using an Analytical Solution for Shape-Dependent Forward Scatter (Abstract)

Yuki Fujimura , Graduate School of Informatics, Kyoto University, Kyoto, Kyoto Japan (e-mail: fujimura@mm.media.kyoto-u.ac.jp)
Masaaki Iiyama , Academic Center for Computing and Media Studies, Kyoto University, Kyoto, Kyoto Japan (e-mail: iiyama@mm.media.kyoto-u.ac.jp)
Atsushi Hashimoto , Graduate School of Education, Kyoto University, Kyoto, Kyoto Japan (e-mail: a_hasimoto@mm.media.kyoto-u.ac.jp)
Michihiko Minoh , Academic Center for Computing and Media Studies, Kyoto University, Kyoto, Kyoto Japan (e-mail: minoh@mm.media.kyoto-u.ac.jp)

Deep Audio-visual Speech Recognition (Abstract)

Triantafyllos Afouras , Engineering Science, University of Oxford, Oxford, Oxfordshire United Kingdom of Great Britain and Northern Ireland (e-mail: afourast@robots.ox.ac.uk)
Joon Son Chung , Engineering Science, University of Oxford, Oxford, Oxfordshire United Kingdom of Great Britain and Northern Ireland (e-mail: joon@robots.ox.ac.uk)
Andrew Senior , Deepmind, Google Inc, 93176 Mountain View, California United States (e-mail: andrewsenior@google.com)
Oriol Vinyals , Deepmind, Google Inc, 93176 Mountain View, California United States (e-mail: vinyals@google.com)
Andrew Zisserman , Engineering Science, University of Oxford, Oxford, Oxford United Kingdom of Great Britain and Northern Ireland (e-mail: az@robots.ox.ac.uk)

Hierarchical Fully Convolutional Network for Joint Atrophy Localization and Alzheimer's Disease Diagnosis using Structural MRI (Abstract)

Chunfeng Lian , Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina United States 27599 (e-mail: chunfeng_lian@med.unc.edu)
Mingxia Liu , Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina United States (e-mail: mxliu@med.unc.edu)
Jun Zhang , Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina United States (e-mail: xdzhangjun@gmail.com)
Dinggang Shen , Department of Radiology, UNC Chapel Hill, Chapel Hill, North Carolina United States (e-mail: dgshen@med.unc.edu)

Advances in Variational Inference (PDF)

Cheng Zhang , Machine Intelligence and Perception, Microsoft Research, Cambridge, UK, Cambridge, Cambridge United Kingdom of Great Britain and Northern Ireland (e-mail: cheng.zhang@microsoft.com)
Judith Butepage , Robotics, Perception, and Learning (RPL), Kungliga Tekniska Hogskolan, 7655 Stockholm, Stockholm Sweden (e-mail: butepage@kth.se)
Hedvig Kjellstrom , CSC/RPL, KTH, Stockholm, Stockholm Sweden SE-100 44 (e-mail: hedvig@csc.kth.se)
Stephan Mandt , Bren School of Information and Computer Science, University of California, Irvine, irvine, California United States (e-mail: stephan.mandt@disneyresearch.com)

Group Maximum Differentiation Competition: Model Comparison with Few Samples (Abstract)

Kede Ma , Electrical and Computer Engineering, University of Waterloo, Waterloo, Ontario Canada (e-mail: k29ma@uwaterloo.ca)
Zhengfang Duanmu , Electrical and Computer Engineering, University of Waterloo, Waterloo, Ontario Canada (e-mail: zduanmu@uwaterloo.ca)
Zhou Wang , Electrical and Computer Engineering, University of Waterloo, Waterloo, Ontario Canada (e-mail: zhou.wang@uwaterloo.ca)
Qingbo Wu , School of Information and Communication Engineering, University of Electronic Science and Technology of China, 12599 Chengdu, Sichuan China (e-mail: wqb.uestc@gmail.com)
Wentao Liu , Electrical and Computer Engineering, University of Waterloo, Waterloo, Ontario Canada (e-mail: w238liu@uwaterloo.ca)
Hongwei Yong , School of Mathematics and Statistics, Xi'an Jiaotong University, 12480 Xi'an, Shaanxi China (e-mail: cshyong@comp.polyu.edu.hk)
Hongliang Li , Electronic Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan China (e-mail: hlli@uestc.edu.cn)
Lei Zhang , Dept. of Computing, The Hong Kong Polytechnic University, Hong Kong, Hong Kong Hong Kong N.A (e-mail: cslzhang@comp.polyu.edu.hk)

Deep Self-Evolution Clustering (Abstract)

Jianlong Chang , National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of Sciences, 74522 Beijing, Beijing China (e-mail: jianlong.chang@nlpr.ia.ac.cn)
Gaofeng Meng , Chinese Academy of Sciences, Institution of Automation, Beijing, Beijing China (e-mail: gfmeng@nlpr.ia.ac.cn)
Lingfeng Wang , National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, Beijing China (e-mail: lingfeng.wang@ia.ac.cn)
Shiming Xiang , School of Artificial Intelligence, University of the Chinese Academy of Sciences, 74519 Beijing, Beijing China (e-mail: smxiang@nlpr.ia.ac.cn)
Chunhong Pan , National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, Beijing China (e-mail: chpan@nlpr.ia.ac.cn)

Automated video face labelling for films and TV material (Abstract)

Omkar Parkhi , Department of Engineering Science, Visual Geometry Group, Oxford University, Oxford, Oxfordshire United Kingdom of Great Britain and Northern Ireland (e-mail: omkar@robots.ox.ac.uk)
Esa Rahtu , Computer Science and Engineering, University of Oulu, Oulu, Northern Ostrobothnia Finland (e-mail: erahtu@ee.oulu.fi)
Qiong Cao , Department of Engineering Science, Visual Geometry Group, Oxford University, Oxford, Oxfordshire United Kingdom of Great Britain and Northern Ireland (e-mail: qiong@robots.ox.ac.uk)
Andrew Zisserman , Department of Engineering Science, University of Oxford, Oxford, Oxford United Kingdom of Great Britain and Northern Ireland (e-mail: az@robots.ox.ac.uk)

Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs (Abstract)

Yury A. Malkov , UFP, Institut prikladnoi fiziki RAN, 104668 Nizhnii Novgorod, Nizhnii Novgorod Russian Federation (e-mail: yurymalkov@mail.ru)
Dmitry A. Yashunin , No affilation, No affilation, Nizhny Novgorod, Nizhny Novgorod Russian Federation (e-mail: yashuninda@yandex.ru)

Extracting Geometric Structures in Images with Delaunay Point Processes (Abstract)

Jean-Dominique Favreau , Titane and GraphDeco groups, INRIA, Sophia Antipolis, Sophia Antipolis France (e-mail: jean-dominique.favreau@inria.fr)
Florent Lafarge , Titane group, INRIA, Sophia Antipolis, Sophia Antipolis France (e-mail: Florent.Lafarge@inria.fr)
Adrien Bousseau , GraphDeco group, INRIA, Sophia Antipolis, Sophia Antipolis France (e-mail: adrien.bousseau@inria.fr)
Alex Auvolat , GraphDeco group, INRIA, Sophia Antipolis, Sophia Antipolis France (e-mail: alex.auvolat-bernstein@inria.fr)

Joint Image Filtering with Deep Convolutional Networks (Abstract)

Yijun Li , Electrical Engineering and Computer Science, University of California at Merced, Merced, California United States (e-mail: yli62@ucmerced.edu)
Jia-Bin Huang , Electrical and Computer Engineering, Virginia Tech, Blacksburg, Virginia United States (e-mail: jbhuang@vt.edu)
Narendra Ahuja , Electrical and Computer Engineering, University of Illinois, Urbana-Champaign, Urbana, Illinois United States (e-mail: n-ahuja@illinois.edu)
Ming-Hsuan Yang , EECS, University of California at Merced, Merced, California United States 95344 (e-mail: mhyang@ucmerced.edu)

Perspective-adaptive Convolutions for Scene Parsing (Abstract)

Rui Zhang , Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China, 100190, Beijing, Beijing China (e-mail: zhangrui@ict.ac.cn)
Sheng Tang , Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, Beijing China (e-mail: ts@ict.ac.cn)
Yongdong Zhang , Center for Advanced Computing Research, Institute of Computing Technology,Chinese Academy of Sciences, Beijing, Beijing China 100190 (e-mail: zhyd@ict.ac.cn)
Jintao Li , Center for Advanced Computing Research, Institute of Computing Technology,Chinese Academy of Sciences, Beijing, Beijing China 100190 (e-mail: jtli@ict.ac.cn)
Shuicheng Yan , AI institute, Qihoo 360, Beijing, Beijing China (e-mail: eleyans@nus.edu.sg)

Visibility graphs for image processing (Abstract)

Jacopo Iacovacci , Surgery and Cancer, Imperial College London Department of Surgery and Cancer, 170714 London, London United Kingdom of Great Britain and Northern Ireland (e-mail: j.iacovacci@imperial.ac.uk)
Lucas Lacasa , School of Mathematical Sciences, Queen Mary University of London, 4617 London, London United Kingdom of Great Britain and Northern Ireland E1 4NS (e-mail: l.lacasa@qmul.ac.uk)

Tensor Robust Principal Component Analysis with A New Tensor Nuclear Norm (Abstract)

Canyi Lu , ECE, National University of Singapore, 37580 Singapore, Singapore Singapore 119260 (e-mail: canyilu@gmail.com)
Jiashi Feng , ECE, National University of Singapore, 37580 Singapore, Singapore Singapore (e-mail: elefjia@nus.edu.sg)
yudong chen , School of Operations Research and Information Engineering, Cornell University, New York, New York United States (e-mail: yudong.chen@cornell.edu)
Wei Liu , School of Engineering and Applied Science, IBM Thomas J. Watson Research Center, New York, New York United States (e-mail: wliu@ee.columbia.edu)
Zhouchen Lin , Key Lab. of Machine Perception (MOE), Peking University, Beijing, Beijing China 100080 (e-mail: zlin@pku.edu.cn)
Shuicheng Yan , ece, NUS, sg, SG Singapore 117576 (e-mail: eleyans@nus.edu.sg)

Weighted Manifold Alignment using Wave Kernel Signatures for Aligning Medical image Datasets (Abstract)

James Clough , School of Biomedical Engineering & Imaging Sciences, Kings College London - Fs Sandbox, 516252 London, London United Kingdom of Great Britain and Northern Ireland (e-mail: james.clough@kcl.ac.uk)
Daniel Robert Balfour , School of Biomedical Engineering & Imaging Sciences, Kings College London - Fs Sandbox, 516252 London, London United Kingdom of Great Britain and Northern Ireland (e-mail: daniel.r.balfour@kcl.ac.uk)
Gastao Lima Da Cruz , School of Biomedical Engineering & Imaging Sciences, Kings College London - Fs Sandbox, 516252 London, London United Kingdom of Great Britain and Northern Ireland (e-mail: gastao.cruz@kcl.ac.uk)
Paul Marsden , School of Biomedical Engineering & Imaging Sciences, Kings College London - Fs Sandbox, 516252 London, London United Kingdom of Great Britain and Northern Ireland (e-mail: paul.marsden@kcl.ac.uk)
Claudia Prieto , School of Biomedical Engineering & Imaging Sciences, Kings College London - Fs Sandbox, 516252 London, London United Kingdom of Great Britain and Northern Ireland (e-mail: claudia.prieto@kcl.ac.uk)
Andrew Reader , School of Biomedical Engineering & Imaging Sciences, Kings College London - Fs Sandbox, 516252 London, London United Kingdom of Great Britain and Northern Ireland (e-mail: andrew.reader@kcl.ac.uk)
Andrew King , School of Biomedical Engineering & Imaging Sciences, Kings College London - Fs Sandbox, 516252 London, London United Kingdom of Great Britain and Northern Ireland (e-mail: andrew.king@kcl.ac.uk)

Tattoo Image Search at Scale: Joint Detection and Compact Representation Learning (Abstract)

Hu Han , Institute of Computing Technology, Chinese Academy of Sciences, Beijing, Beijing China (e-mail: hhan@cse.msu.edu)
Jie Li , Institute of Computing Technology, Chinese Academy of Sciences, Beijing, Beijing China (e-mail: jie.li@vipl.ict.cn)
Anil K. Jain , Computer Science & Engineering, Michigan State University, East Lansing, Michigan United States 48824-1226 (e-mail: jain@cse.msu.edu)
shiguang shan , Institute of Computing Technology, Chinese Academy of Science, Haidian, Beijing China 100080 (e-mail: sgshan@ict.ac.cn)
Xilin Chen , Institute of Computing Technology, Chinese Academy of Sciences, Beijing, Beijing China 100080 (e-mail: xlchen@ict.ac.cn)

Hierarchical Bayesian Inverse Lighting of Portraits with a Virtual Light Stage (Abstract)

Davoud Shahlaei , eti, University of Siegen, Siegen, NRW Germany (e-mail: davoud.shahlaei@gmail.com)
Volker Blanz , eti, University of Siegen, Siegen, NRW Germany (e-mail: blanz@informatik.uni-siegen.de)

On Detection of Faint Edges in Noisy Images (Abstract)

Nati Ofir , Dept. of Computer Science and Applied Math, Weizmann Institute of Science, 34976 Rehovot, IL Israel (e-mail: natiofir@gmail.com)
Meirav Galun , Dept. of Computer Science and Applied Math, Weiznann Institute of Science, Rehovot, N/A Israel (e-mail: meirav.galun@weizmann.ac.il)
Sharon Alpert , Dept. of Computer Science and Applied Math, Weizmann Institute of Science, 34976 Rehovot, N/A Israel (e-mail: sharon.alpert@gmail.com)
Achi Brandt , Dept. of Computer Science and Applied Math, Weizmann Institute of Science, 34976 Rehovot, N/A Israel (e-mail: achibr@gmail.com)
Boaz Nadler , Dept. of Computer Science and Applied Math, Weizmann Institute of Science, 34976 Rehovot, N/A Israel (e-mail: boaz.nadler@weizmann.ac.il)
Ronen Basri , Dept. of Computer Science and Applied Math, Weizmann Institute of Science, Rehovot, N/A Israel (e-mail: ronen.basri@weizmann.ac.il)

Force from Motion: Decoding Control Force of Activity in a First Person Video (Abstract)

Hyun Park , Computer Science and Engineering, University of Minnesota, Minneapolis, Minnesota United States 55455 (e-mail: hspark@umn.edu)
Jianbo Shi , Computer and Information Science, University of Pennsylvania, Philadelphia, Pennsylvania United States (e-mail: jshi@seas.upenn.edu)

Multiple Kernel k-means with Incomplete Kernels (Abstract)

Xinwang Liu , School of Computer, National University of Defense Technology, 58294 Changsha, Hunan China 410073 (e-mail: xinwangliu@nudt.edu.cn)
Xinzhong Zhu , College of Mathematics, Physics and Information Engineering, Zhejiang Normal University, 66344 Jinhua, Zhejiang China (e-mail: zxz@zjnu.edu.cn)
Miaomiao Li , Department of Computer, Changsha College, Changsha, HUNAN China (e-mail: miaomiaolinudt@gmail.com)
Lei Wang , School of Computer Science and Software Engineering, University of Wollongong, 2522, New South Wales Australia (e-mail: leiw@uow.edu.au)
En Zhu , School of Computer Science, School of Computer Science, National University of Defense Technology, Changsha, Hunan China (e-mail: enzhu@nudt.edu.cn)
Tongliang Liu , The the UBTech Sydney Artificial Intelligence Institute and the School of Information Technologies in the Faculty of Engineering and Information Technologies at The University of Sydney, The University of Sydney, Sydney, New South Wales Australia (e-mail: tongliang.liu@sydney.edu.au)
Marius Kloft , Department of Computer Science, Technische Universitat Kaiserslautern Fachbereich Mathematik, 163342 Kaiserslautern, Rheinland-Pfalz Germany (e-mail: kloft@cs.tu-kl.de)
Dinggang Shen , Department of Radiology, UNC Chapel Hill, Chapel Hill, North Carolina United States (e-mail: dgshen@med.unc.edu)
Jianping Yin , School of Computer Science, National University of Defense Technology, Changsha, Hunan China (e-mail: jpyin@nudt.edu.cn)
Wen Gao , CS, Peking University, Beijing, Beijing China (e-mail: wgao@pku.edu.cn)

3D Human Pose Machines with Self-supervised Learning (Abstract)

Keze Wang , School of Data and Computer Science, Sun Yat-Sen University, 26469 Guangzhou, Guangdong China (e-mail: kezewang@gmail.com)
Liang Lin , School of Information Science and Technology, Sun Yat-sen University, Guangzhou, Guangdong China (e-mail: linliang@ieee.org)
Chenhan Jiang , School of Information Science and Technology, Sun Yat-sen University, Guangzhou, Guangdong China (e-mail: jiangchh6@mail2.sysu.edu.cn)
Chen Qian , Research Deparment, SenseTime Group Limited, Hong Kong, Hong Kong China (e-mail: qianchen@sensetime.com)
Pengxu Wei , School of Data and Computer Science, Sun Yat-Sen University, 26469 Guangzhou, Guangdong China (e-mail: pengxu.07@163.com)

Minimal Case Relative Pose Computation using Ray-Point-Ray Features (Abstract)

Ji Zhao , Senior Researcher, TuSimple, Beijing, Beijing City China (e-mail: zhaoji84@gmail.com)
Laurent Kneip , School of Information Science and Technology, ShanghaiTech University, 387433 Pudong, Shanghai China (e-mail: lkneip@shanghaitech.edu.cn)
Yijia He , Institute of Automation, Chinese Academy of Sciences, Beijing, Beijing City China (e-mail: heyijia2016@gmail.com)
Jiayi Ma , Electronic Information School, Wuhan University, 12390 Wuhan, Hubei China 430072 (e-mail: jyma2010@gmail.com)

LCR-Net++: Multi-person 2D and 3D Pose Detection in Natural Images (Abstract)

Gregory Rogez , THOTH, Inria Centre de Recherche Grenoble Rhone-Alpes, 56521 Montbonnot, Rhone-Alpes France (e-mail: gregory.rogez@inria.fr)
Philippe Weinzaepfel , computer vision group, Naver Labs Europe, 84341 Meylan, Auvergne-Rhône-Alpes France (e-mail: philippe.weinzaepfel@naverlabs.com)
Cordelia Schmid , INRIA Grenoble, LEAR team, Montbonnot, Rhône-Alpes France (e-mail: cordelia.schmid@inria.fr)

Online Meta Adaptation for Fast Video Object Segmentation (Abstract)

Huaxin Xiao , System Engineering, National University of Defense Technology, 58294 Changsha, Huanan China (e-mail: xiaohuaxin@nudt.edu.cn)
Bingyi Kang , ECE, National University of Singapore, 37580 Singapore, Singapore Singapore (e-mail: kang@u.nus.edu)
Yu Liu , System Engineering, National University of Defense Technology, 58294 Changsha, Huanan China (e-mail: jasonyuliu@nudt.edu.cn)
Maojun Zhang , System Engineering, National University of Defense Technology, 58294 Changsha, Huanan China (e-mail: mjzhang@nudt.edu.cn)
Jiashi Feng , ECE, National University of Singapore, 37580 Singapore, Singapore Singapore (e-mail: elefjia@nus.edu.sg)

Fast Cross-Validation for Kernel-based Algorithms (Abstract)

Yong Liu , Institute of Information Engineering, Chinese Academy of Sciences, Beijing, Beijing China (e-mail: liuyong@iie.ac.cn)
Shizhong Liao , College of Intelligence and Computing, Tianjin University, Tianjin, Tianjin China (e-mail: szliao@tju.edu.cn)
Shali Jiang , Computer Science and Engineering, Washington University, Missouri, Washington United States (e-mail: jiang.s@wustl.edu)
Lizhong Ding , Inception Institute of Artificial Intelligence (IIAI), Abu Dhabi, UAE, Abu Dhabi, Abu Dhabi United Arab Emirates (e-mail: lizhong.ding@kaust.edu.sa)
Hailun Lin , Institute of Information Engineering, Chinese Academy of Sciences, Beijing, Beijing China (e-mail: linhailun@iie.ac.cn)
Weiping Wang , Institute of Information Engineering, Chinese Academy of Sciences, Beijing, Beijing China (e-mail: wangweiping@iie.ac.cn)

Structured Label Inference for Visual Understanding (Abstract)

Nelson Isao Nauata Junior , Computing Science, Simon Fraser University Faculty of Applied Sciences, 120447 Burnaby, British Columbia Canada (e-mail: nnauata@sfu.ca)
Hexiang Hu , Viterbi School of Engineering, University of Southern California, Los Angeles, California United States (e-mail: frank.hexiang@gmail.com)
Guang-Tong Zhou , Oracle Labs, Oracle Corp, 50301 Vancouver, British Columbia Canada (e-mail: zhouguangtong@gmail.com)
Zhiwei Deng , School of Computing Science, Simon Fraser University, Burnaby, British Columbia Canada (e-mail: zhiweid@sfu.ca)
Zicheng Liao , Computer Science, Zhejiang University, Hangzhou, Zhejiang China (e-mail: zliao@zju.edu.cn)
Greg Mori , Computing Science, Simon Fraser University, Burnaby, British Columbia Canada V5A 1S6 (e-mail: mori@cs.sfu.ca)

Shared Multi-view Data Representation for Multi-domain Event Detection (Abstract)

Zhenguo Yang , Computer Science, City University of Hong Kong, Kowloon, Hong Kong Hong Kong (e-mail: yzgcityu@gmail.com)
Qing Li , Department of Computing, The Hong Kong Polytechnic University, Hong Kong, Hong Kong Hong Kong (e-mail: itqli@cityu.edu.hk)
Liu Wenyin , School of Computer Science and Technology, Guangdong University of Technology, 47870 Guangzhou, Guangdong China (e-mail: liuwenyin@gmail.com)
Jianming Lv , Department of Computer Science, South China University of Technology, Guangzhou, Guangdong China (e-mail: jmlv@scut.edu.cn)

Pixel Transposed Convolutional Networks (Abstract)

Hongyang Gao , School of Electrical Engineering & Computer Science, Washington State University, Pullman, Washington United States (e-mail: hongyang.gao@tamu.edu)
Hao Yuan , School of Electrical Engineering & Computer Science, Washington State University, Pullman, Washington United States (e-mail: hao.yuan@wsu.edu)
Zhengyang Wang , School of Electrical Engineering & Computer Science, Washington State University, Pullman, Washington United States (e-mail: zhengyang.wang@tamu.edu)
Shuiwang Ji , School of Electrical Engineering & Computer Science, Washington State University, Pullman, Washington United States 99164 (e-mail: shuiwang.ji@gmail.com)

Large-scale Urban Reconstruction with Tensor Clustering and Global Boundary Refinement (PDF)

Charalambos Poullis , Computer Science and Software Engineering, Concordia University, Montreal, Quebec Canada H9W1E7 (e-mail: charalambos@poullis.org)

RefineNet: Multi-Path Refinement Networks for Dense Prediction (Abstract)

Guosheng Lin , School of Computer Science and Engineering, Nanyang Technological University, 54761 Singapore, Singapore Singapore (e-mail: gslin@ntu.edu.sg)
Fayao Liu , School of Computer Science, University of Adelaide, Adelaide, South Australia Australia (e-mail: fayaoliu@gmail.com)
Anton Milan , Amazon Research and Development Center in Berlin, Amazon, Berlin, Berlin Germany (e-mail: anton.a.milan@gmail.com)
Chunhua Shen , School of Computer Science, University of Adelaide, Adelaide, South Australia Australia (e-mail: chunhua.shen@adelaide.edu.au)
Ian Reid , School of Computer Science, The University of Adelaide, Adelaide, South Australia Australia (e-mail: ian.reid@adelaide.edu.au)

Rolling Shutter Camera Absolute Pose (Abstract)

Cenek Albl , Cybernetics, Ceske Vysoke Uceni Technicke Fakulta elektrotechnicka, 154241 Prague, Prague Czech Republic 16627 (e-mail: cenek.albl@gmail.com)
Zuzana Kukelova , Department of Cybernetics, Center for Machine Perception, Czech Technical University in Prague, Prague 6, Czech Republic Czech Republic 166 27 (e-mail: kukelova@cmp.felk.cvut.cz)
Viktor Larsson , Department of Mathematics, Lunds Universitet, 5193 Lund, Skåne Sweden (e-mail: viktor.larsson@inf.ethz.ch)
Tomas Pajdla , Czech Institute of Informatics, Robotics and Cybernetics, Center for Machine Perception, Prague, Prague 6 Czech Republic 16636 (e-mail: pajdla@cvut.cz)

Feature Boosting Network For 3D Pose Estimation (Abstract)

Jun Liu , School of Electrical and Electronic Engineering, Nanyang Technological University, 54761 Singapore, Singapore Singapore 639798 (e-mail: jliu029@ntu.edu.sg)
Henghui Ding , School of EEE, Nanyang Technological University, 54761 Singapore, Singapore Singapore (e-mail: ding0093@ntu.edu.sg)
Amir Shahroudy , School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore Singapore 637553 (e-mail: amir3@ntu.edu.sg)
Ling-Yu Duan , National Engineering Laboratory for Video Technology, Peking University, Beijing, Beijing China (e-mail: lingyu@pku.edu.cn)
Xudong Jiang , School of EEE, Nanyang Technological University, Singapore, Singapore Singapore 639798 (e-mail: exdjiang@ntu.edu.sg)
Gang Wang , School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore Singapore (e-mail: gangwang6@gmail.com)
Alex Kot Chichung , School of EEE, Nanyang Technological University, Singapore, Singapore Singapore (e-mail: eackot@ntu.edu.sg)

Models Matter, So Does Training: An Empirical Study of CNNs for Optical Flow Estimation (Abstract)

Deqing Sun , Research, NVIDIA Corp, 196328 Westford, Massachusetts United States (e-mail: deqings@nvidia.com)
Xiaodong Yang , Research, NVIDIA Corp, 196328 Santa Clara, California United States (e-mail: xiaodongy@nvidia.com)
Ming-Yu Liu , Research, NVIDIA Corp, 196328 Santa Clara, California United States (e-mail: mingyul@nvidia.com)
Jan Kautz , Research, NVIDIA Corp, 196328 Westford, Massachusetts United States (e-mail: jkautz@nvidia.com)

Hierarchical LSTMs with Adaptive Attention for Visual Captioning (Abstract)

Lianli Gao , Computer Science and Enginerring, The University of Electronic Science and Technology of China, Chengdu, SiChuan China (e-mail: lianli.gao@uestc.edu.cn)
Xiangpeng Li , Computer Science and Enginerring, The University of Electronic Science and Technology of China, Chengdu, SiChuan China (e-mail: xiangpeng.li@std.uestc.edu.cn)
Jingkuan Song , department of applied science and engineering, Columbia University Fu Foundation School of Engineering and Applied Science, 116460 NEW YORK, New York United States 10027 (e-mail: jingkuan.song@gmail.com)
Heng Tao Shen , School of Computer Science and Engineering, University of Electronic Science and Technology of China, 12599 Chengdu, Sichuhan China 610054 (e-mail: shenhengtao@hotmail.com)

Light Field Super-Resolution using a Low-Rank Prior and Deep Convolutional Neural Networks (Abstract)

Reuben Farrugia , Communications and Computer Engineering, University of Malta, Msida, NA Malta MSD2080 (e-mail: reuben.farrugia@um.edu.mt)
Christine Guillemot , TEMICS, INRIA, Rennes, Brittany France (e-mail: Christine.Guillemot@inria.fr)

Heterogeneous Recommendation via Deep Low-rank Sparse Collective Factorization (Abstract)

Shuhui Jiang , Electrical and computer engineering, Northeastern University, boston, Massachusetts United States 02115 (e-mail: shjiang@coe.neu.edu)
Zhengming Ding , Electrical and Computer Engineering, Northeastern University, Boston, Massachusetts United States (e-mail: allanding@ece.neu.edu)
Yun Fu , ECE, Northeastern University, Boston, Massachusetts United States (e-mail: yunfu@ece.neu.edu)

Unsupervised Video Matting via Sparse and Low-Rank Representation (Abstract)

Dongqing Zou , School of Computer Science and Engineering, Beihang University, Beijing, Beijing China (e-mail: dqzou@buaa.edu.cn)
Xiaowu Chen , School of Computer Science & Engineering, State Key Laboratory of Virtual Reality Technology & Systems, Beihang University, Beijing, Beijing China 100191 (e-mail: chen@buaa.edu.cn)
Guangying Cao , School of Computer Science and Engineering, Beihang University, Beijing, Beijing China (e-mail: cgy@buaa.edu.cn)
Xiaogang Wang , School of Computer Science and Engineering, Beihang University, 12633 Beijing, Beijing China (e-mail: wangxiaogang@buaa.edu.cn)

Hierarchical Surface Prediction (Abstract)

Christian Hane , EECS, University of California, Berkeley, Berkeley, California United States (e-mail: christian.haene@gmx.ch)
Shubham Tulsiani , EECS, UC Berkeley, Berkeley, California United States 94720-1776 (e-mail: shubhtuls@eecs.berkeley.edu)
Jitendra Malik , EECS, University of California at Berkeley, Berkeley, California United States (e-mail: malik@eecs.berkeley.edu)

Absent Multiple Kernel Learning Algorithms (Abstract)

Xinwang Liu , National Laboratory for Parallel and Distributed Processing, National University of Defense Technology, 58294 Changsha, Hunan China (e-mail: xinwangliu@nudt.edu.cn)
Lei Wang , School of Computer Science and Software Engineering, University of Wollongong, 2522, New South Wales Australia (e-mail: leiw@uow.edu.au)
Xinzhong Zhu , College of Mathematics, Physics and Information Engineering, Zhejiang Normal University, 66344 Jinhua, Zhejiang China (e-mail: zxz@zjnu.edu.cn)
Miaomiao Li , Department of Computer, Changsha College, Changsha, HUNAN China (e-mail: miaomiaolinudt@gmail.com)
En Zhu , School of Computer Science, School of Computer Science, National University of Defense Technology, Changsha, Hunan China (e-mail: enzhu@nudt.edu.cn)
Tongliang Liu , The the UBTech Sydney Artificial Intelligence Institute and the School of Information Technologies in the Faculty of Engineering and Information Technologies at The University of Sydney, The University of Sydney, Sydney, New South Wales Australia (e-mail: tongliang.liu@sydney.edu.au)
Li Liu , School of Electronic Science and Engineering, National University of Defense Technology, Changsha, Hunan China (e-mail: lilyliu_nudt@163.com)
Yong Dou , National Laboratory for Parallel and Distributed Processing, National University of Defense Technology, 58294 Changsha, Hunan China (e-mail: yongdou@nudt.edu.cn)
Jianping Yin , School of Computer Science, National University of Defense Technology, 58294 Changsha, Hunan China (e-mail: jpyin@nudt.edu.cn)

Joint Rain Detection and Removal from a Single Image with Contextualized Deep Networks (Abstract)

Wenhan Yang , Institute of computer science & technology, Peking University, Beijing, Beijing China (e-mail: yangwenhan@pku.edu.cn)
Robby T. Tan , National University of Singapore, National University of Singapore, Singapore, Singapore Singapore (e-mail: tanrobby@gmail.com)
Jiashi Feng , ECE, National University of Singapore, 37580 Singapore, Singapore Singapore (e-mail: elefjia@nus.edu.sg)
Jiaying Liu , Institute of computer science & technology, Peking University, 12465 Beijing, Beijing China (e-mail: liujiaying@pku.edu.cn)
Shuicheng Yan , ece, NUS, sg, SG Singapore 117576 (e-mail: eleyans@nus.edu.sg)
Zongming Guo , Institute of Computer Science and Technology, Peking University, Beijing, Beijing China (e-mail: guozongming@pku.edu.cn)

View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognition (Abstract)

Pengfei Zhang , Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, 12480 Xi'an, Shannxi China (e-mail: zpengfei@stu.xjtu.edu.cn)
Cuiling Lan , Internet Media Group, Microsoft Research Asia, 216064 Beijing, Beijing China (e-mail: culan@microsoft.com)
Junliang Xing , National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, Beijing China (e-mail: jlxing@nlpr.ia.ac.cn)
Wenjun Zeng , Internet Media Group, Microsoft Research Asia, Beijing, Beijing China (e-mail: wezeng@microsoft.com)
Jianru Xue , Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an, Shaanxi China (e-mail: jrxue@mail.xjtu.edu.cn)
Nanning Zheng , Automation, Xi'anJiaotongUniv, Xi'an, Shannxi China (e-mail: nnzheng@mail.xjtu.edu.cn)

EuroCity Persons: A Novel Benchmark for Person Detection in Traffic Scenes (Abstract)

Markus Braun , Environment Perception, Daimler AG, Ulm, Baden-Württemberg Germany 89081 (e-mail: markus.ma.braun@daimler.com)
Sebastian Krebs , Evironment Perception, Daimler AG, Ulm, Baden-Württemberg Germany 89081 (e-mail: sebastian.krebs@daimler.com)
Fabian Flohr , Environment Perception, Daimler AG, Ulm, BW Germany (e-mail: fabian.flohr@daimler.com)
Dariu Gavrila , Cognitive Robotics, Delft University of Technology, Delft, South Holland Netherlands (e-mail: d.m.gavrila@tudelft.nl)

Hyperbolic Wasserstein Distance for Shape Indexing (Abstract)

Jie Shi , School of Computing, Informatics, and Decision Systems Engineering, Arizona State University, Tempe, Arizona United States (e-mail: jshi28@asu.edu)
Yalin Wang , School of Computing, Informatics, and Decision Systems Engineering, Arizona State University, Tempe, Arizona United States 85287-8807 (e-mail: ylwang@asu.edu)

Skeleton-Based Online Action Prediction Using Scale Selection Network (Abstract)

Jun Liu , School of Electrical and Electronic Engineering, Nanyang Technological University, 54761 Singapore, Singapore Singapore 639798 (e-mail: jliu029@ntu.edu.sg)
Amir Shahroudy , School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore Singapore 637553 (e-mail: amir3@ntu.edu.sg)
Gang Wang , School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore Singapore (e-mail: gangwang6@gmail.com)
Ling-Yu Duan , Peking University, Peking University, Beijing, Beijing China (e-mail: lingyu@pku.edu.cn)
Alex Kot Chichung , EEE, Nanyang Technological University, Singapore, Singapore Singapore (e-mail: eackot@ntu.edu.sg)

Min-Entropy Latent Model for Weakly Supervised Object Detection (Abstract)

Fang Wan , Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, Beijing China (e-mail: wanfang13@mails.ucas.ac.cn)
Pengxu Wei , School of Data and Computer Science, Sun Yat-Sen University, 26469 Guangzhou, Guangdong China (e-mail: weipengxu11@mails.ucas.ac.cn)
Zhenjun Han , Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, Beijing China (e-mail: hanzhj@ucas.ac.cn)
Jianbin Jiao , Electronic, Electrical and Communication Engineering, University of the Chinese Academy of Sciences, 74519 Beijing, Beijing China (e-mail: jiaojb@ucas.ac.cn)
Qixiang Ye , Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, Beijing China (e-mail: qxye@ucas.ac.cn)

Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistency (Abstract)

Shubham Tulsiani , EECS, UC Berkeley, Berkeley, California United States 94720-1776 (e-mail: shubhtuls@eecs.berkeley.edu)
Tinghui Zhou , EECS, University of California Berkeley College of Engineering, 115095 Berkeley, California United States 94720-1700 (e-mail: tinghuiz@eecs.berkeley.edu)
Alyosha Efros , EECS, University of California at Berkeley, Berkeley, California United States (e-mail: efros@eecs.berkeley.edu)
Jitendra Malik , EECS, University of California at Berkeley, Berkeley, California United States (e-mail: malik@eecs.berkeley.edu)

Measuring Shapes with Desired Convex Polygons (Abstract)

Jovisa Zunic , Mathematical Institute, Serbian Academy of Sciences, Belgrade, Serbia Serbia (e-mail: jovisa_zunic@mi.sanu.ac.rs)
Paul Rosin , Computer Science and Informatics, Cardiff University, Cardiff, South Glamorgan United Kingdom of Great Britain and Northern Ireland (e-mail: rosinpl@cardiff.ac.uk)

End-to-end Active Object Tracking and Its Real-world Deployment via Reinforcement Learning (Abstract)

Wenhan Luo , Computer Vision Center, Tencent AI Lab, Shenzhen, Guangdong China (e-mail: whluo.china@gmail.com)
Peng Sun , Reinforcement Learning Center, Tencent AI Lab, Shenzhen, Guangdong China (e-mail: pengsun000@gmail.com)
Fangwei Zhong , Computer Science Department, Peking University, Beijing, Beijing China (e-mail: zfw@pku.edu.cn)
Wei Liu , Electrical Engineering, Columbia University, New York, New York United States 10027 (e-mail: wl2223@columbia.edu)
Tong Zhang , Tencent AI Lab, Tencent AI Lab, Shenzhen, Guangdong China (e-mail: tongzhang@tongzhang-ml.org)
Yizhou Wang , Computer Science Department, Peking University, Beijing, Beijing China (e-mail: Yizhou.Wang@pku.edu.cn)

Exploiting Unlabeled Data in CNNs by Self-supervised Learning to Rank (Abstract)

Xialei Liu , Computer Vision Center, Computer vision center, Barcelona, Catulunya Spain (e-mail: xialei@cvc.uab.es)
Joost Van De Weijer , Computer Vision Center, Universitait Autonoma de Barcelona, Barcelona, Barcelona Spain (e-mail: joost@cvc.uab.es)
Andrew D. Bagdanov , MICC, University of Florence, Firenze, FI Italy (e-mail: bagdanov@cvc.uab.es)

A Disocclusion Inpainting Framework for Depth-based View Synthesis (Abstract)

Guibo Luo , Communication and Information Security Laboratory, Peking University Shenzhen Graduate School, 429362 Shenzhen, Guangdong China 518055 (e-mail: luoguibo@sz.pku.edu.cn)
Yuesheng Zhu , Communication and Information Security Laboratory, Peking University Shenzhen Graduate School, 429362 Shenzhen, Guangdong China (e-mail: zhuys@pku.edu.cn)
Zhenyu Weng , Communication and Information Security Laboratory, Peking University Shenzhen Graduate School, 429362 Shenzhen, Guangdong China (e-mail: wzytumbler@pku.edu.cn)
Zhaotian Li , Communication and Information Security Laboratory, Peking University Shenzhen Graduate School, 429362 Shenzhen, Guangdong China (e-mail: lizhaotian@pku.edu.cn)

Progressive Representation Adaptation for Weakly Supervised Object Localization (Abstract)

Dong Li , Electronic Engineering, Beijing, Beijing China (e-mail: lidong12@tsinghua.org.cn)
Jia-Bin Huang , Electrical and Computer Engineering, Virginia Tech, Blacksburg, Virginia United States (e-mail: jbhuang@vt.edu)
Yali Li , Electronic Engineering, Tsinghua University, Beijing, Beijing China (e-mail: liyali@ocrserv.ee.tsinghua.edu.cn)
Shengjin Wang , EE, Tsinghua University, Beijing, Beijing China (e-mail: wgsgj@tsinghua.edu.cn)
Ming-Hsuan Yang , EECS, University of California at Merced, Merced, California United States 95344 (e-mail: mhyang@ucmerced.edu)

Generic Primitive Detection in Point Clouds Using Novel Minimal Quadric Fits (Abstract)

Tolga Birdal , Informatics, Technical University of Munich, Muenchen, Bayern Germany 85748 (e-mail: tbirdal@gmail.com)
Benjamin Busam , Informatics, Technische Universitat Munchen Fakultat fur Informatik, 163258 Garching, Bayern Germany (e-mail: b.busam@tum.de)
Nassir Navab , Computer Science Department, Techniche Universitat Munchen, Munich, Bavaria Germany (e-mail: navab@cs.tum.edu)
Slobodan Ilic , Research and Development for Digitalization and Automation Digital Perception, Siemens AG, Munich, Bayern Germany (e-mail: Slobodan.Ilic@siemens.com)
Peter Sturm , Perception, Cognition and Interaction, Grenoble, Rhône-Alpes France (e-mail: peter.sturm@inria.fr)

Structured Low-Rank Matrix Factorization: Global Optimality, Algorithms, and Applications (Abstract)

Benjamin David Haeffele , Center for Imaging Science, Johns Hopkins University, 1466 Baltimore, Maryland United States (e-mail: bhaeffele@jhu.edu)
Rene Vidal , Center for Imaging Science, Dept. of Biomedical Engineering, Johns Hopkins University, Baltimore, Maryland United States 21218 (e-mail: rvidal@cis.jhu.edu)

Synthesizing Supervision for Learning Deep Saliency Network without Human Annotation (Abstract)

Dingwen Zhang , School of Mechano-Electronic Engineering, Xidian University, 47905 Xian, Shaanxi China (e-mail: zdw2006yyy@mail.nwpu.edu.cn)
Junwei Han , School of Automation, Northwestern Polytechnical University, Xi'an, Shaanxi China (e-mail: junweihan2010@gmail.com)
Yu Zhang , School of Automation, Xi'an, Shaanxi China (e-mail: zhangyuygss@mail.nwpu.edu.cn)
Dong Xu , School of Electrical and Information Engineering, The University of Sydney, Sydney, New South Wales Australia 2006 (e-mail: dong.xu@sydney.edu.au)

Moments in Time Dataset: one million videos for event understanding (Abstract)

Mathew Monfort , MIT, Cambridge, Massachusetts United States (e-mail: mmonfort@mit.edu)
Alex Andonian , MIT, Cambridge, Massachusetts United States (e-mail: aandonia@mit.edu)
Bolei Zhou , Information Engineering Department, The Chinese University of Hong Kong, Hong Kong, Hong Kong Hong Kong (e-mail: zhoubolei@gmail.com)
Kandan Ramakrishnan , MIT CSAIL, Cambridge, Massachusetts United States (e-mail: krama@mit.edu)
Sarah Adel Bargal , Computer Science, Boston University, Boston, Massachusetts United States (e-mail: sbargal@bu.edu)
Yan Yan , Department of Information Engineering and Computer Science, University of Trento, Trento, TN Italy (e-mail: tom.yan.555@gmail.com)
Lisa Brown , Vision, IBM T.J. Watson research center, USA, Yorktown, New York United States (e-mail: lisabr@us.ibm.com)
Quanfu Fan , Vision, qfan@us.ibm.com, Hawthorne, New York United States (e-mail: qfan@us.ibm.com)
Dan Gutfreund , Vision, IBM Research, 74286 Yorktown Heights, New York United States (e-mail: dgutfre@us.ibm.com)
Carl Vondrick , Columnbia University, New York, New York United States (e-mail: cvondrick@gmail.com)
Aude Oliva , CSAIL, MIT, Cambridge, Massachusetts United States (e-mail: oliva@mit.edu)

Logistic Regression Confined by Cardinality-Constrained Sample and Feature Selection (Abstract)

Ehsan Adeli , Psychiatry and Computer Science, Stanford University, Stanford, California United States (e-mail: eadeli@stanford.edu)
Xiaorui Li , Mathematics, Burnaby, British Columbia Canada (e-mail: xla97@sfu.ca)
Dongjin Kwon , Department of Electrical Engineering and Computer Science, Seoul National University, Seoul, N/A Korea, Republic of 151-742 (e-mail: dj0330@gmail.com)
Yong Zhang , Psychiatry, Stanford, California United States (e-mail: michaelzhang917@gmail.com)
Kilian Pohl , Center for Health Sciences, SRI International, 5426 Menlo Park, California United States (e-mail: kilian.pohl@sri.com)

Adversarial Learning of Structure-Aware Fully Convolutional Networks for Landmark Localization (Abstract)

Yu Chen , School of Computer Science and Engineering, Nanjing University of Science and Technology, 12436 Nanjing, Jiangsu China 210094 (e-mail: chenyu1523@gmail.com)
Chunhua Shen , School of Computer Science, The University of Adelaide, Adelaide, South Australia Australia 5005 (e-mail: chhshen@gmail.com)
Hao Chen , School of Computer Science, The University of Adelaide, Adelaide, South Australia Australia (e-mail: hao.chen01@adelaide.edu.au)
Xiu-Shen Wei , Nanjing University, Nanjing, Jiangsu China (e-mail: weixs.gm@gmail.com)
Lingqiao Liu , School of Computer Science, University of Adelaide, Adelaide, South Australia Australia (e-mail: lingqiao.liu@adelaide.edu.au)
Jian Yang , Computer Science, Nanjing University of Science and Technology, Nanjing, Jiangsu China (e-mail: csjyang@njust.edu.cn)

Learning Multiple Local Metrics: Global Consideration Helps (Abstract)

Han-Jia Ye , Computer Science and Technology, Nanjing University, Nanjing, Jiangsu China (e-mail: yehj@lamda.nju.edu.cn)
D. C. Zhan , Computer Science Department, Nanjing University, Nanjing, Jiangsu China 210093 (e-mail: zhandc@nju.edu.cn)
Nan Li , Alibaba inc. Ltd., Hangzhou, Zhejiang China (e-mail: nanli.ln@alibaba-inc.com)
Yuan Jiang , Department of Computer Science & Technology, Nanjing University, Nanjing, Jiangsu China 210046 (e-mail: jiangy@lamda.nju.edu.cn)

Hiding Images Within Images (PDF)

Shumeet Baluja , AI, Google, San Diego, California United States 92121 (e-mail: shumeet@google.com)
76 ms
(Ver 3.3 (11022016))