Oral

Object Detection and Learning

Multi-task Unaligned Shared Knowledge Transfer

Tatiana Tommasi (Idiap Research Institute), Novi Quadrianto (University of Cambridge), Barbara Caputo (IDIAP), Christoph Lampert (IST Austria)

Cross-database Transfer Learning via Learnable and Discriminant Error-correcting Output Codes

Feng-Ju Chang (Academia Sinica), Yen-Yu Lin (Academia Sinica), Ming-Fang Weng (Academia Sinica)

Human Reidentification with Transferred Metric Learning

Wei LI (The Chinese University of HK), Rui ZHAO (The Chinese University of HK), Xiaogang Wang (The Chinese University HK)

Object Recognition I

Grouping Active Contour Fragments for Object Recognition

Wei Zheng (Chinese Academy of Sciences), Songling Song, Hong Chang, xilin Chen

Detecting partially occluded objects with an Implicit Shape Model Random Field (PDF)

Paul Wohlhart (Graz University of Technology), Peter Roth, Michael Donoser (Graz University of Technology), Horst Bischof (Technische Universitat Graz)

Relative Forest for Attribute Prediction

Shaoxin Li (Chinese Academy of Science), Shiguang Shan (CAS, China), Xilin Chen (Institute of Computing Technology, Chinese Academy of Sciences)

Discriminative Dictionary Learning with Pairwise Constraints

Huimin Guo (University of Maryland), Zhuolin Jiang (University of Maryland), Larry Davis (U. Maryland, USA)

Segmentation and Grouping

Simultaneous Monocular 2D Segmentation, 3D Pose Recovery and 3D Reconstruction

Victor Prisacariu (University of Oxford), Alex Segal (University of Oxford), Ian Reid (University of Oxford)

JOINT KERNEL LEARNING FOR SUPERVISED IMAGE SEGMENTATION

JONGMIN KIM (KAIST), SANGHYUK PARK (KAIST), YOUNGJOO SEO (KAIST), SUNGRACK YUN (KAIST), CHANG YOO (KAIST)

Application of heterogenous motion models towards structure recovery from motio

Rohith MV (University of Delaware), Chandra Kambhamettu (University of Delaware)

Image Representation and Retrieval

Quadra-Embedding: Binary Code Embedding with Low Quantization Error

Youngwoon Lee (KAIST), Jae-Pil Heo (KAIST), Sung-eui Yoon (KAIST)

Learning a Context Aware Dictionary for Sparse Representation

Gianfranco Doretto (West Virginia University), Farzad Siyahjani (West Virginia University)

Robust Multiple-Instance Learning with Superbags

Borislav Antic (University of Heidelberg), Bjorn Ommer

Object Recognition II

Rapid Uncertainty Computation with Gaussian Processes and Histogram Intersection Kernels

Alexander Freytag (Friedrich Schiller University Jena), Erik Rodner (Friedrich Schiller University Jena), Paul Bodesheim (University of Jena, Germany), Joachim Denzler

Histogram of Oriented Normal Vectors for Object Recognition with a Depth Sensor

Shuai Tang (University of Missouri), Xiaoyu Wang, Tony Han (University of Missouri), James Keller, Marjorie Skubic, Shihong Lao, Zhihai He

Globally Optimal Consensus Set Maximization Through Rotation Search

Jean-Charles Bazin (ETHZ), yongduek Seo (Sogang)

Graspable PartsRecognition in Man-made 3D Shapes

Hamid Laga (University of South Australia)

Optical flow and Tracking

Adaptive Integration of Feature Matches into Variational Optical Flow Methods

Michael Stoll (University of Stuttgart (VIS)), Sebastian Volz (University of Stuttgart), Andres Bruhn (University of Stuttgart)

Efficient Learning of Linear Predictors using Dimensionality Reduction

Stefan Holzer (Technische Universität München), Slobodan Ilic, David Joseph Tan (Technische Universität München), Nassir Navab (TU Muenchen)

Robust visual tracking using dynamic classifier selection with sparse representation of label noise

Yuefeng Chen, Qing Wang (Northwestern Polytechnical University)

Video Analysis and Action Recognition

Action Disambiguation Analysis Using Normalized Google-Like Distance Correlogram

Qianru Sun (Peking University), Hong Liu (Peking University)

Alpha flow for video matting

Mikhail Sindeev (Keldysh Institute), Carsten Rother (Microsoft Research), Anton Konushin

Combinational Subsequence Matching for Human Identification from General Actions

Maodi Hu (Buaa), Yunhong Wang, James Little

Shape Reconstruction and and Optimization

Self-calibration and Motion Recovery from Silhouettes with Two Mirrors

Hui Zhang (United International College), Kwan-Yee Kenneth Wong (HKU, Hong Kong), Ling Shao

Stereo Reconstruction and Contrast Restoration in Daytime Fog

Laurent Caraffa (IFSTTAR), Jean-Philippe Tarel (IFSTTAR)

Large-Scale Bundle Adjustment by Parameter Space Decomposition

Shanmin Pang (Xi'an Jiao tong University), Jianru Xue (Xian Jiaotong University, China), Le Wang, Nanning Zheng

Learning Feature Subspaces for Appearance-Based Bundle Adjustment

Hwann-Tzong Chen, Chia-Ming Cheng

Applications of Computer Vision

Apparel Classification with Style (PDF, dataset)

Lukas Bossard, Matthias Dantone, Christian Leistner, Christian Wengert, Till Quack, Luc Van Gool

Removing skin wrinkles and deblurreing veins by using tri-band illumination

Naoto Miura (University of Tokyo), Yoichi Sato (University of Tokyo)

Reconstruction of 3D surface and restoration of flat document image from monocular image sequence

Yoshihiro Watanabe (University of Tokyo), hiroki Shibayama, Masatoshi Ishikawa (Japan)

Utilizing Optical Aberrations for Light-efficient Panoramas

Huixuan Tang (University of Toronto), Kyros Kutulakos (University of Toronto)

Posters

Object Detection, Learning and Matchingg

Design of a Text Detection System via Hypothesis Generation and Verification

Sam Tsai (Stanford University), Vasu Parameswaran (Nokia Research Center), Jerome Berclaz (Nokia Research Center), Ramakrishna Vedantham (Nokia Research Center), Radek Grzeszczuk (Nokia Research Center), Bernd Girod (Stanford University)

Tell me what you like and I'll tell you what you are: discriminating visual preferences by crowdsourcing

Pietro Lovato, Alessandro Perina, Omar Zandona, Alessio Montagnini, Nicu Sebe (University of Trento, Italy), Manuele Bicego, Marco Cristani (IIT)

Local Context Priors for Object Proposal Generation

Marko Ristin (ETH Zurich), Juergen Gall (Max Planck Institute for Intelligent Systems), Luc Van Gool (ETH Zurich)

Arbitrary-Shape Object Localization using Adaptive Image Grids

Chunluan Zhou (NTU), Junsong Yuan (Nanyang Technological University, Singapore)

Disambiguation in Unknown Object Detection by Integrating Image and Speech Recognition Condences

Yuko Ozasa (Kobe University), Yasuo Ariki (Kobe University), Naoto Iwahashi (NICT), Mikio Nakano (HRI)

Class-Specific Weighted Dominant Orientation Templates for object detection

HuiJin Lee (POSTECH), Ki Sang Hong

Salient Object Detection via Color Contrast and Color Distribution

Keren Fu (Shanghai Jiao Tong University), Chen Gong, Jie Yang

Data Decomposition and Spatial Mixture Modeling for Part based Model

Junge ZHANG (NLPR), Kaiqi Huang (Institute of Automation, Chinese Academy of Sciences), Tieniu Tan (NLPR, CASIA, china)

Appearance Sharing for Collective Human Pose Estimation

Marcin Eichner (ETH Zurich), Vittorio Ferrari (University of Edinburgh)

Max-Margin Regularization for Reducing Accidentalness in Chamfer Matching

Pradeep krishna Yarlagadda (University of Heidelberg), Angela Eigenstetter (IWR University Heidelberg), Bjorn Ommer

Coupling-and-Decoupling: a Hierarchical Model for Occlusion-Free Car Detection

Bo Li (bit.edu.cn), Tianfu Wu (bupt.edu.cn), Wenze Hu (ucla.edu), Mingtao Pei (bit.edu.cn)

The Pooled NBNN Kernel: Beyond Image-to-Class and Image-to-Image

Konstantinos Rematas (K.U. Leuven), Tinne Tuytelaars (K.U.Leuven), Mario Fritz (MPI-Informatik)

Local Hypersphere Coding Based on Edges between Visual Words

Weiqiang Ren (CASIA), YongZhen Huang (NLPR), Kaiqi Huang (Institute of Automation, Chinese Academy of Sciences), Tieniu Tan (NLPR, CASIA, china)

Spatially Local Coding for Object Recognition

Sancho McCann (UBC), David Lowe

Semantic Segmentation with Millions of Features: Integrating Multiple Cues in a Combined Random Forest Approach

Björn Fröhlich (FSU Jena), Erik Rodner (Friedrich Schiller University Jena), Joachim Denzler

Semi-Supervised Learning on a Budget: Scaling up to Large Datasets

Sandra Ebert (Max Planck Institute), Mario Fritz (MPI-Informatik), Bernt Schiele (MPI Informatics)

One-Class Multiple Instance Learning via Robust PCA for Common Object Discovery

Xinggang Wang (Huazhong Univ. of Sci. &), Tech., Zhengdong Zhang, Yi Ma (Microsoft Research Asia), Zhuowen Tu (Laboratory of Neuro Imaging Department of Neurology, UCLA )

Online Semi-supervised Discriminative Dictionary Learning for Sparse Representation

Guangxiao Zhang (University of Maryland), Zhuolin Jiang (University of Maryland), Larry Davis (U. Maryland, USA)

Efficient Discriminative Learning of Class Hierarchy for Many Class Prediction

Lin Chen (NTU), Lxin Duan (NTU), Ivor Tsang (NTU), Dong Xu (Nanyang Technological University)

CMML: a New Metric Learning Approach for Cross Modal Matching

Alexis Mignon (GREYC -- CNRS), Frederic Jurie

Feature, Representation and Recognition

Adaptive Unsupervised Multi-View Feature Selection for Visual Concept Recognition

Yinfu Feng (Zhejiang University), Jun Xiao (Zhejiang University), Yueting Zhuang (Zhejiang University), Xiaoming Liu (General Electric)

Iris Recognition using Consistent Corner Optical Flow

Aditya Nigam (Indian Institute of Technology), Phalguni Gupta (Indian Institute of Technology)

Face Recognition in Videos - A Graph Based Modified Kernel Discriminant Analysis

Gayathri Mahalingam (University of Delaware), Chandra Kambhamettu (University of Delaware)

Learning Hierarchical Bag of Words using Naive Bayes Clustering

Siddhartha Chandra (IIIT Hyderabad), Shailesh Kumar, Jawahar C V (IIIT, Hyderabad)

Efficient Human Parsing Based on Sketch Representation

Meng Wang (BUAA), Zhaoxiang Zhang (Beihang University), Yunhong Wang

Effectively Leveraging Visual Context to Detect Texts in Natural Scenes

Jiyan Pan (Carnegie Mellon University), Ye Chen (Microsoft Corporation), Bo Anderson (Microsoft Corporation), Pavel Berkhin (Microsoft Corporation), Takeo Kanade (Carnegie Mellon University)

Exclusive Visual Descriptor Quantization

YU ZHANG (Ntu.sg), Jianxin Wu (NTU, Singapore), Weiyao Lin (Shanghai Jiao Tong University, China)

Hierarchical Classification for Live Fish Recognition

Phoenix Huang (University of Edinburgh), Bastiaan Boom (University of Edinburgh), Robert Fisher (University of Edinburgh)

Local 3D Symmetry for Visual Saliency

Ekaterina Potapova (TUW), Michael Zillich, Markus Vincze

Exploiting Features -- Locally Interleaved Sequential Alignment for Object Detection

Tomas Svoboda (CTU in Prague), Karel Zimmermann (CTU in Prague), David Hurych (CTU in Prague)

Efficient and Scalable $4$-th order Match Propagation

David Ok (Imagine ENPC), Renaud Marlet

Hierarchical Object Representations for Visual Recognition via Weakly Supervised Learning

Tianzhu Zhang (ADSC)

Invariant Surface-Based Shape Descriptor for Dynamic Surface Encoding

Tony Tung (Kyoto University), Takashi Matsuyama

Linear Discriminant Analysis with Maximum Correntropy Criterion

Wei ZHOU (Waseda University)

AfNet: The Affordance Network

Karthik Mahesh Varadarajan (TU Wien)

A Directed Graphical Model for Linear Barcode Scanning from Blurred Images

Ling Chen (SWUFE)

A Probabilistic 3D Model Retrieval System using Sphere Image

Ke Ding (The Chinese University of HK), yunhui Liu (The Chinese University of Hong Kong)

Model Based Training, Detection and Pose Estimation of Texture-Less 3D Objects in Heavily Cluttered Scenes

Stefan Hinterstoisser (TU Muenchen), Vincent Lepetit (EPFL, Switzerland), Slobodan Ilic, Stefan Holzer (Technische Universität München), Kurt Konolige (Industrial Perception), Gary Bradski (Industrial Perception), Nassir Navab (TU Muenchen)

Boosting with Side Information

Jixu Chen (GE), Xiaoming Liu (General Electric), lsw@cs.albany.edu Lyu

Generalized Mutual Subspace Based Methods for Image Set Classification

Takumi Kobayashi (National Institute of AIST)

Segmentation, Grouping and Classification

Locality-constrained Active Appearance Model (PDF, code)

Xiaowei Zhao (ICT,CAS,China), Shiguang Shan (CAS, China), Xiujuan Chai (ICT,CAS), Xilin Chen (Institute of Computing Technology, Chinese Academy of Sciences)

Modeling Hidden Topics with Dual Local Consistency for Image Analysis

Peng Li (CASIA), Jian Cheng, Hanqing Lu (Institure of Automation, Chinese Academy of Sciences)

Design of Non-Linear Discriminative Dictionaries for Image Classification

Ashish Shrivastava (University of Maryland, CP), Hien Nguyen (University of Maryland, CP), Vishal Patel (University of Maryland, CP), Rama Chellappa (University of Maryland, CP)

Efficient Background Subtraction\\ under Abrupt Illumination Variations

Junqiu Wang (Osaka University), Yasushi Yagi

Naive Bayes Image Classification: beyond Nearest Neighbors (PDF)

Radu Timofte (K.U. Leuven), Tinne Tuytelaars (K.U.Leuven), Luc Van Gool (K.U. Leuven and ETH Zurich)

Contextual Pooling in Image Classification

Zifeng Wu (NLPR), YongZhen Huang (NLPR), Liang Wang (Institute of Automation, Chinese Academy of Sciences), Tieniu Tan (NLPR, CASIA, china)

Spatial Graph for Image Classification

Zifeng Wu (NLPR), YongZhen Huang (NLPR), Liang Wang (Institute of Automation, Chinese Academy of Sciences), Tieniu Tan (NLPR, CASIA, china)

Knowledge Leverage from Contours to Bounding Boxes: A Concise Approach to Annotation

Jie-Zhi Cheng, Feng-Ju Chang (Academia Sinica), Kuang-Jui Hsu (Academia Sinica), Yen-Yu Lin (Academia Sinica)

Efficient Pixel-Grouping based on Dempster's Theory of Evidence for Image Segmentation

Björn Scheuermann (Leibniz Universität Hannover), Markus Schlosser (Technicolor), Bodo Rosenhahn

Video Segmentation with Superpixels

Fabio Galasso (MPI Informatics), Bernt Schiele (MPI Informatics)

A Noise Tolerant Watershed Transformation with Viscous Force for Seeded Image Segmentation

Di Yang (The Australian National Univ), Stephen Gould (Australian National University), Marcus Hutter (The Australian National University)

Active Learning for Interactive Segmentation with Expected Confidence Change

Dan Wang (CAS), Canxiang Yan, Shiguang shan (ICT), xilin Chen

Cross Anisotropic Cost Volume Filtering for Segmentation

Vladislav Kramarev (Saarland University), Oliver Demetz (Saarland University), Christopher Schroers (Saarland University), Joachim Weickert (Saarland University)

Multi-layer Spectral Clustering for Video Segmentation

Xiaofei Di (ICT, CAS), Hong Chang, xilin Chen

Video Co-Segmentation

Jose Rubio (Computer Vision Center. UAB), Joan Serrat, Antonio López (Computer Vision Center, Univ. Autónoma de Barcelona)

Globally Minimal Path Method Using Dynamic Speed Functions Based on Progressive Wave Propagation

Wei Liao (University of Heidelberg, and DKFZ Heidelberg), Stefan Wörz, Karl Rohr

Vanishing Points Estimation and Line Classification in a Manhattan World

Lilian Zhang (Institute of Computer Science), Reinhard Koch

Online Learning for Fast Segmentation of Moving Objects (PDF)

Liam Ellis (Linkoping University), vasileios Zografos (Linkoping University)

A Linear Programming based Method for Joint Object Matching and Segmentation

Junyan Wang (Nanyang Technological Universi), Li Wang (Nanyang Technological University, ADM), Kap Luk Chan (Nanyang Technological University, Singapore), Martin Constable (Nanyang Technological University)

Using Models of Objects with Deformable Parts for Joint Categorization and Segmentation of Objects

Nikhil Naikal, Dheeraj Singaraju (UC Berkeley), Shankar Sastry (University of California, Berkeley)

A Robust Stereo Prior for Human Segmentation

Glenn Sheasby (Oxford Brookes University), Julien Valentin (Oxford Brookes University), Nigel Crook (Oxford Brookes University), Philip Torr (Oxford Brookes University)

Voronoi-based Extraction of a Feature Skeleton from Noisy Triangulated Surfaces

Tilman Wekel (TU-Berlin), Olaf Hellwich (TU-Berlin)

Maximal Cliques based Rigid Body Motion Segmentation with a RGB-D Camera

Kukulage Perera (Australian National University), Nick Barnes

Online Web-Data-Driven Segmentation of Selected Moving Objects in Videos

Xiang Xiang (Computer Science, JHU)

Multi-Level Structured Image Coding on High-Dimensional Image Representation

Jia Li (Yahoo! Research)

Incremental Slow Feature Analysis with Indefinite Kernel for Online Temporal Video Segmentation

Stephan Liwicki (Imperial College London), Stefanos Zafeiriou (Imperial College London), Maja Pantic (Imperial College London)

Texture classification based on BIMF monogenic signals

JianJia Pan (Department of Computer Science, Hong Kong Baptist University), YuanYan Tang (University of Macao )

Gabor-Based Novel Local, Texture, Shape and Color Descriptors for Image Classification

Atreyee Sinha (New Jersey Inst. of Technology), Sugata Banerji (New Jersey Institute of Technology), Chengjun Liu (New Jersey Institute of Technology)

Toward Perception-based Shape Decomposition

Tingting Jiang (Peking University), Zhongqian Dong, Chang Ma, Yizhou Wang (Peking University, China)

Co-Regularized PLSA for Multi-View Clustering

Yu Jiang (CASIA), Liu Jing, Zechao Li, Peng Li (CASIA), Hanqing Lu (Institure of Automation, Chinese Academy of Sciences)

Image/Video Retrieval and Medical Image Analysis

Automatic Grading of Cortical and PSC Cataracts using Retroillumination Lens Images

Xinting Gao* (Institute for Infocomm Researc), Damon (Wing kee Wong, ), Tian-Tsong Ng (Institute for Infocomm Research,?ASTAR, Singapore), Carol Cheung, Ching-Yu Cheng, Tien Yin Wong

Registration of Pre-operative CT and non-contrast-enhanced C-arm CT: An application to Trans-catheter Aortic Valve Implantation (TAVI)

Yongning Lu (National University of Singapo), Ying Sun (National University of Singapore), Rui Liao (Siemens Corporate Research and Technology), Sim Heng Ong (NUS, Singapore )

Automatic Webcam-based Human Heart Rate Measurements Using Laplacian Eigenmap

Lan Wei (National Engineering Laboratory for Video Technology, Peking University), Yonghong Tian (National Engineering Lab for Video Technology, Peking University), Yaowei Wang (Department of Electronic Engineering, Beijing Institute of Technology), Touradj Ebrahimi (Swiss Federal Institute of Technology), Tiejun Huang (National Engineering Lab for Video Technology, Peking University )

Superpixel Classification based Optic Disc Segmentation

Jun Cheng (Institute for Infocomm Researc), Jiang Liu, Yanwu Xu, Fengshou Yin, Damon (Wing kee Wong, ), Ngan-Meng Tan, Ching-Yu Cheng, Yih Chung Tham, Tien Yin Wong

Anterior Cruciate Ligament Segmentation from Knee MR Images Using Graph Cuts with Geometric and Probabilistic Shape Constraints

Hansang Lee (KAIST), Helen Hong (Seoul Women's University), Junmo Kim (KAIST )

Robust Mid-Sagittal Plane Extraction in 3-D Ultrasound Fetal Volume for First Trimester Screening

Kwanghee Lee (Sogang university), Sang Wook Lee (Sogang University, Korea)

Automatic skin lesion segmentation based on texture analysis and supervised learning

He Yingding (Beihang University), Xie Fengying (Beihang University)

Multiscale Convolutional Neural Networks for Vision–based Classification of Cells

Pierre BUYSSENS (Université de Caen), Abderrahim Elmoataz, Olivier Lézoray

Semantic-Context-Based Augmented Descriptor For Image Feature Matching

Samir Khoualed (LASMEA - FRANCE), Thierry Chateau (Institut Pascal (ex. LASMEA)), Umberto Castellani

A Real-Time Synthesis and Occlusion Removal of Intermediate Views with Stereo Matching

Seongyun Cho (Postech), JeongMok HA (POSTECH), Hong Jeong (POSTECH)

PEDIVHANDI: Multimodal indexation and retrieval system for lecture videos

Nhu Van NGUYEN (Appt 310, Le Ponant 3), Jean-Marc OGIER (University of La Rochelle )

Digitization of Deformed Documents using a High-speed Multi-camera Array

Yoshihiro Watanabe (University of Tokyo), Kotaro Itoyama, Masahiro Yamada (University of Tokyo), Masatoshi Ishikawa (Japan)

A Phase-based Approach for Caption Detection in Videos

Shu Wen (Xi'an Jiaotong University )

Efficient Clothing Retrieval with Semantic-Preserving Visual Phrases

Jianlong Fu (CASIA), Jin-qiao Wang (Institute of Automation, Chinese Academy of Scieces), Zechao Li, Hanqing Lu (Institure of Automation, Chinese Academy of Sciences)

Towards On-the-fly Large-Scale Object Category Retrieval

Ken Chatfield (University of Oxford), Andrew Zisserman (University of Oxford)

A Picture is Worth a Thousand Tags: Automatic Web Based Image Tag Expansion

Andrew Gilbert (University of Surrey), Richard Bowden

Image Retrieval using Eigen Queries

Nisarg Raval (IIIT Hyderabad), Rashmi Vilas Tonge (IIIT Hyderabad), Jawahar C V (IIIT, Hyderabad )

Fast and effective retrieval of plant leaf shapes

Bin Wang (Griffith University), Yongsheng Gao (Griffith University, Austrilia )

Complete Generic Camera Calibration and Modeling Using Spline Surfaces

Dennis Rosebrock (Technische Universität Braunschweig, Institut für Robotik und Prozessinformatik), Friedrich Wahl (Technische Universität Braunschweig, Institut für Robotik und Prozessinformatik )

q-Gaussian Mixture Models Based on Non-Extensive Statistics for Image And Video Semantic Indexing

Nakamasa Inoue (Tokyo Institute of Technology), Koichi Shinoda (Tokyo Institute of Technology )

Face/Gesture Analysis and Recognition

Modeling and Detection of Wrinkles in Aging Human Faces using Marked Point Processes

William Frick (University of Maryland College )

Recognizing Faces With Plastic Surgery: A Comprehensive Study

Xin Liu (Chinese Academy of Science), Shiguang Shan (CAS, China), Xilin Chen (Institute of Computing Technology, Chinese Academy of Sciences )

Enhancing Expression Recognition in the Wild with Unlabeled Reference Data

Mengyi Liu (Chinese Academy of Sciences), Shaoxin Li (Chinese Academy of Science), Shiguang Shan (CAS, China), Xilin Chen (Institute of Computing Technology, Chinese Academy of Sciences)

Benchmarking Still-to-Video Face Recognition via Partial and Local Discriminant Analysis on COX-S2V Dataset

Zhiwu Huang (ICT, CAS), Shiguang Shan (CAS, China), Haihong Zhang, Shihong Lao, xilin Chen

Fusing Magnitude and Phase Features for Robust Face Recognition

Yan Li (ICT, CAS), Shiguang Shan (CAS, China), Haihong Zhang, Shihong Lao, Xilin Chen (Institute of Computing Technology, Chinese Academy of Sciences )

Finding Happiest Moments in a Social Context (PDF, supplementary material)

Abhinav Dhall (Australian National University), Jyoti Joshi (University of Canberra), Ibrahim Radwan (University of Canberra), Roland Goecke (University of Canberra)

Sparsity sharing embedding for face verification

Donghoon Lee (KAIST), Hyunsin Park (KAIST), Junyoung Chung (KAIST), Youngook Song (KAIST), cHANG YOO (KAIST )

Semantic Pixel Sets based Local Binary Patterns for Face Recognition

Zhenhua Chai (Chinese Academy of Sciences), Heydi Mendez-Vazquez, Ran He, Zhenan Sun (Institute of Automation, Chinese Academy of Sciences(CASIA) ), Tieniu Tan (NLPR, CASIA, china)

An Adaptation Framework for Head Pose Estimation in Dynamic Multi-view Scenarios

Anoop Rajagopal (Indian Institute of Science), Ramanathan Subramanian (University of Trento), Radu Vieriu (“Gheorghe Asachi” Technical University, Iasi, Romania), Elisa Ricci (University of Perugia, Italy), Oswald Lanz (FBK Fondazione Bruno Kessler), Nicu Sebe (University of Trento, Italy), Kalpathi Ramakrishnan (Indian Institute of Science )

Face Parts Localization Using Structured-Output Regression Forests (PDF) - formely: Face Parts Localization Using Structured-output Regression Forests

Heng Yang (Queen Mary Univ. of London), Ioannis Patras (Queen Mary, University of London)

Human Face Super-Resolution Based on NSCT

Jing Liu (Tsinghua university )

Digital Paparazzi:\\ Spotting Celebrities in Professional Photo Libraries

Sina Jafarpour (Yahoo! Research), Jia Li (Yahoo! Research), Reolof van Zwol (Netflix)

Nighttime Face Recognition at Long Distance: Cross-distance and Cross-spectral Matching

Hyunju Maeng (Korea University), Shengcai Liao, Dong-oh Kang, Seong-Whan Lee, Anil K. Jain

Hand Posture Recognition from Disparity Cost Map

Wang Hanjie (ICTCAS), wang qi (ICTCAS), xilin Chen

Qualitative Pose Estimation by Discriminative Deformable Part Models (PDF)

Hyungtae Lee (University of Maryland), Vlad Morariu, Larry Davis

Learning Discriminant Face Descriptor for Face Recognition

Zhen Lei (CBSR), Stan Li

Optimal Operator Space Pursuit: A Framework for Video Sequence Data Analysis

Xiao Bian (North Carolina State Univ)

Cross-view Graph Embedding

Zhiwu Huang (ICT, CAS), Shiguang Shan (CAS, China), Haihong Zhang, Shihong Lao, xilin Chen

Fast Training of Effective Multi-class Boosting Using Coordinate Descent Optimization

Guosheng Lin (The University of Adelaide), Chunhua Shen (University of Adelaide, Australia), David Suter (The University of Adelaide), anton van den Hengel (The University of Adelaide )

Hierarchical Space Tiling in Scene Modeling

Shuo Wang (Peking University), Yizhou Wang (Peking University, China), Song-Chun Zhu (UCLA )

Motion, Tracking and Computational Photography

Dynamic Objectness for Adaptive Tracking (PDF, videos)

Severin Stalder (ETH Zurich), Helmut Grabner (ETH Zurich), Luc Van Gool (ETH Zurich)

Visual Tracking in Continuous Appearance Space via Sparse Coding

Guofeng Wang (Shandong University), Fan Zhong (Shandong University), Yue Liu (Academy of Mathematics and Systems Science, CAS), Qunsheng Peng (Zhejiang University), Xueying Qin

Robust Object Tracking in Crowd Dynamic Scenes using Explicit Stereo Depth

Chi Li (Xiamen University), le lu (Siemens Corporate Research), Gregory Hager (Johns Hopkins University), Jianyu Tang (Xiamen University), Hanzi Wang (Xiamen University, China)

Structured Tracker with Dynamic Graph

Zhaowei Cai (CBSR.CASIA), Longyin Wen (CBSR.CASIA), Yang Jianwei (NLPR), Zhen Lei (CBSR), Stan Z. Li (CBSR.CASIA)

Online Multi-Target Tracking by Large Margin Structured Learning (PDF)

SunA Kim (POSTECH), Suha Kwak (POSTECH), Jan Feyereisl (POSTECH), Bohyung Han (POSTECH, Korea)

An Anchor Patch Based Optimization Framework For Reducing Optical Flow Drift in Long Image Sequences (PDF)

Wenbin Li (University of Bath), Darren Cosker (University of Bath), Matthew Brown (University of Bath)

One-Class Multiple Instance Learning and Applications to Target Tracking

Karthik Sankaranarayanan (IBM), Jim Davis (Ohio State University)

Dense Scene Flow Based on Depth and Multi-Channel Bilateral Filter

Xiao wei Zhang (Xi'an Jiaotong University)

Object Tracking Within the Framework of

Li Chen (SJTU), yue zhou (sjtu)

Multiple Target Tracking Using Frame-Triplets (PDF)

Asad Butt (Penn State), Robert Collins (Penn State)

Spatio-temporal clustering model for multi-object tracking through occlusions

Lei Zhang (Northwestern Polytechnical University), Qing Wang (Northwestern Polytechnical University)

Robust Object Tracking Using Constellation Model with Superpixel

Weijun Wang (USC), Ram Nevatia (USC)

Robust registration-based tracking by sparse representation with model update

Peihua Li (Heilongjiang University), Qilong Wang

Robust and Efficient Pose Estimation from Line Correspondences

Lilian Zhang (Institute of Computer Science), Chi Xu, Kok-Meng Lee, Reinhard Koch

Nonlocal Spectral Prior Model for Low-level Vision

Shenlong Wang (Northwestern Polytechnic Univ.), Lei Zhang (Hong Kong Polytechnic University, Hong Kong, China), Yan Liang (Northwestern Polytechnical University)

Simultanious Multiple Rotation Averaging using Lagrangian Duality

Carl Olsson (Lund University), Johan Fredriksson (Lund University)

Observation-Driven Adaptive Differential Evolution for Robust Bronchoscope 3-D Motion Tracking

Xiongbiao Luo (Nagoya University), Kensaku Mori, Takayuki Kitasaka

Tracking Growing Axons by Particle Filtering in 3D+t Fluorescent Two-Photon Microscopy Images

Huei-Fang Yang (INRIA, France), Xavier Descombes, Charles Kervrann (INRIA, France), Caroline Medioni, Florence Besse

Image upscaling using multiple dictionaries of natural image patches

Pulak Purkait (Indian Statistical Institute), Bhabatosh Chanda (Indian Statistical Institute)

A Biologically Motivated Double-Opponency Approach to Illumination Invariance

Sivalogeswaran Ratnasingam (NICTA), Antonio Robles-Kelly (NICTA)

Measuring Linearity of Closed Curves and Connected Compound Curves

Paul Rosin (Cardiff University), Jovanka Pantovic (University of Novi Sad), Jovisa Zunic (Exeter University)

Patch Mosaic for Fast Motion Deblurring

Hyeoungho Bae (University of California, Irvi), Charless Fowlkes (UC Irvine), Pai Chou (Univ of California Irvine)

Single-image blind deblurring for non-uniform camera-shake blur

Yuquan Xu (IACAS), Lu Wang, Xiyuan Hu, Silong Peng

Image Super-Resolution Using Local Learnable Kernel Regression

Renjie Liao (Beihang University), Zengchang Qin (Beihang University)

Nonlocal Low Rank Modeling for Interpolation

Kaiden Matthew (University of California, Los )

MRF-based Blind Image Deconvolution

Nikos Komodakis (U. Crete, Greece), Nikos Paragios (Ecole Centrale de Paris)

Efficient Image Appearance Description Using Dense Sampling Based Local Binary Patterns

Juha Ylioinas (University of Oulu), Abdenour Hadid (University of Oulu), Yimo Guo (University of Oulu), Matti Pietikäinen (University of Oulu)

Navigation toward Non-static Target Object using Footprint Detection based Tracking

Meng Yi (Temple University), yinfei Yang (University of Pennsylvania), Wenjing Qi (Temple University), Yu Zhou (Huazhong University of Science and Technology ), yunfeng Li (Purdue University), Zygmunt Pizlo (Purdue University), Longin Jan Latecki (Temple)

Single Image Super Resolution Reconstruction in Perturbed Exemplar Sub-Space

Takashi Shibata (NEC), Akihiko Iketani (NEC), Shuji Senda (NEC)

Image Super-Resolution: Use of Self-learning and Gabor Prior

Nilay Khatri (DA-IICT), Manjunath Joshi (DAIICT, Gandhinagar)

Video Analysis and Action Recognition

Fast Iterative Semi-Global Matching for Robust Driver Assistance Systems

Simon Hermann (The University of Auckland), Reinhard Klette (The University of Auckland)

Action Recognition using Canonical Correlation Kernels

Nagendar G (IIIT Hyderabad), Sai Ganesh B, Mahesh Goud Tandarpally, Jawahar C V (IIIT, Hyderabad)

A New Framework for Background Subtraction Using Multiple Cues

SeungJong Noh (GIST in S.Korea), Moongu Jeon (gist.ac.kr)

Weighted Interaction Force Estimation for Abnormal Detection in Crowd Scenes

Xiaobin Zhu (NLPR, CASIA, China), Liu Jing, Jin-qiao Wang (Institute of Automation, Chinese Academy of Scieces), Wei Fu, Hanqing Lu (Institure of Automation, Chinese Academy of Sciences)

Egocentric Activity Monitoring and Recovery

Ardhendu Behera (University of Leeds), David Hogg (University of Leeds), Anthony Cohn (University of Leeds)

Spatiotemporal Salience via Centre-Surround Comparison of Visual Spacetime Orientations

Andrei Zaharescu (Aimetis), Richard Wildes (York U)

Temporal-Spatial Refinements for Video Concept Fusion

Jie Geng (Beijing Jiaotong University), Zhenjiang Miao (Beijing Jiaotong University)

Features with Feeling---Incorporating User Preferences in Video Categorization

Ramya Srinivasan (UC, Riverside), Amit Roy Chowdhury

A Comparative Study of Encoding, Pooling and Normalization Methods for Action Recognition

Xingxing Wang (Siat), LiMin Wang (CUHK), Yu Qiao

Dynamic saliency models and human attention: a comparative study on videos

Nicolas Riche, Matei Mancas (University of Mons (UMONS)), Dubravko Culibrk, Vladimir Crnojevic, Beranrd Gosselin, Thierry Dutoit

Horror Video Scene Recognition based on Multi-view Multi-instance Learning

Xinmiao Ding (China University of Mining and), Bing Li, Weihua Xiong, Weiming Hu (NLPR, Casia, P.R.C), Zhenchong Wang

Learning Object Appearance from Occlusions using Structure and Motion Recovery

Kai Cordes (Universität Hannover)

Exploring the similarities of neighboring spatiotemporal points for action pair matching

IRENE KOTSIA (Queen Mary University of Londo), Ioannis Patras (Queen Mary, University of London)

Sequential Reconstruction Segment-Wise Feature Track and Structure Updating Based on Parallax Paths

Mauricio Hess-Flores (UC Davis), Mark Duchaineau (Google), Kenneth Joy (UC Davis)

Generic Active Appearance Models Revisited

Stefanos Zafeiriou (Imperial College London), Georgios Tzimiropoulos (Imperial College London), Maja Pantic (Imperial College London), Joan Medina (Imperial College London)

Tracking Pedestrian with Multi-Component Online Deformable Part-Based Model

Yi Xie (Beijing Institute of Technolog), Mingtao Pei (bit.edu.cn), Zhao Liu (cppsu.edu.cn), Tianfu Wu (bupt.edu.cn)

Local Distance Comparison for Multiple-shot People Re-Identification

Guanwen Zhang (Nagoya University), Yu Wang, Jien Kato (Nagoya University), Takafumi Marutani (Nagoya University), Kenji Mase (Nagoya University)

Non-Sequential Multi-View Detection, Localization and Identification of People using Multi-Modal Feature Maps

Rok Mandeljc (University of Ljubljana), Stanislav Kovacic (University of Ljubljana, Faculty of Electrical Engineering), Matej Kristan (University of Ljubljana, Faculty of Electrical Engineering), Janez Pers (University of Ljubljana)

Full 6DOF Pose Estimation from Geo-Located Images

Clemens Arth (Graz University of Technology), Gerhard Reitmayr (Graz University of Technology), Dieter Schmalstieg (Graz University of Technology)

Learning a Quality-Based Ranking for Feature Point Trajectories

Liangjing Ding (Florida State University), Adrian Barbu, Anke Meyer-Baese

Shape from X and Photometry

Toward Efficient Acquisition of BRDFs with Fewer Samples

Muhammad Asad Ali (University of Tokyo), Imari Sato (NII, Japan), Takahiro Okabe (University of Tokyo), Yoichi Sato (University of Tokyo)

Shadow-free TILT for Facade Rectification

Lumei Li (China University of Geoscience), hongping Yan, Lingfeng Wang (NLPR), Pan Chunhong

Reconstructing Shape from Dictionaries of Shading Primitives

Alexandros Panagopoulos (Stony Brook University), Sunil Hadap, Dimitris Samaras

Iterative Feedback Estimation of Depth and Radiance from Defocused Images

Xing Lin (Tsinghua), Jinli Suo (Tsinghua University, China), Xun Cao, Qionghai Dai (Tsinghua University)

Two-Image Perspective Photometric Stereo using Shape-from-Shading

Roberto Mecca (Technion), Ariel Tankus (Technion), Alfred Bruckstein (Technion)

Stable two view reconstruction using the six-point algorithm

Kazuki Nozawa (Tokyo Institute of Technology), Akihiko Torii (Tokyo Institute of Technology), Masatoshi Okutomi

Unknown Radial Distortion Centers in Multiple View Geometry Problems

José Henrique Brito (IPCA), Roland Angst (ETH Zurich), Kevin Koeser (ETH Zurich), Christopher Zach (ETH Zurich), Pedro Branco (Universidade do Minho), Manuel João Ferreira, Marc Pollefeys (ETH Zurich)

Depth-Estimation-Free Condition for Projective Factorization and Its Application to 3D Reconstruction

Yohei Murakami, Takeshi Endo, Yoshimichi Ito (Osaka University), Noboru Babaguchi

Epipolar Geometry Estimation for Urban Scenes with Repetitive Structures

Maria Kushnir (Haifa University), Ilan Shimshoni

Non-Rigid Self-Calibration Of A Projective Camera

Hanno Ackermann (Leibniz University Hannover), Bodo Rosenhahn

Piecewise Planar Scene Reconstruction and Optimization for Multi-View Stereo

Hyojin Kim (UC Davis), Nelson Max, Hong Xiao

A Bayesian Approach to Uncertainty-Based Depth Map Super Resolution

Jing Li (Peking University), Gang Zeng (Peking University)

Cross Image Inference Scheme for Stereo Matching

Xiao Tan (CSIRO), Changming Sun, Xavier Sirault (CSIRO), Robert Furbank (CSIRO), Tuan Pham

Bayesian Epipolar Geometry Estimation from Tomographic Projections

Sami Brandt (University of Copenhagen), Katrine Hommelhoff Jensen (University of Copenhagen), Francois Lauze

On the Global Self-calibration of Central Cameras using Two Infinitesimal Rotations

Ferran Espuny (Université Paris-Descartes)

Adaptive Structure from Motion with a contrario model estimation (poster, PDF, code) - formely: Adaptive Structure from Motion with a contrario model estimations

Pierre Moulon (LIGM/Mikros Image), Pascal Monasse, Renaud Marlet

Precious 3D reconstruction from a single image

Changqing Zou (SIAT, China), jianzhuang Liu

An Efficient Image Matching Method for Multi-View Stereo

Shuji Sakai (Tohoku University), Koichi Ito (Tohoku University), Takafumi Aoki (Tohoku University), Tomohito Masuda (Toppan Printing Co., Ltd.), Hiroki Unten (Toppan Printing Co., Ltd.)

Self-calibration of PTZ camera using new LMI constraints

François Rameau (Le2i), Adlane Habed (Le2i), Cédric Demonceaux (Le2i), Désiré Sidibé (Le2i), David Fofi (Le2i)

Fast 3D surface reconstruction from point clouds using graph-based fronts propagation

EL Chakik Abdallah (GREYC, IMAGE TEAM), Xavier Desquesnes (GREYC), Abderrahim Elmoataz (GREYC - image team)

Low-level Vision and Applications of Computer Vision

Motion-Invariant Coding Using a Programmable Aperture Camera

Toshiki Sonoda (Kyushu University), Hajime Nagahara (Kyushu University), Rin-ichiro Taniguchi (Kyushu University)

Color-aware Regularization for Gradient Domain Image Manipulation

Fanbo Deng (National Univ. of Singapore), Seon Joo Kim (SUNY Korea), Yu-Wing Tai (KAIST), Michael Brown (NUS, Singapore)

Local Covariance Filtering for Color Images (PDF, code)

Keiichiro Shirai (Shinshu Univ.), Masahiro Okuda (Univ. of Kitakyushu), Takao Jinno (Toyohashi Univ. of Tech.), Masaaki Ikehara (Keio Univ.), Masayuki Okamoto (Shinshu Univ.)

A New Projection Space for Separation of Specular and Diffuse Re?ection Components in Color Images

Yang Jianwei (NLPR), Zhaowei Cai (CBSR.CASIA), Longyin Wen (CBSR.CASIA), Zhen Lei (CBSR), Guodong Guo, Stan Z. Li (CBSR.CASIA)

Hand Vein Recognition based on Oriented Gradient Maps and Local Feature Matching

Di Huang (Beihang University), Yinhang Tang (Beihang University), Yiding Wang (North China University of Technology), Liming Chen (Ecole Centrale de Lyon), Yunhong Wang

Fusing Warping, Cropping, and Scaling for Optimal Image Thumbnail Generation

Zhan Qu (Chinese Academy of Sciences), Jin-qiao Wang (Institute of Automation, Chinese Academy of Scieces), Min Xu (iNEXT, School of Computing and Communications, University of Technology, Sydney), Hanqing Lu (Institure of Automation, Chinese Academy of Sciences)

Shift-Map Based Stereo Image Retargeting with Disparity Adjustment

Shaoyu Qi (University of Florida), Jeffrey Ho (University of Florida)

Object Templates for Visual Place Categorization

Hao Yang (NTU), Jianxin Wu (NTU, Singapore)

Visual Business Recognition - A Multimodal Approach

Amir Roshan zamir (UCF), afshin dehghan (UCF)

Reconstructing Sequential Patterns without Knowing Image Correspondences

Saba Miyan (Nagoya Institute of Technology), Jun Sato (Nagoya Institute of Technology)

Registration of Multi-View Images of Planar Surfaces

Jiri Filip (UTIA AS CR), Radomir Vavra (UTIA AS CR)

Automatic Stave Discovery for Musical Facsimiles (PDF, supplementary material)

Radu Timofte (K.U. Leuven), Luc Van Gool (K.U. Leuven and ETH Zurich)

Unsupervised Language Learning for Discovered Visual Concepts

PRITHWIJIT GUHA (TCS INNOVATION LABS), Amitabha Mukerjee (IIT Kanpur)

Parameterized Variety Based View Synthesis Scheme for Multi-View 3DTV

Mansi Sharma (IIT Delhi), Santanu Chaudhury (Indian Institute of Delhi), Brejesh Lall (IIT DELHI)

Quasi-Regular Facade Structure Extraction

Tian HAN (HKUST), CHUN LIU (HKUST), peng ZHAO (HKUST), chiew-Lan TAI (HKUST), Long Quan (HKUST)

Multi-view Synthesis Based on Single View Reference Layer

Yang-Ho Cho (Samsung Electronics Co., Ltd.), Ho-Young Lee, Du-Sik Park

Hand-Eye Calibration without Hand Orientation Measurement Using Minimal Solution

Zuzana Kukelova (CTU in Prague), Jan Heller (CTU in Prague), Tomas Pajdla (CTU in Prague)

Detecting changes in images of street scenes

Jana Kosecka (George Mason University)

Adaptive Background Defogging with Foreground Decremental Preconditioned Conjugate Gradient

Jacky Shun-Cho Yuk (The University of Hong Kong), Kwan-Yee Kenneth Wong (HKU, Hong Kong)

A Shadow Repair Approach for Kinecr Depth Maps

Yu Yu (Xi'an Jiaotong Universtity)

A Unified Framework for Line Extraction in Dioptric and Catadioptric Cameras

Jesus Bermudez-Cameo (Universidad de Zaragoza), Gonzalo Lopez-Nicolas (Universidad de Zaragoza), Josechu Guerrero

Fusion of time-of-flight and stereo for unambiguous wide range depth measurements

Ouk Choi (SAIT), Seungkyu Lee