ACCV 2016 Main Conference

Monday, November 21–Wednesday, November 23

Day 1:
Monday, November 21
Day 2:
Tuesday, November 22
Day 3:
Wednesday, November 23
0800 Registration starts 08:30 Registration starts 08:30 Registration starts
08450900 Opening session
09001030 Oral session 1 Oral session 3 Oral session 5
10301100 Coffee break Coffee break Coffee break
11001200 Keynote:
Prof. Jitendra Malik
Keynote:
Prof. Katsushi Ikeuchi
Keynote:
Prof. Marc Pollefeys
12001330 Lunch break Lunch break Lunch break
13301530 Poster session 1
Demos
Poster session 2
Demos
Poster session 3
Demos
15301600 Coffee break Coffee break Coffee break
16001715 Oral session 2 Oral session 4 Oral session 6
18302130 Banquet at Humble House
(Cultural and entertainment activities start at 5:30 pm.)

Oral sessions

Day 1: Monday, November 21

Oral session 1 : 09:00-10:30

No. SESSION 1: Segmentation and Classification
O1-1 Realtime Hierarchical Clustering based on Boundary and Surface Statistics
Dominik Klein, Fraunhofer FKIE; Dirk Schulz, Fraunhofer FKIE; Armin Cremers, Bonn-Aachen International Center for Information Technology
O1-2 Weakly-supervised Video Scene Co-parsing
Guangyu Zhong, Dalian University of Technolog; Yi-Hsuan Tsai, UC Merced; Ming-Hsuan Yang, UC Merced
O1-3 Supervoxel-based Segmentation of 3D Volumetric Images
Chengliang Yang, University of Florida; Manu Sethi, University of Florida; Anand Rangarajan, University of Florida; Sanjay Ranka, University of Florida
O1-4 Message Passing on the Two-Layer Network for Geometric Model Fitting
Xing Wang, Xiamen University ; Guobao Xiao, Xiamen University; Yan Yan, Xiamen University; Hanzi Wang, Xiamen University
O1-5 Deep Supervised Hashing with Triplet Labels
Xiaofang Wang, Carnegie Mellon University; Yi Shi, Carnegie Mellon University; Kris Kitani, Carnegie Mellon University
O1-6 Boosting Zero-Shot Image Classification via Pairwise Relationship Learning
Hanhui Li, Sun Yat-sen University; Hefeng Wu, Guangdong University of Foreign Studies,; Shujin Lin, Sun Yat-sen University; Liang Lin, Sun Yat-sen University; Xiaonan Luo, Sun Yat-sen University; Ebroul Izquierdo, Queen Mary University of London

Oral session 2 : 16:00-17:15

No. SESSION 2: People and Actions
O2-1 Sparse Code Filtering for Action Pattern Mining
Wei Wang, University of Trento; Yan Yan, University of Trento; Liqiang Nie, National University of Singapore; Luming Zhang, Advanced Digital Sciences Center; Stefan Winkler, Hefei University of Technology; Nicu Sebe, University of Trento
O2-2 Learning Action Concept Trees and Semantic Alignment Networks from Image-Description Data
Jiyang Gao, University of Southern California; Ram Nevatia, University of Southern California
O2-3 Pedestrian Color Naming via Convolutional Neural Network
Zhiyi Cheng, The Chinese University of Hong Kong; Xiaoxiao Li, The Chinese University of Hong Kong; Chen Change Loy, The Chinese University of Hong Kong
O2-4 Speed Invariance vs. Stability: Cross-Speed Gait Recognition Using Single-Support Gait Energy Image
Chi Xu, Nanjing University of Science & Technology / Osaka University ; Yasushi Makihara, Osaka University; Xiang Li, Nanjing University of Science & Technology / Osaka Univ.; Yasushi Yagi, Osaka University; Jianfeng Lu, Nanjing University of Science & Technology
O2-5 Parametric Image Segmentation of Humans with Structural Shape Priors
Alin Popa, Institute of Mathematics of the Romanian Academy; Cristian Sminchisescu, Lund University
Day 2: Tuesday, November 22

Oral session 3 : 09:00-10:30

No. SESSION 3: Faces
O3-1 Lip Reading in the Wild
Joon Son Chung, University of Oxford; Andrew Zisserman, University of Oxford
O3-2 Recurrent Convolutional Face Alignment
Wei Wang, University of Trento; Sergey Tulyakov, University of Trento; Nicu Sebe, University of Trento
O3-3 Continuous Supervised Descent Method for Facial Landmark Localisation
Marc Oliu, University of Barcelona; Ciprian Corneanu, University of Barcelona; L´aszl´o A. Jeni, Carnegie Mellon University;  Jeffrey F. Cohn, Carnegie Mellon University and University of Pittsburgh; Takeo Kanade, Carnegie Mellon University; Sergio Escalera, University of Barcelona
O3-4 Modeling Stylized Character Expressions via Deep Learning
Deepali Aneja, University of Washington; Alex Colburn, Zillow Group; Gary Faigin, Gage Academy of Art; Linda Shapiro, University of Washington; Barbara Mones, University of Washington
O3-5 Variational Gaussian Process Auto-Encoder for Ordinal Prediction of Facial Action Units
Stefanos Eleftheriadis, Imperial College London; Ognjen Rudovic, Imperial College London; Marc Deisenroth, Imperial College London; Maja Pantic, Imperial College London
O3-6 Multi-instance Dynamic Ordinal Random Fields for weakly-supervised pain intensity estimation
Adrià Ruiz, Universitat Pompeu Fabra; Ognjen Rudovic, Imperial College London; Xavier Binefa, Universitat Pompeu Fabra; Maja Pantic, Imperial College London

Oral session 4 : 16:00-17:15

No. SESSION 4: Computational Photography and Image Processing
O4-1 Blind Image Quality Assessment Based on Natural Redundancy Statistics
Jia Yan, Wuhan University; Weixia Zhang, Wuhan University; Tianpeng Feng, Wuhan University
O4-2 Sparse Coding on Cascaded Residuals
Tong Zhang, The Australian National Univ.; Fatih Porikli, Australian National University / CSIRO
O4-3 End-To-End Learning for Image Burst Deblurring
Patrick Wieschollek, University of Tuebingen; Bernhard Schölkopf, Max Planck Institute for Intelligent Systems; Hendrik P.A. Lensch, University of Tubingen; Michael Hirsch, Max Planck Institute for Intelligent Systems
O4-4 Spectral Reflectance Recovery with Interreflection Using a Hyperspectral Image
Hiroki Ohkawa, Tokyo Institute of Technology; Yinqiang Zheng, National Institute of Informatics; Antony Lam, Saitama University; Imari Sato, National Institute of Informatics
O4-5 Learning Contextual Dependencies for Optical Flow with Recurrent Neural Networks
Minlong Lu, Zhejiang University; Zhiwei Deng, Simon Fraser University; Ze-Nian Li, Simon Fraser University
Day 3: Wednesday, November 23

Oral session 5 : 09:00-10:30

No. SESSION 5: Language and Video
O5-1 Auto-Illustrating Poems and Songs with Style
Katharina Schwarz, University of Tübingen; Tamara Berg, UNC Chapel Hill; Hendrik P.A. Lensch, University of Tubingen
O5-2 Spatio-Temporal Attention Models for Grounded Video Captioning
Elisabeta Marinoiu, Institute of Mathematics of the Romanian Academy; Mihai Zanfir, Institute of Mathematics of the Romanian Academy; Cristian Sminchisescu, Lund University
O5-3 Variational Convolutional Networks for Human-Centric Annotations
Tsung-Wei Ke, Academia Sinica; Che-Wei Lin, Appier Inc; Tyng-Luh Liu, Academia Sinica; Davi Geiger, NYU
O5-4 Anticipating Accidents in Dashcam Videos
Fu-Hsiang Chan, National Tsing Hua University; Yu-Ting Chen, National Tsing Hua University; Yu Xiang, Stanford University; Min Sun, National Tsing Hua University
O5-5 Pano2Vid: Automatic Cinematography for Watching 360-Degree Videos
Yu-Chuan Su, University of Texas at Austin; Dinesh Jayaraman, University of Texas at Austin; Kristen Grauman, University of Texas at Austin
O5-6 PicMarker: Data-Driven Image Categorization Based on Iterative Clustering
Jiagao Hu, Nanjing University; Zhengxing Sun, Nanjing University; Bo Li, Nanjing University; Shuang Wang, Nanjing University

Oral session 6 : 16:00-17:15

No. SESSION 6: 3D Vision
O6-1 Divide and Conquer: Efficient Density-Based Tracking of 3D Sensors in Manhattan Worlds
Yi Zhou, Australian National University; Laurent Kneip, Australian National University; Cristian Rodriguez, Australian National University; Hongdong Li, Australian National University
O6-2 Visual Saliency Detection for RGB-D Images with Generative Model
Song-Tao Wang, Harbin University of Science & Technology and Beijing Academy of Science and Technology; Zhen Zhou, Harbin University of Science & Technology; Han-Bing Qu, Beijing Academy of Science and Technology; Bin Li, Beijing Academy of Science and Technology
O6-3 A Coarse-to-Fine Indoor Layout Estimation (CFILE) Method
Yuzhuo Ren, University of Southern California; Shangwen Li, University of Southern California; Chen Chen, University of Southern California; C.-C. Jay Kuo, University of Southern California
O6-4 Unifying Algebraic Solvers for Scaled Euclidean Registration from Point, Line and Plane Constraints
Folker Wientapper, Fraunhofer IGD; Arjan Kuijper, TU Darmstadt
O6-5 Generalized Fusion Moves for Continuous Label Optimization
Christopher Zach, Toshiba Research Europe

Poster sessions

Day 1: Monday, November 21

Poster session 1 : 13:30-15:30

No. Segmentation and Semantic Segmentation
P1-01 Hierarchical Supervoxel Graph for Interactive Video Object Representation and Segmentation
Xiang Fu, USC; Changhu Wang, Microsoft; C.-C. Jay Kuo, USC
P1-02 Learning to Generate Object Segmentation Proposals with Multi-modal Cues
Haoyang Zhang, The Australian National University and CSIRO; Xuming He, The Australian National University and CSIRO; Fatih Porikli, The Australian National University and CSIRO
P1-03 Saliency Detection via Diversity-Induced Multi-view Matrix Decomposition
Xiaoli Sun, Shenzhen University; Zhixiang He, Shenzhen University; Xiujun Zhang, Shenzhen Polytechnic; Wenbin Zou, Shenzhen University; George Baciu, Hongkong Ploytechnic University
P1-04 Parallel Accelerated Matting Method Based on Local Learning
Xiaoqiang Li, Shanghai University; Qing Cui, Shanghai University
P1-05 Semi-Supervised Domain Adaptation for Weakly Labeled Semantic Video Object Segmentation
Huiling Wang, Aalto University; Tapani Raiko, Aalto University; Lasse Lensu, Lappeenranta University of Technology; Tinghuai Wang, Nokia Technologies; Juha Karhunen, Aalto University
P1-06 Semantic Segmentation of Earth Observation Data Using Multimodal and Multi-Scale Deep Networks
Nicolas Audebert, ONERA; Bertrand Le Saux, ONERA; Sébastien Lefèvre, IRISA
P1-07 Object Boundary Guided Semantic Segmentation
Qin Huang, USC; Chunyang Xia, USC; Wenchao Zheng, USC; Yuhang Song, USC; Hao Xu, USC; C.-C. Jay Kuo, USC
P1-08 FuseNet: Incorporating Depth into Semantic Segmentation via Fusion-based CNN Architecture
Caner Hazırbaş, TU München; Lingni Ma, TU München; Csaba Domokos, TU München; Daniel Cremers, TU München
P1-09 Point-Cut: Interactive Image Segmentation using point Supervision
Changjae Oh, Yonsei University; Bumsub Ham, Yonsei University; Kwanghoon Sohn, Yonsei University
P1-10 A Holistic Approach for Data-Driven Object Cutout
Huayong Xu, Shandong University; Yangyan Li, Tel Aviv University; Wenzheng Chen, Shandong University; Dani Lischinski, Hebrew University of Jerusalem; Daniel Cohen-Or, Tel Aviv University; Baoquan Chen, Shandong University
P1-11 Interactive Segmentation from 1-Bit Feedback
Ding-Jie Chen, National Tsing Hua University; Hwann-Tzong Chen, National Tsing Hua University; Long-Wen Chang, National Tsing Hua University
P1-12 Geodesic Distance Histogram Feature for Video Segmentation
Hieu Le, Stony Brook University; Vu Nguyen, Stony Brook University; Chen-Ping Yu, Stony Brook University; Dimitris Samaras, Stony Brook University
P1-13 HF-FCN: Hierarchically Fused Fully Convolutional Network for Robust Building Extraction
Tongchun Zuo, University of Science and Technology of China; Juntao Feng, University of Science and Technology of China; Xuejin Chen, University of Science and Technology of China
No. Dictionary Learning, Retrieval, and Clustering
P1-14 Dictionary Reduction: Automatic Compact Dictionary Learning for Classification
Yang Song, University of Tennessee, Knoxville; Zhifei Zhang, University of Tennessee, Knoxville; Liu Liu, University of Tennessee, Knoxville; Alireza Rahimpour, University of Tennessee, Knoxville; Hairong Qi, University of Tennessee, Knoxville
P1-15 A Vote-and-Verify Strategy for Fast Spatial Verification in Image Retrieval
Johannes Schönberger, ETH Zürich; True Price, UNC Chapel Hill; Torsten Sattler, ETH Zürich; Jan-Michael Frahm, UNC Chapel Hill; Marc Pollefeys, ETH Zürich
P1-16 SSP: Supervised Sparse Projections for Large-Scale Retrieval in High Dimensions
Frederick Tung, University of British Columbia; Jim Little, University of British Columbia
P1-17 An Online Algorithm for Efficient and Temporally Consistent Subspace Clustering
Vasileios Zografos, Technical University Munich; Kai Krajsek, Forschungszentrum Juelich; Bjoern Menze, TU Munich
P1-18 Sparse Gradient Pursuit for Robust Visual Analysis
Jiangxin Dong, Dalian University of Technology; Risheng Liu, Dalian University of Technology; Kewei Tang, Liaoning Normal University; Yiyang Wang, Dalian University of Technology; Xindong Zhang, Dalian University of Technology; Zhixun Su, Dalian University of Technology
P1-19 F-SORT: An Alternative for Faster Geometric Verification
Jacob Chan, Nanyang Technological University; Jimmy Lee, ASTAR; Kemao Qian, Nanyang Technological University
P1-20 Clustering Symmetric Positive Definite Matrices on the Riemannian Manifolds
Ligang Zheng, Guangzhou University; Guoping Qiu, University of Nottingham Ningbo China; Jiwu Huang, Shenzhen University
P1-21 Subspace Learning Based Low-Rank Representation
Kewei Tang, Liaoning Normal University; Xiaodong Liu, Dalian University of Technology; Zhixun Su, Dalian University of Technology; Wei Jiang, Liaoning Normal University; Jiangxin Dong, Dalian University of Technology
No. Deep Learning
P1-22 Analysis on the Dropout Effect in Convolutional Neural Networks
Sungheon Park, Seoul National University; Nojun Kwak, Seoul National University
P1-23 Efficient Model Averaging for Deep Neural Networks
Michael Opitz, Graz University of Technology; Horst Possegger, Graz University of Technology; Horst Bischof, Graz University of Technology
P1-24 Joint Training of Generic CNN-CRF Models with Stochastic Optimization
Alexander Kirillov, TU Dresden; Dmitrij Schlesinger, TU Dresden; Shuai Zheng, University of Oxford; Bogdan Savchynskyy, TU Dresden; Philip Torr, University of Oxford; Carsten Rother, TU Dresden
P1-25 Object-Aware Dictionary Learning with Deep Features
Yurui Xie, Australian National University; Fatih Porikli, Australian National University; Xuming He, Australian National University
No. People Tracking and Action Recognition
P1-26 Gait Energy Response Function for Clothing-Invariant Gait Recognition
Xiang Li, Nanjing Univ. of Sci. & Tech. / Osaka Univ.; Yasushi Makihara, Osaka Univ.; Chi Xu, Nanjing Univ. of Sci. & Tech./ Osaka Univ. ; Daigo Muramatsu, Osaka Univ.; Yasushi Yagi, Osaka University; Mingwu Ren, Nanjing Univ. of Sci. & Tech.
P1-27 Action Recognition Based on Optimal Joint Selection and Discriminative Depth Descriptor
Haomiao Ni, Chinese Academy of Sciences; Hong Liu, Chinese Academy of Sciences; Xiangdong Wang, Chinese Academy of Sciences; Yueliang Qian, Chinese Academy of Sciences
P1-28 Model-Free Multiple Object Tracking with Shared Proposals
Gao Zhu, Australian National University; Fatih Porikli, Australian National University; Hongdong Li, Australian National University
P1-29 Learning to integrate Occlusion-specific Detectors for Heavily Occluded Pedestrian Detection
Chunluan Zhou, NTU; Junsong Yuan, Nanyang Technological University
P1-30 Deep Second-Order Siamese Network for Pedestrian Re-identification
Xuesong Deng, Chinese Academy of Sciences; Bingpeng Ma, Chinese Academy of Sciences; Hong Chang, Chinese Academy of Sciences; Shiguang Shan, Chinese Academy of Sciences; Xilin Chen, Chinese Academy of Sciences
P1-31 Cost-sensitive Two-stage Depression Prediction using Dynamic Visual Clues
Xingchen Ma, Beihang University; Di Huang, Beihang University; Yunhong Wang, Beihang University; Yiding Wang, North China University of Technology
P1-32 Human Interaction Recognition by Mining Discriminative Patches on Key Frames
Dingyi Shan, University of Chinese Academy of Sciences; Laiyun Qing, University of Chinese Academy of Sciences; Jun Miao, Chinese Academy of Sciences
P1-33 Stacked Overcomplete Independent Component Analysis for Action Recognition
Zhikang Liu, University of Science and Technology of China; Ye Tian, Stanford University; Zilei Wang, University of Science and Technology of China
P1-34 Searching Action Proposal via Spatial Actionness Estimation and Temporal Path Inference and Tracking
Nannan Li, Peking University ; Dan Xu, University of Trento; Zhenqiang Ying, Peking University; Zhihao Li, Peking University; Ge Li, Peking University
P1-35 Markov Chain Monte Carlo Cascade for Camera Network Calibration based on Unconstrained Pedestrian Tracklets
Louis Lettry, ETHZ; Ralf Dragon, ETHZ; Luc Van Gool, ETHZ
P1-36 Scale-Adaptive Deconvolutional Regression Network for Pedestrian Detection
Yousong Zhu, Chinese Academy of Sciences; Jinqiao Wang, Chinese Academy of Sciences; Chaoyang Zhao, Chinese Academy of Sciences; Haiyun Guo, Chinese Academy of Sciences; Hanqing Lu, Chinese Academy of Sciences
Day 2: Tuesday, November 22

Poster session 2 : 13:30-15:30

No. Computational Photography
P2-01 Layered Scene Reconstruction from Multiple Light Field Camera Views
Ole Johannsen, University of Konstanz; Antonin Sulc, University of Konstanz; Nico Marniok, University of Konstanz; Bastian Goldluecke, University of Konstanz
P2-02 A Dataset and Evaluation Methodology for Depth Estimation on 4D Light Fields
Katrin Honauer, Heidelbeg University; Ole Johannsen, University of Konstanz; Daniel Kondermann, Heidelbeg University; Bastian Goldluecke, University of Konstanz
P2-03 Radial Lens Distortion Correction Using Convolutional Neural Networks Trained with Synthesized Images
Jiangpeng Rong, Peking University; Shiyao Huang, Peking University; Zeyu Shang, Peking University; Xianghua Ying, Peking University
P2-04 Ultrasound Speckle Reduction via L0 Minimization
Lei Zhu, The Chinese University of Hong Kong; Weiming Wang, Shenzhen Institute of Advanced Integration Technology; Xiaomeng Li, The Chinese University of Hong Kong; Qiong Wang, Shenzhen Institute of Advanced Integration Technology, ; Jing Qin, The Hong Kong Polytechnic University; Kin-Hong Wong, The Chinese University of Hong Kong; Pheng-Ann Heng, The Chinese University of Hong Kong
P2-05 A Variational Model for Intrinsic Light Field Decomposition
Anna Alperovich, University of Konstanz; Bastian Goldluecke, University of Konstanz
P2-06 Dense Depth-map Estimation and Geometry Inference from Light Fields via Global Optimization
Lipeng Si, Northwestern Polytechnical University; Qing Wang, Northwestern Polytechnical University
P2-07 Direct and Global Component Separation from a Single Image using Basis Representation
Art Subpa-asa, Tokyo Institute of Technology; Ying Fu, University of Tokyo; Yinqiang Zheng, National Institute of Informatics; Amano Toshiyuki, Wakayama University; Imari Sato, National Institute of Informatics
P2-08 Ultra-Shallow DoF Imaging using Faced Paraboloidal Mirrors
Ryoichiro Nishi,Nara Institute of Science and Technology; Takahito Aoto, Nara Institute of Science and Technology; Norihiko Kawai, Nara Institute of Science and Technology; Tomokazu Sato, Nara Institute of Science and Technology; Yasuhiro Mukaigawa, Nara Institute of Science and Technology; Naokazu Yokoya, Nara Institute of Science and Technology
P2-09 ConvNet-based Depth Estimation, Reflection Separation and Deblurring of Plenoptic Images
Paramanand Chandramouli, University of Bern; Mehdi Noroozi, University of Bern; Paolo Favaro, University of Bern
P2-10 Learning a Mixture of Deep Networks for Single Image Super-Resolution
Ding Liu, University of Illinois at Urbana-Champain; Zhaowen Wang, Adobe Research; Nasser Nasrabadi, West Virginia University; Thomas Huang, University of Illinois at Urbana-Champain
P2-11 A Fast Blind Spatially-varying Motion Deblurring Algorithm with Camera Poses Estimation
Yuquan Xu, Toyota Technological Institute; Seiichi Mita, Toyota Technological Institute; Silong Peng, Chinese Academy of Sciences
P2-12 Removing Shadows from Images of Documents
Steve Bako, UC Santa Barbara; Soheil Darabi, Adobe; Jue Wang, Adobe; Eli Shechtman, Adobe; Kalyan Sunkavalli, Adobe; Pradeep Sen, UC Santa Barbara
P2-13 Video Enhancement via Super-resolution using Deep Quality Transfer Network
Pai-Heng Hsiao, Umbo CV; Ping-Lin Chang, Umbo CV
No. Face and Gestures
P2-14 Age Estimation Based on A Single Network with Soft Softmax of Aging Modeling
Zichang Tan,Chinese Academy of Sciences; Shuai Zhou, Macau University of Science and Technology; Jun Wan, Chinese Academy of Sciences; Zhen Lei, Chinese Academy of Sciences; Stan Li, Chinese Academy of Sciences
P2-15 Illumination-Recovered Pose Normalization for Unconstrained Face Recognition
Zhongjun Wu, Beijing University of Posts and Telecommunications; Weihong Deng, Beijing University of Posts and Telecommunications
P2-16 Local Fractional Order Derivative Vector Quantization Pattern for Face Recognition
Jing Li, Huazhong University of Science and Technology; Nong Sang, Huazhong University of Science and Technology; Changxin Gao, Huazhong University of Science and Technology
P2-17 Learning Facial Point Response for Alignment by Purely Convolutional Network
Zhenqi Xu, Beijing University of Posts and Telecommunications; Weihong Deng, Beijing University of Posts and Telecommunications
P2-18 Random Forest with Suppressed Leaves for Hough Voting
Hui Liang, Nanyang Technological Univ; Junhui Hou , Nanyang Technological University; Junsong Yuan, Nanyang Technological University; Daniel Thalmann, Nanyang Technological University
P2-19 Sign-Correlation Partition based on Global Supervised Descent Method for Face Alignment
Yongqiang Zhang, Harbin Institute of Technology; Shuang Liu, Bournemouth University; Xiaosong Yang, Bournemouth University; Daming Shi, Middlesex University; Jianjun Zhang, Bournemouth University
P2-20 Deep Video Code for Efficient Face Video Retrieval
Shishi Qiao, Chinese Academy of Sciences; Ruiping Wang, Institute of Computing Technology, Chinese Academy of Sciences; Shiguang Shan, Chinese Academy of Sciences; Xilin Chen, Chinese Academy of Sciences
P2-21 From Face Images and Attributes to Attributes
Robert Torfason, ETH Zurich; Eirikur Agustsson, ETH Zurich; Rasmus Rothe, ETH Zurich; Radu Timofte, ETH Zurich
P2-22 Learning with Ambiguous Label Distribution for Apparent Age Estimation
Ke Chen, Tampere University of Technology; Joni-Kristian Kamarainen, Tampere University of Technology
P2-23 Prototype Discriminative Learning for Face Image Set Classification
Wen Wang, Chinese Academy of Sciences; Ruiping Wang,Chinese Academy of Sciences; Shiguang Shan, Chinese Academy of Sciences; Xilin Chen, Chinese Academy of Sciences
P2-24 Collaborative Learning Network for Face Attribute Prediction
Shiyao Wang, Tsinghua University; Zhidong Deng, Tsinghua University; Zhenyang Wang, Tsinghua University
P2-25 Facial Expression-Aware Face Frontalization
Yiming Wang, University of Portsmouth; Hui Yu, University of Portsmouth; Junyu Dong, Ocean University of China; Brett Stevens, University of Portsmouth;Honghai Liu, University of Portsmouth
P2-26 Eigen-Aging Reference Coding for Cross-Age Face Verification and Retrieval
Kaihua Tang, Waseda University; Shanghai Jiao Tong University; Sei-ichiro Kamata, Waseda University; Xiaonan Hou, Shanghai Jiao Tong University; Shouhong Ding, Shanghai Jiao Tong University; Lizhuang Ma, Shanghai Jiao Tong University
P2-27 Consistent Sparse Representation for video-based face recognition
Xiuping Liu, Dalian University of Technology; Aihong Shen, Dalian University of Technology; Jie Zhang, Liaoning Normal University; Junjie Cao, Dalian University of Technology; Yanfang Zhou, Dalian University of Technology
P2-28 Unconstrained Gaze Estimation Using Random Forest Regression Voting
Amine Kacete, Institute of Research and Technology B-com; Renaud Séguier, Institute of Research and Technology B-com; Michel Collobert, Institute of Research and Technology B-com; Jérôme Royan, Institute of Research and Technology B-com
P2-29 A Novel Time Series Kernel for Sequences Generated by LTI Systems
Liliana Lo Presti, University of Palermo; Marco La Cascia, University of Palermo
P2-30 Hand Pose Regression via a Classification-guided Approach
Hongwei Yang, USTC; Juyong Zhang, USTC
P2-31 Who’s that Actor? Automatic Labelling of Actors in TV series starting from IMDB Images
Rahaf Aljundi, KU Leuven; Punarjay Chakravarty, KU Leuven; Tinne Tuytelaars, KU Leuven
No. Image Alignment
P2-32 Adaptive Direct RGB-D Registration and Mapping for Large Motions
Renato Martins, Inria/Mines Paristech; Eduardo Fernandez-Moral, Inria; Patrick Rives, INRIA
P2-33 Deep Discrete Flow
Fatma Guney, MPI for Intelligent Systems; Andreas Geiger, MPI for Intelligent Systems and ETH Zurich
P2-34 Dense Motion Estimation for Smoke
Da Chen, University of Bath; Wenbin Li, University College London; Peter Hall, University of Bath
P2-35 Data Association based Multi-Target Tracking Using a Joint Formulation
Jun Xiang, Huazhong University of Science; Jian Hou, University for Nationalities;Chang Gao, Huazhong University of Science;Nong Sang, Huazhong University of Science
P2-36 Combining Texture and Shape Cues for Object Recognition With Minimal Supervision
Xingchao Peng, Boston University; Kate Saenko, Boston University
P2-37 Video Temporal Alignment for Object Viewpoint
Anestis Papazoglou, University of Edinburgh; Luca Del Pero, University of Edinburgh; Vittorio Ferrari, University of Edinburgh
Day 3: Wednesday, November 23

Poster session 3 : 13:30-15:30

No. 3D Computer Vision
P3-01 Recovering Pose and 3D Deformable Shape from Multi-Instance Image Ensembles
Antonio Agudo, Institut de Robòtica i Informàtica Industrial; Francesc Moreno-Noguer, Institut de Robòtica i Informàtica Industrial
P3-02 Robust Multi-Model Fitting using Density and Preference Analysis
Lokender Tiwari, IIIT-Delhi; Saket Anand, IIIT-Delhi; Sushil Mittal, Scibler Corporation
P3-03 Photometric Bundle Adjustment for Vision-Based SLAM
Hatem Alismail, Carnegie Mellon University; Brett Browning, Carnegie Mellon University; Simon Lucey, Carnegie Mellon University
P3-04 Can Computer Vision Techniques be Applied to Automated Forensic Examinations? A Study on Sex Identication from Human Skulls Using Head CT Scans
Olasimbo Arigbabu, University of Nottingham Malaysia Campus; Iman Liao, University of Nottingham Malaysia Campus; Nurliza Abdullah, Hospital Kuala Lumpur ; Mohamad Helmee Mohamad Noor, Hospital Kuala Lumpur.
P3-05 Deep Depth Super-Resolution: Learning Depth Super-Resolution using Deep Convolutional Neural Network
Xibin Song, Shandong University; Yuchao Dai, The Australian National University; Xueying Qin, Shandong University
P3-06 3D Watertight Mesh Generation with Uncertainties from Ubiquitous Data
Laurent Caraffa, IGN; Mathieu Bredif, IGN; Bruno Vallet, IGN
P3-07 Color Correction for Image-Based Modeling in the Large
Tianwei Shen, HKUST; Jinglu Wang, HKUST; Tian Fang, HKUST; Siyu Zhu, HKUST; Long Quan, HKUST
P3-08 Bringing 3D Models Together: Mining Video Liaisons in Crowdsourced Reconstructions
Ke Wang, UNC Chapel Hill; Enrique Dunn, Stevens Institute of Technology; Mikel Rodriguez, Mitre Corp., USA; Jan-Michael Frahm, UNC Chapel Hill
P3-09 Planar Markerless Augmented Reality using Online Orientation Estimation
Tatsuya Kobayashi, KDDI R&D Laboratories Inc.; Haruhisa Kato, KDDI R&D Laboratories Inc.; Masaru Sugano, KDDI R&D Laboratories Inc.
P3-10 Simultaneous Independent Image Display Technique on Multiple 3D Objects
Hiroshi Kawasaki, Kagoshima University; Marco Visentini-Scarzanella, Kagoshima University; Takuto Hirukawa, ; Ryo Furukawa, Hiroshima City University; Shinsaku Hiura, Hiroshima City University
P3-11 ZigzagNet: Efficient Deep Learning for Real Object Recognition Based on 3D Models
Yida Wang, Beijing University of Posts and Telecommunications; Can Cui, Beijing Jiaotong University; Xiuzhuang Zhou, Capital Normal University; Weihong Deng, Beijing University of Posts and Telecommunications
P3-12 Precise Measurement of Cargo Boxes for Gantry Robot Palletization in Large Scale Workspaces using Low-Cost RGB-D Sensors
Yaadhav Raaj, TUM CREATE; Suraj Nair, TUM CREATE; Alois Knoll, TUM CREATE
P3-13 Visual Place Recognition using Landmark Distribution Descriptors
Pilailuck Panphattarasap, University of Bristol; Andrew Calway, University of Bristol
P3-14 Real Time Direct Visual Odometry for Flexible Multi-Camera Rigs
Benjamin Resch, Tübingen University; Jian Wei, Tübingen University; Hendrik P.A. Lensch, Tübingen University
P3-15 Analysis and Practical Minimization of Registration Error in a Spherical Fish Tank Virtual Reality System
Qian Zhou, University of British Columbia; Gregor Miller, University of British Columbia; Kai Wu, University of British Columbia; Ian Stavness, University of Saskatchewan; Sidney Fels, University of British Columbia
P3-16 Enhancing Direct Camera Tracking with Dense Feature Descriptors
Hatem Alismail, Carnegie Mellon University; Brett Browning, Carnegie Mellon University; Simon Lucey, Carnegie Mellon University
No. Image Attributes, Language, and Recognition
P3-17 Learning to Describe E-Commerce Images from Noisy Online Data
Takuya Yashima, Tohoku University; Naoaki Okazaki, Tohoku University; Kentaro Inui, Tohoku University; Kota Yamaguchi, Tohoku University; Takayuki Okatani, Tohoku University
P3-18 phi-LSTM: A Phrase-based Hierarchical LSTM Model for Image Captioning
Ying Hua Tan, University Malaya; Chee Seng Chan, University of Malaya
P3-19 Deep Relative Attributes
Yaser Souri, Sobhe; Erfan Noury, Sharif University of Technology; Ehsan Adeli, University of North Carolina at Chapel Hill
P3-20 Fast Fashion Guided Clothing Image Retrieval: Delving Deeper into What Feature Makes Fashion
Yuhang He, Sun Yat-sen University; Long Chen, Sun Yat-sen University
P3-21 Using Gaussian Processes to Improve Zero-Shot Learning with Relative Attributes
Yeshi Dolma, IIT Kanpur; Vinay Namboodiri, IIT Kanpur
P3-22 MARVEL: A Large-Scale Image Dataset for Maritime Vessels
Erhan Gundogdu, Aselsan Research Center; Berkan Solmaz, Aselsan Research Center; Veysel Yucesoy, Aselsan Research Center; Aykut Koc, Aselsan Research Center
P3-23 `Part’ly First Among Equals: Semantic Part-Based Benchmarking for State-of-the-Art Object Recognition Systems
Ravi Kiran Sarvadevabhatla, Indian Institute of Science; Shanthakumar Venkatraman, IIT Hyderabad; Venkatesh Babu R, Indian Institute of Science
P3-24 End-to-End Training of Object Class Detectors for Mean Average Precision
Paul Henderson, University of Edinburgh; Vittorio Ferrari, University of Edinburgh
P3-25 R-CNN for Small Object Detection
Chenyi Chen, Princeton University; Ming-Yu Liu, Mitsubishi Electric Research Labs (MERL); Oncel Tuzel, Mitsubishi Electric Research Labs (MERL); Jianxiong Xiao, Princeton University
P3-26 Image Set Classification via Template Triplets and Context-Aware Similarity Embedding
Feng-Ju Chang, Univeristy of Southern California; Ram Nevatia, Univeristy of Southern California
P3-27 Object-Centric Representation Learning from Unlabeled Videos
Ruohan Gao, University of Texas at Austin; Dinesh Jayaraman, University of Texas at Austin; Kristen Grauman, University of Texas at Austin
P3-28 Visual Concept Recognition and Localization via Iterative Introspection
Amir Rosenfeld, Weizmann Institute of Science; Shimon Ullman, Weizmann Institute of Science
P3-29 Aggregating Local Context for Accurate Scene Text Detection
Dafang He, Penn State University; Xiao Yang, Penn State University; Wenyi Huang, Penn State University; Zihan Zhou, Penn State University; Dan Kifer, Penn State University; C. Lee Giles, Penn State University
P3-30 Bilinear Discriminant Analysis Hashing: A Supervised Hashing Approach for High-Dimensional Data
Yanzhen Liu, Beihang University; Xiao Bai, Beihang University; Cheng Yan, Beihang University; Jun Zhou, Griffith University
P3-31 Signature of Geometric Centroids for 3D Local Shape Description and Partial Shape Matching
Keke Tang, University of Science and Technology of China; Peng Song, University of Science and Technology of China; Xiaoping Chen, University of Science and Technology of China
No. Video Understanding
P3-32 Unsupervised Crowd Counting
Nada Elassal, York University; James Elder, York University
P3-33 Long-Term Activity Forecasting Using First-Person Vision
Syed Zahir Bokhari, Carnegie Mellon University; Kris Kitani, Carnegie Mellon University
P3-34 Video Summarization using Deep Semantic Features
Mayu Otani, Nara Inst of Sci. and Tech.; Yuta Nakashima, Nara Institute of Science and Technology; Esa Rahtu, University of Oulu; Janne Heikkilä, University of Oulu; Naokazu Yokoya, Nara Institute of Science and Technology
P3-35 Towards Segmenting Consumer Stereo Videos: Benchmark, Baselines and Ensembles
Wei-Chen Chiu, Max Planck Institute for Informatics; Fabio Galasso, OSRAM Corporate Technology; Mario Fritz, Max Planck Institute for Informatics
P3-36 No-Reference Video Shakiness Quality Assessment
Zhaoxiong Cui, Peking University; Tingting Jiang, Peking University
P3-37 Learning to Extract Motion from Videos in Convolutional Neural Networks
Damien Teney, University of Adelaide; Martial Hebert, Carnegie Mellon University