MM 2012 Proceedings

Kiyoharu Aizawa, Noboru Babaguchi, John R. Smith (Eds.), Proceedings of the 2012 ACM Multimedia Conference, MM '12, October 29�November 2, 2012, Nara, Japan. ACM 2012, ISBN 978-1-4503-1589-5.

Table of Contents

Message from the General Chairs
Kiyoharu Aizawa (The University of Tokyo)
Noboru Babaguchi (Osaka University)
John R. Smith (IBM T.J. Watson Research Center)

Message from the Technical Program Chairs
Shin'ichi Satoh (National Institute of Informatics)
Thomas Plagemann (University of Oslo)
Xian-Sheng Hua (Microsoft)
Rong Yan (Facebook)

Message from the ACM SIGMM Chair
Klara Nahrstedt (University of Ilinois at Urbana-Champaign)

MM 2012 Conference Organization

MM 2012 Technical Program Committee

MM 2012 Technical Demo Program Committee

MM 2012 Area Chairs

MM 2012 Additional Reviewers

MM 2012 Sponsor & Supporters

Poster Session 1
Session Chair: Tat-Seng Chua (National Univ. of Singapore)

Video Saliency Detection in the Compressed Domain (Page 697)
Yuming Fang (Nanyang Technological University)
Weisi Lin (Nanyang Technological University)
Zhenzhong Chen (Nanyang Technological University)
Chia-Ming Tsai (National Chung Cheng University)
Chia-Wen Lin (National Tsing Hua University)

A Robust and Efficient Shot Boundary Detection Approach Based on Fisher Criterion (Page 701)
Chi Zhang (Chinese Academy of Sciences)
Weiqiang Wang (Chinese Academy of Sciences)

A Genetic Algorithm for Audio Retargeting (Page 705)
Stephan Wenger (Technische Universit�t Braunschweig)
Marcus Magnor (Technische Universit�t Braunschweig)

Seam Carving with Forward Gradient Difference Maps (Page 709)
Hyeonwoo Noh (POSTECH)
Bohyung Han (POSTECH)

Surveillance Video Coding via Low-Rank and Sparse Decomposition (Page 713)
Chongyu Chen (Xidian University)
Jianfei Cai (Nanyang Technological University)
Weisi Lin (Nanyang Technological University)
Guangming Shi (Xidian University)

Enhanced Extraction of Moving Objects in Variable Bit-Rate Video Streams (Page 717)
Jui-Yu Yen (National Taipei University of Technology)
Bo-Hao Chen (National Taipei University of Technology)
Shih-Chia Huang (National Taipei University of Technology)

Context-Aware Affective Images Classification Based on Bilayer Sparse Representation (Page 721)
Bing Li (Chinese Academy of Sciences)
Weihua Xiong (Chinese Academy of Sciences)
Weiming Hu (Chinese Academy of Sciences)
Xinmiao Ding (Shandong Institute of Business and Technology)

Gabor-Based Gradient Orientation Pyramid for Kinship Verification Under Uncontrolled Environments (Page 725)
Xiuzhuang Zhou (Capital Normal University)
Jiwen Lu (Advanced Digital Sciences Center)
Junlin Hu (Nanyang Technological University)
Yuanyuan Shang (Capital Normal University)

Robust Stroke-Based Video Animation via Layered Motion and Correspondence (Page 729)
Tao Lin (Sun Yat-Sen University)
Liang Lin (Sun Yat-Sen University & Lotus Hill Research Institute)
Qing Wang (Sun Yat-Sen University)

Texture Optimization for Seamless View Synthesis through Energy Minimization (Page 733)
Wenxiu Sun (The Hong Kong University of Science and Technology)
Oscar C. Au (The Hong Kong University of Science and Technology)
Lingfeng Xu (The Hong Kong University of Science and Technology)
Yujun Li (The Hong Kong University of Science and Technology)
Wei Hu (The Hong Kong University of Science and Technology)
Zhiding Yu (The Hong Kong University of Science and Technology)

Semi-Supervised Multi-Instance Multi-Label Learning for Video Annotation Task (Page 737)
Xin-Shun Xu (Shandong University & Nanjing University)
Yuan Jiang (Nanjing University)
Xiangyang Xue (Fudan University)
Zhi-Hua Zhou (Nanjing University)

Geo-Location Inference on News Articles via Multimodal pLSA (Page 741)
Youjie Zhou (University of North Carolina, Charlotte)
Jiebo Luo (University of Rochester)

A Method for Detecting Salient Regions Using Integrated Features (Page 745)
Zhendong Mao (Chinese Academy of Sciences & Nanjing University of Posts and Telecommunications)
Yongdong Zhang (Chinese Academy of Sciences)
Ke Gao (Chinese Academy of Sciences)
Dongming Zhang (Chinese Academy of Sciences)

Deep Nonlinear Metric Learning with Independent Subspace Analysis for Face Verification (Page 749)
Xinyuan Cai (Chinese Academy of Sciences)
Chunheng Wang (Chinese Academy of Sciences)
Baihua Xiao (Chinese Academy of Sciences)
Xue Chen (Chinese Academy of Sciences)
Ji Zhou (Chinese Academy of Sciences)

Color Transfer Based on Multiscale Gradient-aware Decomposition and Color Distribution Mapping (Page 753)
Zhuo Su (Sun Yat-sen University)
Daiguo Deng (Sun Yat-sen University)
Xue Yang (Sun Yat-sen University)
Xiaonan Luo (Sun Yat-sen University)

On Sparse and Low-Rank Matrix Decomposition for Singing Voice Separation (Page 757)
Yi-Hsuan Yang (Academia Sinica)

Memorable Basis: Towards Human-Centralized Sparse Representation (Page 761)
Xiaoshuai Sun (Harbin Institute of Technology)
Hongxun Yao (Harbin Institute of Technology)

Detecting Text in the Real World (Page 765)
Trung Quy Phan (National University of Singapore)
Palaiahnakote Shivakumara (National University of Singapore)
Chew Lim Tan (National University of Singapore)

Face Image Super-Resolution via Nearest Feature Line (Page 769)
Zhen Han (Wuhan University)
Junjun Jiang (Wuhan University)
Ruimin Hu (Wuhan University)
Tao Lu (Wuhan University)
Kebin Huang (Wuhan University)

Modalities Consensus for Multi-Modal Constraint Propagation (Page 773)
Zhenyong Fu (Shanghai Jiao Tong University)
Hongtao Lu (Shanghai Jiao Tong University)
Horace H.S. Ip (City University of Hong Kong)
Zhiwu Lu (Peking University)

Joint Semantic Segmentation by Searching for Compatible-Competitive References (Page 777)
Ping Luo (The Chinese University of Hong Kong & Chinese Academy of Sciences)
Xiaogang Wang (The Chinese University of Hong Kong & Chinese Academy of Sciences)
Liang Lin (Sun Yat-sen University)
Xiaoou Tang (The Chinese University of Hong Kong & Chinese Academy of Sciences)

An Effective Multi-Clue Fusion Approach for Web Video Topic Detection (Page 781)
Tianlong Chen (Chinese Academy of Sciences)
Chunxi Liu (Graduate University of Chinese Academy of Sciences)
Qingming Huang (Chinese Academy of Sciences)

3D Fingertip and Palm Tracking in Depth Image Sequences (Page 785)
Hui Liang (Nanyang Technological University & Graduate University of Chinese Academy of Sciences)
Junsong Yuan (Nanyang Technological University)
Daniel Thalmann (Nanyang Technological University)

From Speech to Personality: Mapping Voice Quality and Intonation into Personality Differences (Page 789)
Gelareh Mohammadi (Idiap Research Institute)
Antonio Origlia (University of Naples)
Maurizio Filippone (University of Glasgow)
Alessandro Vinciarelli (University of Glasgow and Idiap Research Institute)

Predicting the Conflict Level in Television Political Debates: An Approach Based on Crowdsourcing, Nonverbal Communication and Gaussian Processes (Page 793)
Samuel Kim (Idiap Research Institute)
Maurizio Filippone (University of Glasgow)
Fabio Valente (�cole Polytechnique F�d�rale de Lausanne & University of Glasgow)
Alessandro Vinciarelli (Idiap Research Institute & University of Glasgow)

Using Structural Patches Tiling to Guide Human Head-Shoulder Segmentation (Page 797)
Pengyang Bu (Tsinghua University)
Nan Wang (Tsinghua University)
Haizhou Ai (Tsinghua University)

Video Object Segmentation with Shortest Path (Page 801)
Bao Zhang (Tianjin University)
Handong Zhao (Tianjin University)
Xiaochun Cao (Tianjin University)

Video Object Cosegmentation (Page 805)
Ding-Jie Chen (National Tsing Hua University)
Hwann-Tzong Chen (National Tsing Hua University)
Long-Wen Chang (National Tsing Hua University)

Community as a Connector: Associating Faces with Celebrity Names in Web Videos (Page 809)
Zhineng Chen (City University of Hong Kong)
Chong-Wah Ngo (City University of Hong Kong)
Juan Cao (Chinese Academy of Sciences)
Wei Zhang (City University of Hong Kong)

Comparison of Prediction-based Fusion and Feature-Level Fusion across Different Learning Models (Page 813)
Stavros Petridis (Imperial College London)
Sanjay Bilakhia (Imperial College London)
Maja Pantic (Imperial College London & University Twente)

Depth Estimation for Semi-Automatic 2D to 3D Conversion (Page 817)
Richard Rzeszutek (Ryerson University)
Raymond Phan (Ryerson University)
Dimitrios Androutsos (Ryerson University)

Predicting Domain Adaptivity: Redo or Recycle? (Page 821)
Ting Yao (City University of Hong Kong)
Chong-Wah Ngo (City University of Hong Kong)
Shiai Zhu (City University of Hong Kong)

Music/Speech Classification Using High-Level Features Derived from FMRI Brain Imaging (Page 825)
Xi Jiang (The University of Georgia)
Tuo Zhang (Northwestern Polytechnical University & The University of Georgia)
Xintao Hu (Northwestern Polytechnical University)
Lie Lu (Dolby Laboratories)
Junwei Han (Northwestern Polytechnical University)
Lei Guo (Northwestern Polytechnical University)
Tianming Liu (The University of Georgia)

Bilingual Analysis of Song Lyrics and Audio Words (Page 829)
Jen-Yu Liu (Academia Sinica)
Chin-Chia Yeh (Academia Sinica)
Yi-Hsuan Yang (Academia Sinica)
Yuan-Ching Teng (Academia Sinica)

Self-Paced Dictionary Learning for Image Classification (Page 833)
Ye Tang (Nanjing University)
Yu-Bin Yang (Nanjing University)
Yang Gao (Nanjing University)

Cross Matching of Music and Image (Page 837)
Xixuan Wu (Chinese Academy of Sciences & The Chinese University of Hong Kong)
Yu Qiao (Chinese Academy of Sciences)
Xiaogang Wang (The Chinese University of Hong Kong)
Xiaoou Tang (Chinese Academy of Sciences & The Chinese University of Hong Kong)

Name that Room: Room Identification Using Acoustic Features in a Recording (Page 841)
Nils Peters (International Computer Science Institute)
Howard Lei (International Computer Science Institute)
Gerald Friedland (International Computer Science Institute)

Enhancing Visual Dominance by Semantics-Preserving Image Recomposition (Page 845)
Lai-Kuan Wong (National University of Singapore)
Kok-Lim Wong (National University of Singapore)

Image Tag Re-Ranking by Coupled Probability Transition (Page 849)
Jie Xiao (University of Texas at San Antonio)
Wengang Zhou (University of Texas at San Antonio)
Xia Li (University of Texas at San Antonio)
Meng Wang (Hefei University of Technology)
Qi Tian (University of Texas at San Antonio)

Low Rank Metric Learning for Social Image Retrieval (Page 853)
Zechao Li (Chinese Academy of Sciences)
Jing Liu (Chinese Academy of Sciences)
Yu Jiang (Chinese Academy of Sciences)
Jinhui Tang (Nanjing University of Science and Technology)
Hanqing Lu (Chinese Academy of Sciences)

Can We Understand van Gogh's Mood? Learning to Infer Affects from Images in Social Networks (Page 857)
Jia Jia (Ministry of Education, Tsinghua National Laboratory for Information and Technology & Tsinghua University)
Sen Wu (Tsinghua University)
Xiaohui Wang (Tsinghua University)
Peiyun Hu (Tsinghua University)
Lianhong Cai (Tsinghua University)
Jie Tang (Tsinghua University)

Social Tag Alignment with Image Regions by Sparse Reconstructions (Page 861)
Yang Liu (Chinese Academy of Sciences)
Jing Liu (Chinese Academy of Sciences)
Zechao Li (Chinese Academy of Sciences)
Biao Niu (Chinese Academy of Sciences)
Hanqing Lu (Chinese Academy of Sciences)

Social Event Detection with Interaction Graph Modeling (Page 865)
Yanxiang Wang (Australian National University)
Hari Sundaram (Arizona State University)
Lexing Xie (Australian National University, NICTA)

Poster Session 2
Session Chair: Liangliang Cao (IBM T. J. Watson Research Center)

Visual Query Attributes Suggestion (Page 869)
Jingwen Bian (National University of Singapore)
Zheng-Jun Zha (National University of Singapore)
Hanwang Zhang (National University of Singapore)
Qi Tian (University of Texas at San Antonio)
Tat-Seng Chua (National University of Singapore)

Attribute-Assisted Reranking for Web Image Retrieval (Page 873)
Junjie Cai (University of Texas at San Antonio)
Zheng-Jun Zha (National University of Singapore)
Wengang Zhou (University of Texas at San Antonio)
Qi Tian (University of Texas at San Antonio)

Query Expansion Enhancement by Fast Binary Matching (Page 877)
Xia Li (The University of Texas at San Antonio)
Wengang Zhou (The University of Texas at San Antonio)
Jinhui Tang (Nanjing University of Science and Technology)
Qi Tian (The University of Texas at San Antonio)

Compact Kernel Hashing with Multiple Features (Page 881)
Xianglong Liu (Beihang University)
Junfeng He (Columbia University)
Di Liu (China Academy of Telecommunication Research of MIIT)
Bo Lang (Beihang University)

Similar Image Search with a Tiny Bag-of-Delegates Representation (Page 885)
Weiwen Tu (Sun Yat-sen University)
Rong Pan (Sun Yat-sen University)
Jingdong Wang (Microsoft Research Asia)

Online Non-Feedback Image Re-Ranking via Dominant Data Selection (Page 889)
Chen Cao (Chinese Academy of Sciences)
Shifeng Chen (Chinese Academy of Sciences)
Yuhong Li (Chinese Academy of Sciences)
Jianzhuang Liu (Chinese Academy of Sciences, Chinese University of Hong Kong & Huawei Technologies Co. Ltd.)

Optimal Semi-Supervised Metric Learning for Image Retrieval (Page 893)
Kun Zhao (Chinese Academy of Sciences)
Wei Liu (Columbia University)
Jianzhuang Liu (Chinese Academy of Sciences, CUHK & Huawei Technologies Co. Ltd.)

View-Based 3D Object Retrieval by Bipartite Graph Matching (Page 897)
Yue Wen (Tsinghua University)
Yue Gao (Tsinghua University & National University of Singapore)
Richang Hong (Hefei University of Technology)
Huanbo Luan (Tsinghua University & National University of Singapore)
Qiong Liu (Huazhong University of Science and Technology)
Jialie Shen (Singapore Management University)
Rongrong Ji (Columbia University)

Local Geometry Adaptive Manifold Re-Ranking for Shape-Based 3D Object Retrieval (Page 901)
Ryutarou Ohbuchi (University of Yamanashi)
Yukinori Kurita (University of Yamanashi)

DLMSearch: Diversified Landmark Search by Photo (Page 905)
Junfeng Ye (Shanghai Jiao Tong University)
Jia Chen (Shanghai Jiao Tong University)
Zejia Chen (Shanghai Jiao Tong University)
Yihe Zhu (Shanghai Jiao Tong University)
Shenghua Bao (IBM China Research Laboratory)
Zhong Su (IBM China Research Laboratory)
Yong Yu (Shanghai Jiao Tong University)

Fast Semantic Image Retrieval Based on Random Forest (Page 909)
Hao Fu (University of Nottingham)
Guoping Qiu (University of Nottingham)

Sketch-Based Image Retrieval on Mobile Devices Using Compact Hash Bits (Page 913)
Kai-Yu Tseng (National Taiwan University)
Yen-Liang Lin (National Taiwan University)
Yu-Hsiu Chen (National Taiwan University)
Winston H. Hsu (National Taiwan University)

Towards Relevance and Saliency Ranking of Image Tags (Page 917)
Songhe Feng (Beijing Jiaotong University)
Congyan Lang (Beijing Jiaotong University)
Bing Li (NLPR, Institute of Automation & Chinese Academy of Sciences)

Mobile-Based Advertisement Information Retrieval from Images and Websites (Page 921)
Yi-Feng Pan (Fujitsu R&D Center Co., Ltd.)
Jian Sun (Fujitsu R&D Center Co., Ltd.)
Siyuan Chen (Fujitsu R&D Center Co., Ltd.)
Yuan He (Fujitsu R&D Center Co., Ltd.)
Yingju Xia (Fujitsu R&D Center Co., Ltd.)
Jun Sun (Fujitsu R&D Center Co., Ltd.)
Satoshi Naoi (Fujitsu R&D Center Co., Ltd.)

A User Study on Image Browsing on Touchscreens (Page 925)
David Ahlstr�m (Alpen-Adria-Universit�t Klagenfurt)
Marco A. Hudelist (Alpen-Adria-Universit�t Klagenfurt)
Klaus Schoeffmann (Alpen-Adria-Universit�t Klagenfurt)
Gerald Schaefer (Loughborough University)

Discriminative ICA Model with Reconstruction Constraint for Image Classification (Page 929)
Yanhui Xiao (Beijing Jiaotong University)
Zhenfeng Zhu (Beijing Jiaotong University)
Shikui Wei (Beijing Jiaotong University)
Yao Zhao (Beijing Jiaotong University)

Search Web Images Using Objects, Backgrounds and Conditions (Page 933)
Jiemi Zhang (Zhejiang University)
Chenxia Wu (Zhejiang University)
Deng Cai (Zhejiang University)

Sparsity Cue in Image Copy Detection (Page 937)
Huan-Cheng Hsu (National Chung Hsing University)
Chun-Rong Huang (National Chung Hsing University)
Chun-Shien Lu (Academia Sinica)

Near-Duplicate Video Retrieval Based on Clustering by Multiple Sequence Alignment (Page 941)
Yandan Wang (Monash University)
Mohammed Belkhatir (University of Lyon)
Bashar Tahayna (Monash University)

Neighborhood Preserving Hashing for Fast Similarity Search (Page 945)
Cong Liu (Huazhong University of Science and Technology)
Hefei Ling (Huazhong University of Science and Technology)
Fuhao Zou (Huazhong University of Science and Technology)
Lingyu Yan (Huazhong University of Science and Technology)

Face Photo Retrieval by Sketch Example (Page 949)
Hamed Kiani Galoogahi (National University of Singapore)
Terence Sim (National University of Singapore)

Geometric Context-Preserving Progressive Transmission in Mobile Visual Search (Page 953)
Junhai Xia (Chinese Academy of Sciences)
Ke Gao (Chinese Academy of Sciences)
Dongming Zhang (Chinese Academy of Sciences)
Zhendong Mao (Chinese Academy of Sciences)

Supervised Cross-Collection Topic Modeling (Page 957)
Haidong Gao (Zhejiang University)
Siliang Tang (Zhejiang University)
Yin Zhang (Zhejiang University)
Dapeng Jiang (Zhejiang University)
Fei Wu (Zhejiang University)
Yueting Zhuang (Zhejiang University)

PDSS: Patch-Descriptor-Similarity Space for Effective Face Verification (Page 961)
Xiaohua Zhai (Peking University)
Yuxin Peng (Peking University)
Jianguo Xiao (Peking University)

Correlation-Based Burstiness for Logo Retrieval (Page 965)
Jerome Revaud (INRIA Grenoble)
Matthijs Douze (INRIA Grenoble)
Cordelia Schmid (INRIA Grenoble)

Large-Scale Simultaneous Multi-Object Recognition and Localization via Bottom Up Search-Based Approach (Page 969)
Chun-Che Wu (National Taiwan University)
Yin-Hsi Kuo (National Taiwan University)
Winston H. Hsu (National Taiwan University)

Sketch-Based Image Retrieval on a Large Scale Database (Page 973)
Rong Zhou (Shanghai Jiao Tong University)
Liuli Chen (Shanghai Jiao Tong University)
Liqing Zhang (Shanghai Jiao Tong University)

Dynamic Vocabularies for Web-based Concept Detection by Trend Discovery (Page 977)
Damian Borth (University of Kaiserslautern)
Adrian Ulges (German Research Center for Artificial Intelligence)
Thomas M. Breuel (University of Kaiserslautern)

Coherent Image Selection Using a Fast Approximation to the Generalized Traveling Salesman Problem (Page 981)
Meng Wang (Boston University)
Prakash Ishwar (Boston University)
Janusz Konrad (Boston University)
Cenk Gazen (Google Inc.)
Rohit Saboo (Google Inc.)

PRiSMA: Searching Images in Parallel (Page 985)
Pancho Tolchinsky (Yahoo! Research)
Luca Chiarandini (Universtitat Pompeu Fabra & Yahoo! Research)
Alejandro Jaimes (Yahoo! Research)

Local Visual Words Coding for Low Bit Rate Mobile Visual Search (Page 989)
Yue Wu (University of Science and Technology of China)
Shiyang Lu (The University of Sydney)
Tao Mei (Microsoft Research Asia)
Jian Zhang (University of Technology)
Shipeng Li (Microsoft Research Asia)

Virtual Reference View Generation for CBIR-based Visual Pose Estimation (Page 993)
Robert Huitl (Technische Universit�t M�nchen)
Georg Schroth (Technische Universit�t M�nchen)
Sebastian Hilsenbeck (Technische Universit�t M�nchen)
Florian Schweiger (Technische Universit�t M�nchen)
Eckehard Steinbach (Technische Universit�t M�nchen)

Detecting the Directions of Viewing Landmarks for Recommendation by Large-Scale User-contributed Photos (Page 997)
Yen-Ta Huang (National Taiwan University)
Kuan-Ting Chen (National Taiwan University)
Liang-Chi Hsieh (National Taiwan University)
Winston H. Hsu (National Taiwan University)
Ya-Fan Su (Chunghwa Telecom Co., Ltd.)

Efficient Mobile Landmark Recognition Based on Saliency-Aware Scalable Vocabulary Tree (Page 1001)
Kim-Hui Yap (Nanyang Technological University)
Zhen Li (Nanyang Technological University)
Da-Jiang Zhang (Nanyang Technological University)
Zhan-Ke Ng (Nanyang Technological University)

Client-Side Backprojection of Presentation Slides into Educational Video (Page 1005)
Yekaterina Kharitonova (University of Arizona)
Qiyam Tung (University of Arizona)
Alexander Danehy (University of Arizona)
Alon Efrat (University of Arizona)
Kobus Barnard (University of Arizona)

A Study on the User Perception to Color Variations (Page 1009)
Marco V. Bernardo (Universidade da Beira Interior)
Ant�nio M. G. Pinheiro (Universidade da Beira Interior)
Manuela Pereira (Universidade da Beira Interior)
Paulo Torr�o Fiadeiro (Universidade da Beira Interior)

Parallel Deblocking Filtering in H.264/AVC Using Multiple CPUs and GPUs (Page 1013)
Bart Pieters (Ghent University)
Charles Hollemeersch (Ghent University)
Jan De Cock (Ghent University)
Wesley De Neve (Ghent University)
Peter Lambert (Ghent University)
Rik Van de Walle (Ghent University)

Energy-Aware Adaptations in Mobile 3D Graphics (Page 1017)
Mohammad Hosseini (Simon Fraser University)
Alexandra Fedorova (Simon Fraser University)
Joseph Peters (Simon Fraser University)
Shervin Shirmohammadi (University of Ottawa)

ITEM: Immersive Telepresence for Entertainment and Meetings with Commodity Setup (Page 1021)
Viet Anh Nguyen (Advanced Digital Sciences Center)
Tien Dung Vu (Advanced Digital Sciences Center)
Hongsheng Yang (Advanced Digital Sciences Center)
Jiangbo Lu (Advanced Digital Sciences Center)
Minh N. Do (University of Illinois at Urbana-Champaign)

Reducing Cross-Group Traffic with a Cooperative Streaming Architecture (Page 1025)
Zhijie Shen (National University of Singapaore)
Roger Zimmermann (National University of Singapaore)

QoE-based Opportunistic Transmission for Video Broadcasting in Heterogeneous Circumstance (Page 1029)
Wen Ji (Chinese Academy of Sciences)
Zhu Li (Futurewei Technology)
Yiqiang Chen (Chinese Academy of Sciences)

ROI-based Protection Scheme for High Definition Interactive Video Applications (Page 1033)
Kiana Calagari (Sharif University of Technology)
Mohammad Reza Pakravan (Sharif University of Technology)
Shervin Shirmohammadi (University of Ottawa)

Advanced Downlink LTE Radio Resource Management for HTTP-Streaming (Page 1037)
Thomas Wirth (Fraunhofer Heinrich Hertz Institute)
Yago S�nchez (Fraunhofer Heinrich Hertz Institute)
Bernd Holfeld (Fraunhofer Heinrich Hertz Institute)
Thomas Schierl (Fraunhofer Heinrich Hertz Institute)

Poster Session 3
Session Chair: Sethuraman Panchanathan (Arizona State University)

Touch Saliency (Page 1041)
Mengdi Xu (National University of Singapore)
Bingbing Ni (Advanced Digital Science Center)
Jian Dong (National University of Singapore)
Zhongyang Huang (Panasonic Singapore Laboratories)
Meng Wang (Hefei University of Technology)
Shuicheng Yan (National University of Singapore)

Robust Cross-Media Transfer for Visual Event Detection (Page 1045)
Yang Yang (The University of Queensland)
Yi Yang (Carnegie Mellon University)
Zi Huang (The University of Queensland)
Jiajun Liu (The University of Queensland)
Zhigang Ma (University of Trento)

Predicting Human Activities Using Spatio-Temporal Structure of Interest Points (Page 1049)
Gang Yu (Nanyang Technological University)
Junsong Yuan (Nanyang Technological University)
Zicheng Liu (Microsoft Research, Redmond)

Human Action Recognition and Retrieval Using Sole Depth Information (Page 1053)
Yan-Ching Lin (Academia Sinica)
Min-Chun Hu (Academia Sinica & National Cheng Kung University)
Wen-Huang Cheng (Academia Sinica)
Yung-Huan Hsieh (Academia Sinica)
Hong-Ming Chen (Academia Sinica)

Recognizing Actions Using Depth Motion Maps-Based Histograms of Oriented Gradients (Page 1057)
Xiaodong Yang (The City College, City University of New York)
Chenyang Zhang (The City College, City University of New York)
YingLi Tian (The City College, City University of New York)

Activity-Based Person Identification Using Sparse Coding and Discriminative Metric Learning (Page 1061)
Jiwen Lu (Advanced Digital Sciences Center)
Junlin Hu (Nanyang Technological University)
Xiuzhuang Zhou (Capital Normal University)
Yuanyuan Shang (Capital Normal University)

Detection Bank: An Object Detection Based Video Representation for Multimedia Event Recognition (Page 1065)
Tim Althoff (University of California, Berkeley)
Hyun Oh Song (University of California, Berkeley)
Trevor Darrell (University of California, Berkeley)

A New Heat-Map-based Algorithm for Human Group Activity Recognition (Page 1069)
Hang Chu (Shanghai Jiao Tong University)
Weiyao Lin (Shanghai Jiao Tong University)
Jianxin Wu (Nanyang Technological University)
Xingtong Zhou (Shanghai Jiao Tong University)
Yuanzhe Chen (Shanghai Jiao Tong University)
Hongxiang Li (University of Louisville)

Multimedia Event Recounting with Concept Based Representation (Page 1073)
Qian Yu (SRI International Sarnoff)
Jingen Liu (SRI International Sarnoff)
Hui Cheng (SRI International Sarnoff)
Ajay Divakaran (SRI International Sarnoff)
Harpreet Sawhney (SRI International Sarnoff)

What Is Happening: Annotating Images with Verbs (Page 1077)
Gang Tian (The University of Sydney)
Genliang Guan (The University of Sydney)
Zhiyong Wang (The University of Sydney)
Dagan Feng (The University of Sydney)

Hybrid Generative-Discriminative Recognition of Human Action in 3D Joint Space (Page 1081)
Zhe Wu (Shanghai Jiao Tong University)
Xiong Li (Shanghai Jiao Tong University)
Xu Zhao (Shanghai Jiao Tong University)
Yuncai Liu (Shanghai Jiao Tong University)

Parsing Collective Behaviors by Hierarchical Model with Varying Structure (Page 1085)
Cong Zhang (Shanghai Jiao Tong University)
Xiaokang Yang (Shanghai Jiao Tong University)
Jun Zhu (Shanghai Jiao Tong University)
Weiyao Lin (Shanghai Jiao Tong University)

Toward Next Generation Coaching Tools for Court Based Racquet Sports (Page 1089)
Damien Connaghan (Dublin City University)
Noel E. O'Connor (Dublin City University)

Predicting Participants in Public Events Using Stock Photos (Page 1093)
Neil O'Hare (Yahoo! Research)
Luca Maria Aiello (Yahoo! Research)
Alejandro Jaimes (Yahoo! Research)

Breaking Row-Column Shuffle Based Image Cipher (Page 1097)
Weihai Li (University of Science and Technology of China)
Yupeng Yan (University of Science and Technology of China)
Nenghai Yu (University of Science and Technology of China)

On the Music Content Authentication (Page 1101)
Wei Li (Fudan University)
Bilei Zhu (Fudan University)
Zhurong Wang (Fudan University)

Secure Cloud-based Medical Data Visualization (Page 1105)
Manoranjan Mohanty (National University of Singapore)
Pradeep Atrey (University of Winnipeg)
Wei Tsang Ooi (National University of Singapore)

State-based Steganography in Low Bit Rate Speech (Page 1109)
Ke Zhou (Huazhong University of Science and Technology)
Jin Liu (Huazhong University of Science and Technology)
Hui Tian (National Huaqiao University)
Chunhua Li (Huazhong University of Science and Technology)

Markov-based Image Forensics for Photographic Copying from Printed Picture (Page 1113)
Jing Yin (Sun Yat-sen University)
Yanmei Fang (Sun Yat-sen University)

Secure Content Sharing for Social Network Using Fingerprinting and Encryption in the TSH Transform Domain (Page 1117)
Conghuan Ye (Huazhong University of Science and Technology & Hubei Engineering University)
Hefei Ling (Huazhong University of Science and Technology)
Fuhao Zou (Huazhong University of Science and Technology)
Cong Liu (Huazhong University of Science and Technology)

Conversationally-Inspired Stylometric Features for Authorship Attribution in Instant Messaging (Page 1121)
Marco Cristani (University of Verona)
Giorgio Roffo (Istituto Italiano di Tecnologia)
Cristina Segalin (Istituto Italiano di Tecnologia)
Loris Bazzani (Istituto Italiano di Tecnologia)
Alessandro Vinciarelli (University of Glasgow)
Vittorio Murino (Istituto Italiano di Tecnologia)

Dynamic Camera Calibration Method for Free-Viewpoint Experience in Sport Videos (Page 1125)
Hiroshi Sankoh (KDDI R&D Laboratories, Inc.)
Masaru Sugano (KDDI R&D Laboratories, Inc.)
Sei Naito (KDDI R&D Laboratories, Inc.)

Improving Dense Image Correspondence Estimation with Interactive User Guidance (Page 1129)
Kai Ruhl (TU Braunschweig)
Benjamin Hell (TU Braunschweig)
Felix Klose (TU Braunschweig)
Christian Lipski (TU Braunschweig)
S�ren Petersen (TU Braunschweig)
Marcus Magnor (TU Braunschweig)

Personalized Video Recommendation through Tripartite Graph Propagation (Page 1133)
Bisheng Chen (South China University of Technology)
Jingdong Wang (Microsoft Research Asia)
Qinghua Huang (South China University of Technology)
Tao Mei (Microsoft Research Asia)

Clothing Genre Classification by Exploiting the Style Elements (Page 1137)
Shintami C. Hidayati (National Taiwan University of Science and Technology)
Wen-Huang Cheng (Academia Sinica)
Kai-Lung Hua (National Taiwan University of Science and Technology)

AttachedShock: Facilitating Moving Targets Acquisition on Augmented Reality Devices Using Goal-Crossing Actions (Page 1141)
Chuang-Wen You (Dartmouth College)
Yung-Huan Hsieh (Academia Sinica)
Wen-Huang Cheng (Academia Sinica)

MixPad: Augmenting Interactive Paper with Mice & Keyboards for Cross-Media and Fine-Grained Interaction with Documents (Page 1145)
Xin Yang (University of California, Santa Barbara)
Chunyuan Liao (FX Palo Alto Laboratory, Inc.)
Qiong Liu (FX Palo Alto Laboratory, Inc.)

Detecting Rule of Simplicity from Photos (Page 1149)
Long Mai (Portland State University)
Hoang Le (Portland State University)
Yuzhen Niu (Portland State University)
Yu-Chi Lai (National Taiwan University of Science and Technology)
Feng Liu (Portland State University)

An Approach to Automatic Creation of Cinemagraphs (Page 1153)
Mei-Chen Yeh (National Taiwan Normal University)
Po-Yi Li (National Taiwan Normal University)

Human-Computer Dance Interaction with Realtime Accelerometer Control (Page 1157)
Takuya Yasunaga (Osaka University)
Atsushi Nakazawa (Osaka University)
Haruo Takemura (Osaka University)

Robust AAM-Based Audio-Visual Speech Recognition Against Face Direction Changes (Page 1161)
Yuto Komai (Kobe University)
Nan Yang (Kobe University)
Tetsuya Takiguchi (Kobe University)
Yasuo Ariki (Kobe University)

A Study on Making Camera Trajectory from Panorama Watching Manipulation (Page 1165)
Daisuke Ochi (Nippon Telegraph and Telephone Corporation)
Hideaki Kimata (Nippon Telegraph and Telephone Corporation)
Hajime Noto (Nippon Telegraph and Telephone Corporation)
Akira Kojima (Nippon Telegraph and Telephone Corporation)

Drive Video Summarization Based on Double Articulation Structure of Driving Behavior (Page 1169)
Kazuhito Takenaka (Denso Corporation)
Takashi Bando (Denso Corporation)
Shogo Nagasaka (Ritsumeikan University)
Tadahiro Taniguchi (Ritsumeikan University)

Interactive Multimodal Social Robot for Improving Quality of Care of Elderly in Australian Nursing Homes (Page 1173)
Rajiv Khosla (La Trobe University)
Mei-Tai Chu (La Trobe University)
Reza Kachouie (La Trobe University)
Keiji Yamada (NEC Corporation)
Fujita Yoshihiro (NEC Corporation)
Tomoharu Yamaguchi (NEC Corporation)

Plug&Touch: A Mobile Interaction Solution for Large Display via Vision-Based Hand Gesture Detection (Page 1177)
Lei Xu (Nokia Research Center)
Yikai Fang (Nokia Research Center)
Kongqiao Wang (Nokia Research Center)
Jiangwei Li (Nokia Research Center)

Ulcer Detection in Wireless Capsule Endoscopy Video (Page 1181)
Yingju Chen (University of Bridgeport)
Jeongkyu Lee (University of Bridgeport)

Critical Gameplay: Designing Games to Critique Convention (Page 1185)
Lindsay D. Grace (Miami University)

Smooth and Efficient Crowd Transformation (Page 1189)
Mingliang Xu (Zhengzhou University)
Yunpeng Wu (Zhengzhou University)
Yangdong Ye (Zhengzhou University)

Augmented Reality Card Game Based on User-Specific Information Control (Page 1193)
Seiko Myojin (Ritsumeikan University)
Arata Sato (Ritsumeikan University)
Nobutaka Shimada (Ritsumeikan University)

Indoor and Outdoor Profiling of Users in Multimedia Installations (Page 1197)
Gianpaolo D'Amico (University of Florence)
Alberto Del Bimbo (University of Florence)
Andrea Ferracani (University of Florence)
Lea Landucci (University of Florence)
Daniele Pezzatini (University of Florence)

Digiti Sonus: An Interactive Fingerprint Sonification (Page 1201)
Yoon Chung Han (University of California, Santa Barbara)
Byeong-jun Han (Korea University)

Extending the Lifelog to Non-Human Subjects: Ambient Storytelling for Human-Object Relationships (Page 1205)
Joshua McVeigh-Schultz (University of Southern California)
Jen Stein (University of Southern California)
Jeff Watson (University of Southern California)
Scott Fisher (University of Southern California)

Brave New Ideas Program
Session Chairs: Alejandro Jaimes (Yahoo! Research) and Tat-seng Chua (National University of Singapore)

Situation Recognition: An Evolving Problem for Heterogeneous Dynamic Big Multimedia Data (Page 1209)
Vivek K. Singh (University of California, Irvine)
Mingyan Gao (University of California, Irvine)
Ramesh Jain (University of California, Irvine)

Distributional Semantics with Eyes: Using Image Analysis to Improve Computational Representations of Word Meaning (Page 1219)
Elia Bruni (University of Trento)
Jasper Uijlings (University of Trento)
Marco Baroni (University of Trento)
Nicu Sebe (University of Trento)

Towards Indexing Representative Images on The Web (Page 1229)
Xin-Jing Wang (Microsoft Research Asia)
Zheng Xu (University of Science and Technology of China)
Lei Zhang (Microsoft Research Asia)
Ce Liu (Micrososft Research New England)
Yong Rui (Microsoft Research Asia)

Intent and Its Discontents: The User at the Wheel of the Online Video Search Engine (Page 1239)
Alan Hanjalic (Delft University of Technology)
Christoph Kofler (Delft University of Technology)
Martha Larson (Delft University of Technology)