Main Conference Technical Program

Session Details

Tuesday, June 30

TueAM1 - Best student paper session - 11:20-12:40

EXPLORING FEATURE SPACE WITH SEMANTIC ATTRIBUTES, JUNJIE CAI (IBM), Richang Hong (Hefei University of Technology), Meng Wang, Qi Tian (University of Texas at San Antonio, USA)

GEOSPATIAL INTERPOLATION ANALYTICS FOR DATA STREAMS IN EVENTSHOP, Mengfan Tang (UC Irvine), Pranav Agrawal (University of California, Irvine), Siripen Pongpaichet (University of California, Irvine), Ramesh Jain

3D EAR IDENTIFICATION USING LC-KSVD AND LOCAL HISTOGRAMS OF SURFACE TYPES, Lida Li (Tongji University), Lin Zhang (Tongji University), Hongyu Li (Tongji University)

CHARACTERISTIC NUMBER REGRESSION FOR FACIAL FEATURE EXTRACTION, Yuntao Li (Dalian University of Technology), Xin Fan (Dalian University of Technolog), Risheng Liu (DUT), Yuyao Feng (Dalian University of Technology), Zhongxuan Luo (Dalian University of Technology), Zezhou Li (Donghua University)

TueAM2 - Multimedia Processing I - 11:20-12:40

ROBUST INTERACTIVE IMAGE SEGMENTATION WITH WEAK SUPERVISION FOR MOBILE TOUCH SCREEN DEVICES, Tinghuai Wang (Nokia Technologies), Huiling Wang (Lappeenranta University of Technology), Lixin Fan (Nokia Technologies)

PIXEL FUSION BASED STEREO IMAGE RETARGETING, Bahetiyaer Bare, Ke Li, Bo Yan (Fudan University), Xiaoyu Qi, Hamid Gharavi

IMAGE INTERPOLATION BASED ON NON-LOCAL GEOMETRIC SIMILARITIES, Shuyuan Zhu (UESTC), Bing Zeng (UESTC), Guanghui Liu (UESTC), Liaoyuan Zeng (UESTC), Lu Fang (USTC), Moncef Gabbouj (TUT)

SINGLE IMAGE SUPER-RESOLUTION VIA 2D SPARSE REPRESENTATION, Na Qi (Bjut), Yunhui Shi (bjut), Xiaoyan Sun (Mircrosoft Research Asia), Wenpeng Ding (Beijing University of Technology), Baocai Yin (bjut)

TueAM3 - Multimedia Search and Retrieval I - 11:20-12:40

SHAPE DESCRIPTION USING PHASE-PRESERVING FOURIER DESCRIPTOR, Emir Sokic (Faculty of Elec. Engineering), Samim Konjicija (Faculty of Electrical Engineering Sarajevo)

WHAT IS THE NEXT STEP OF BINARY FEATURES?, Zhendong Mao (IIE,CAS), Lei Zhang, Bin Wang, Li Guo

IMAGE RETRIEVAL BASED ON COMPRESSED CAMERA SENSOR FINGERPRINTS, Diego Valsesia (Politecnico di Torino - DET), Giulio Coluccia (Politecnico di Torino), Tiziano Bianchi (Politecnico di Torino), Enrico Magli ( Politecnico di Torino)

VECTORS OF LOCALLY AGGREGATED CENTERS FOR COMPACT VIDEO REPRESENTATION, Alhabib Abbas (University College London), Nikos Deligiannis (University College London), Yiannis Andreopoulos (UCL)

TuePM1a - Multimedia Coding & Compression - 14:40-15:40

3D VIDEO CODING USING MOTION INFORMATION AND DEPTH MAP, Fei Cheng (XJTLU/UoL), Jimin Xiao (XJTLU), Tammam Tillo (Xi'an Jiaotong-Liverpool University),

ENERGY AND AREA EFFICIENT HARDWARE IMPLEMENTATION OF 4K MAIN-10 HEVC DECODER IN ULTRA-HD BLU-RAY PLAYER AND TV SYSTEMS, Tsu-Ming Liu (Mediatek Inc.), Yung-Chang Chang, Chih-Ming Wang, Hue-Min Lin, Chia-Yun Cheng, Chun-Chia Chen, Min-Hao Chiu, Sheng-Jen Wang, Ping Chao, Meng-Jye Hu, Fu-Chun Yeh, Shun-hsiang Chuang, Hsiu-Yi Lin, Ming-Long Wu, Che-Hong Chen, Chia-Lin Ho, Chi-Cheng Ju (MediaTek Inc.)

COMPOUND IMAGE COMPRESSION USING LOSSLESS AND LOSSY LZMA IN HEVC, Cuiling Lan (Microsoft Research Asia), Jizheng Xu, Wenjun Zeng (Microsoft Research Asia), Feng Wu (University of Science & Technology of China, China)

TuePM1b - Multimedia Coding & Compression - 17:00-18:00

UNEQUAL ERROR PROTECTION FOR SCALABLE VIDEO STORAGE IN THE CLOUD, Xiaodan Song (Xidian University), Xiulian Peng (Microsoft Research Asia), Jizheng Xu, Guangming Shi (Xidian University, China), Feng Wu (University of Science & Technology of China, China)

INTER-FRAME DEPENDENT RATE-DISTORTION OPTIMIZATION USING LAGRANGIAN MULTIPLIER ADAPTION, Shuai Li, Ce Zhu (University of Electronic Science and Technology of China), Yanbo Gao (University of Electronic Science and Technology of China), Yimin Zhou, Frederic Dufaux (CNRS, France), Ming-Ting Sun (University of Washington)

TOWARDS GPU HEVC INTRA DECODING: SEIZING FINE-GRAIN PARALLELISM, Diego De Souza (INESC-ID / IST, Universidade de Lisboa), Aleksandar Ilic (INESC-ID / IST, Universidade de Lisboa), Nuno Roma (INESC-ID, IST, Universidade de Lisboa), Leonel Sousa (INESC-ID / IST, Universidade de Lisboa)

TuePM2a - Understanding from visual data - 14:40-15:40

TENSOR POOLING FOR ONLINE VISUAL TRACKING, Lianghua Huang (Beijing Institute of Tech.), Bo Ma (Beijing Institute of Technology)

DISCRIMINATIVE MULTI-VIEW FEATURE SELECTION AND FUSION, Yanbin Liu (Tianjin University), Binbing Liao, Yahong Han (Tianjing University)

CHARACTERIZING DYNAMIC TEXTURES WITH SPACE-TIME LACUNARITY ANALYSIS, Yuping Sun (SCUT), Yong Xu (SCUT), Yuhui Quan (SCUT)

Best Paper Candidates Poster Session - 15:40-17:00

ROBUST INTERACTIVE IMAGE SEGMENTATION WITH WEAK SUPERVISION FOR MOBILE TOUCH SCREEN DEVICES, Tinghuai Wang (Nokia Technologies), Huiling Wang (Lappeenranta University of Technology), Lixin Fan (Nokia Technologies)

TENSOR POOLING FOR ONLINE VISUAL TRACKING, Lianghua Huang (Beijing Institute of Tech.), Bo Ma (Beijing Institute of Technology)

ACTIVE CROSSTALK REDUCTION SYSTEM FOR MULTIVIEW AUTOSTEREOSCOPIC DISPLAYS, Philippe Hanhart (EPFL), Carmelo di Nolfo (EPFL), Touradj Ebrahimi

ESTIMATING HEART RATE VIA DEPTH VIDEO MOTION TRACKING, Cheng Yang (University of Strathclyde), Gene Cheung (National Institute of Informatics), Vladimir Stankovic (University of Strathclyde)

EVALUATING MUSIC RECOMMENDATION IN A REAL-WORLD SETTING: ON DATA SPLITTING AND EVALUATION METRICS, Szu-Yu Chou (Academia Sinica), Yi-Hsuan Yang (Academia Sinica), Yu-Ching Lin (kkbox)

EXPLORING FEATURE SPACE WITH SEMANTIC ATTRIBUTES, JUNJIE CAI (IBM), Richang Hong (Hefei University of Technology), Meng Wang, Qi Tian (University of Texas at San Antonio, USA)

GEOSPATIAL INTERPOLATION ANALYTICS FOR DATA STREAMS IN EVENTSHOP, Mengfan Tang (UC Irvine), Pranav Agrawal (University of California, Irvine), Siripen Pongpaichet (University of California, Irvine), Ramesh Jain

3D EAR IDENTIFICATION USING LC-KSVD AND LOCAL HISTOGRAMS OF SURFACE TYPES, Lida Li (Tongji University), Lin Zhang (Tongji University), Hongyu Li (Tongji University)

CHARACTERISTIC NUMBER REGRESSION FOR FACIAL FEATURE EXTRACTION, Yuntao Li (Dalian University of Technology), Xin Fan (Dalian University of Technolog), Risheng Liu (DUT), Yuyao Feng (Dalian University of Technology), Zhongxuan Luo (Dalian University of Technology), Zezhou Li (Donghua University)

TuePM2b - Understanding from visual data - 17:00-18:00

LEARNING DEEP TRAJECTORY DESCRIPTOR FOR ACTION RECOGNITION IN VIDEOS USING DEEP NEURAL NETWORKS, Yemin Shi (Peking university), Wei Zeng, Yaowei Wang, Tiejun Huang

A FRAMEWORK OF EXTRACTING MULTI-SCALE FEATURES USING MULTIPLE CONVOLUTIONAL NEURAL NETWORKS, Kuan-Chuan Peng (Cornell University), Tsuhan Chen (Cornell University)

JOINT KERNEL DICTIONARY AND CLASSIFIER LEARNING FOR SPARSE CODING VIA LOCALITY PRESERVING K-SVD, Weiyang Liu (School of Electronic and Computer Engineering, Peking University), Zhiding Yu (Carnegie Mellon University), Meng Yang (Shenzhen University), Lijia Lu (Peking University), Yuexian Zou (Peking University)

TueAMPoster - Poster session - 10:00-11:20

INSTANCE-AWARE SIMPLIFICATION OF 3D POLYGONAL MESHES, Tahir Azim (Stanford University, NUST-SEECS), Ewen Cheslack-Postava (Stanford University), Philip Levis (Stanford University)

DISTANCE PRESERVING MARGINAL HASHING FOR IMAGE RETRIEVAL, Li Wu (Shanghai Jiao Tong University), Kang Zhao, Hongtao Lu, Zhen Wei, Baoliang Lv

COMPRESSION OF PHOTO COLLECTIONS USING GEOMETRICAL INFORMATION, Simone Milani (University of Padova), Pietro Zanuttigh (University of Padova)

EVALUATING VISUAL AND TEXTUAL FEATURES FOR PREDICTING USER 'LIKES', Sharath Chandra Guntuku (NTU Singapore), Sujoy Roy (Institute for Infocomm Research, Singapore), Weisi Lin (Nanyang Technological University)

OBJECT TRACKING USING BOOSTED BINARY PATTERNS, Haoyu Ren (Simon Fraser University), Ze-Nian Li

IMPROVING CROSS-MODAL CORRELATION LEARNING BY HYPERLINKS, Shuhui Wang (VIPL, ICT, JDL), yiling Wu (VIPL,ICT,CAS), Qingming Huang (ICT)

SEGBOMP: AN EFFICIENT ALGORITHM FOR BLOCK NON-SPARSE SIGNAL RECOVERY, Xushan Chen (PLAUST), Xiongwei Zhang, Jibin Yang, Meng Sun, Li Zeng

AN ADAPTIVE PEE-BASED REVERSIBLE DATA HIDING SCHEME EXPLOITING REFERENTIAL PREDICTION-ERRORS, Fei Peng (Peking University), Xiaolong Li (Peking University), Bin Yang (Peking University)

TOWARDS ACTIVE ANNOTATION FOR DETECTION OF NUMEROUS AND SCATTERED OBJECTS, Hang Su (Tsinghua University), Hua Yang (Shanghai Jiaotong University), Shibao Zheng (Shanghai Jiaotong University), Sha Wei (China Electronics Standardization Institute), Yu Wang (Shanghai Jiaotong University), Shuang Wu (Shanghai Jiao Tong University)

A COMPACT COLOR DESCRIPTOR FOR PERSON RE-IDENTIFICATION WITH CLOTHING SELECTION FROM A WARDROBE, Yusuke Takahashi (NEC), Hiroyoshi Miyano (NEC)

A SVM ACTIVE LEARNING METHOD BASED ON CONFIDENCE, KNN AND DIVERSITY , Yan Leng (Shandong Normal University), Xinyan Xu (Shandong College of Electronic Technology), Chengli Sun (Nanchang Hangkong University), Chuanfu Cheng (Shandong Normal University), Honglin Wan (Shandong Normal University), Jing Fang (Shandong Normal University), Dengwang Li (Shandong Normal University)

DATA-DRIVEN TAXONOMY FOREST FOR FINE-GRAINED IMAGE CATEGORIZATION, Xiaomeng Wu (NTT), Minoru Mori (NTT), Kunio Kashino (NTT)

MULTI-CUE NORMALIZED NON-NEGATIVE SPARSE ENCODER FOR IMAGE CLASSIFICATION, Shizhou Zhang (Xi'an Jiaotong University), Jinjun Wang, Yudong Liang, Yihong Gong, Nanning Zheng (Xi'an Jiaotong University),

THE EFFECT OF NON-LINEAR STRUCTURES ON THE USAGE OF HYPERVIDEO FOR PHYSICAL TRAINING, Katrin Tonndorf (University of Passau), Christian Handschigl (University of Passau), Julian Windscheid (University of Passau), Harald Kosch, Michael Granitzer (University of Passau)

PERFORMANCE EVALUATION OF THE 1ST AND 2ND GENERATION KINECT DEVICES FOR MULTIMEDIA APPLICATIONS, Simone Zennaro (University of Padova, Italy), Matteo Munaro (University of Padova), Simone Milani (University of Padova), Pietro Zanuttigh (University of Padova), Andrea Bernardi (University of Padova), Stefano Ghidoni (University of Padova, italy), Emanuele Menegatti (University of Padova, italy)

TEMPORALLY CONSISTENT REGION-BASED VIDEO EXPOSURE CORRECTION, Xuan Dong (Tsinghua University), Lu Yuan (MSRA), Weixin Li (UCLA), Alan Yuille (UCLA)

TuePMPoster - Poster session - 15:40-17:00

EFFECTIVELY COMPRESSING NEAR-DUPLICATE VIDEOS IN A JOINT WAY, Hanli Wang (Tongji University), Ming Ma (Tongji University), Tao Tian (Tongji University)

IMPROVING IMAGE FIDELITY BY LUMA-ASSISTED CHROMA UPSAMPLING, Jari Korhonen (DTU)

KEYPOINT ENCODING AND TRANSMISSION FOR IMPROVED FEATURE EXTRACTION FROM COMPRESSED IMAGES, Jianshu Chao (Technische Universität München), Eckehard Steinbach, Lexing Xie

AN ARCHITECTURE TO ASSIST MULTIMEDIA APPLICATION AUTHORS AND PRESENTATION ENGINE DEVELOPERS, Rodrigo Santos (PUC-Rio), Marcio Moreno (PUC-Rio), Luiz Fernando Soares

A DVFS BASED HEVC DECODER FOR ENERGY-EFFICIENT SOFTWARE IMPLEMENTATION ON EMBEDDED PROCESSORS, Erwan Nogues (IETR INSA), Romain Berrada, Maxime Pelcat (IETR INSA), Daniel Menard (IETR INSA), Erwan Raffin (IETR INSA)

LOCALITY CONSTRAINT NEIGHBOUR EMBEDDING VIA REFERENCE PATCH, Javaria Ikram (Bijing Institute of Technology), Yao Lu (BIT), Danfeng Wan (BIT), Jianwu Li (BIT)

GRAPH REGULARIZED NON-NEGATIVE LOCAL COORDINATE FACTORIZATION WITH PAIRWISE CONSTRAINTS FOR IMAGE REPRESENTATION, Yangcheng He (Shanghai Jiao Tong University), Hongtao Lu, Baoliang Lv

INSTRUCTIVE VIDEO RETRIEVAL FOR SURGICAL SKILL COACHING USING ATTRIBUTE LEARNING, Lin Chen (Arizona State University), Peng Zhang, Qiang Zhang, Baoxin Li

VTOUCH: VISION-ENHANCED INTERACTION FOR LARGE TOUCH DISPLAYS, Yinpeng Chen (Microsoft Research), Zicheng Liu (Microsoft Research, USA), Phil Chou, Zhengyou Zhang (Microsoft Research)

MULTI-GRAPH MULTI-INSTANCE LEARNING WITH SOFT LABEL CONSISTENCY FOR OBJECT-BASED IMAGE RETRIEVAL, Fei Li (Fujitsu R & D Center), Rujie Liu (Fujitsu R & D Center)

FACIAL EXPRESSION PRESERVING PRIVACY PROTECTION USING IMAGE MELDING, Yuta Nakashima (NAIST), Tatsuya Koyama (Graduate School of Engineering, Osaka University), Naokazu Yokoya (Graduate School of Information Science, Nara Institute of Science and Technology), Noboru Babaguchi

GROUP SENSITIVE CLASSIFIER CHAINS FOR MULTI-LABEL CLASSIFICATION, Jun Huang (University of Chinese Academy ), guorong Li, Shuhui Wang (VIPL, ICT, JDL), Weigang Zhang, Qingming Huang (ICT)

SEEING THROUGH THE APPEARANCE: BODY SHAPE ESTIMATION USING MULTI-VIEW CLOTHING IMAGES, Wei-Yi Chang (Academia Sinica), Yu-Chiang Frank Wang (Academia Sinica)

EDGE-PRESERVING IMAGE SMOOTHING WITH LOCAL CONSTRAINTS ON GRADIENT AND INTENSITY, Pan Shao (Shanghai Jiao Tong University), Shouhong Ding, Lizhuang Ma

HARMONIC CHANGE DETECTION FOR MUSICAL CHORDS SEGMENTATION, Alessio Degani (University of Brescia), Marco Dalai (University of Brescia), Riccardo Leonardi (University of Brescia), Pierangelo Migliorati (University of Brescia, DII)

CUBOIDS DETECTION IN RGB-D IMAGES VIA MAXIMUM WEIGHTED CLIQUE, Han Zhang (Beihang University), Xiaowu Chen, Yu Zhang, Jia Li, Qing Li, Xiaogang Wang

Wednesday, July 1

WedAM1 - Special Session - Visual Sentiment Analytics in Social Media - 11:20-12:40

ON THE SELECTION OF TRENDING IMAGE FROM THE WEB, Dongfei Yu (USTC), Xinmei Tian, Tao Mei (Microsoft), Yong Rui (Microsoft Research, China)

UNDERSTANDING THE EMOTIONS BEHIND SOCIAL IMAGES: INFERRING WITH USER DEMOGRAPHICS, Boya Wu (Tsinghua University), Jia Jia (Tsinghua University), Yang Yang (Tsinghua University), Peijun Zhao (Tsinghua University), Jie Tang (Tsinghua University)

MULTIMODAL HYPERGRAPH LEARNING FOR MICROBLOG SENTIMENT PREDICTION, Fuhai Chen (Xiamen University), Yue Gao (National University of Singapore), Donglin Cao (Xiamen University), Rongrong Ji (Xiamen University)

JOINT LEARNING FOR IMAGE-BASED HANDBAG RECOMMENDATION, Yan Wang (Nanyang Tech. Univ.), Sheng Li (NTU), Alex Kot (NTU)

WedAM2 - Multimedia Processing II - 11:20-12:40

BACKGROUND BASIS SELECTION FROM MULTIPLE CLUSTERING ON LOCAL NEIGHBORHOOD STRUCTURE, Ming Qin (Beijing Institute of Technolog), Yao Lu (BIT), Huijun Di, Wei Huang

SUPERPIXEL TRACKING VIA GRAPH-BASED SEMI-SUPERVISED SVM AND SUPERVISED SALIENCY DETECTION, Yuxia Wang (Beijing Institute of Technolog), Qingjie Zhao

SIFT KEYPOINT REMOVAL VIA CONVEX RELAXATION, An Cheng (University of Macau), Yuanman Li (University of Macau), Jiantao Zhou (University of Macau)

FAST TWO-CYCLE LEVEL SET TRACKING WITH NARROW PERCEPTION OF BACKGROUND, Yaochen Li (Xi'an Jiaotong University), Yuanqi Su, Yuehu Liu,

WedAM3 - Image/Video content analysis I - 11:20-12:40

PROBABILISTIC LEARNING FROM MISLABELLED DATA FOR MULTIMEDIA CONTENT RECOGNITION, Pravin Kakar (I2R), Alex Chia (I2R)

COUPLED DICTIONARY LEARNING AND FEATURE MAPPING FOR CROSS-MODAL RETRIEVAL, XING XU (Kyushu University), Atsushi Shimada, Rin-ichiro Taniguchi (Kyushu University), Li He

IMAGE RETARGETING BY COMBINING FAST SEAM CARVING WITH NEIGHBORING PROBABILITY (FSC_NEIP) AND SCALING, Lifang Wu (Beijing University of Technolo), Lijuan Wang (Beijing University of Technology), Shuang Liu (Beijing University of Technology), Qingyang Zheng (Beijing University of Technology), Yuchen Jing (Beijing University of Technology), Chang Wen Chen (State University of New York at Buffalo), Bo Yan (Fudan University)

A SCALE SPACE FOR TEXTURE+DEPTH IMAGES BASED ON A DISCRETE LAPLACIAN OPERATOR, Maxim Karpushin (Telecom ParisTech), Giuseppe Valenzise (Telecom ParisTech), Frederic Dufaux (CNRS, France)

WedPM1a - Multimedia Systems and Applications I - 14:40-15:40

CREATIVE DESIGN OF COLOR PALETTES FOR PRODUCT PACKAGING, Ying Li, Anshul Sheopuri (IBM T. J. Watson Research Center)

FREESCUP: A NOVEL PLATFORM FOR ASSISTING SCULPTURE POSE DESIGN, Yirui Wu (Nanjing University), Tong Lu (Nanjing University), Zehuan Yuan, Hao Wang (Nanjing University)

A CASE FOR APPLICATION-MANAGED CACHE FOR BROWSER, Ashok Anand (Instart Logic), Mehrdad Reshadi (Instart Logic), Bowei Du (Instart Logic), Hariharan Kolam (Instart Logic), Sharad Jaiswal, Aditya Akella (University of Wisconsin, Madison)

WedPM1b - Image/Video content analysis II - 17:00-18:00

SALIENCY AND CO-SALIENCY DETECTION BY LOW-RANK MULTISCALE FUSION, Rui Huang (Tianjin university), Wei Feng (Tianjin university), Jizhou Sun (Tianjin university)

STRUCTURE-PRESERVING IMAGE QUALITY ASSESSMENT, Yilin Wang (Arizona State University), Qiang Zhang (Advanced Image Research Lab, Samsung Electronic), Baoxin Li

A ROBUST HIERARCHICAL DETECTION METHOD FOR SCENE TEXT BASED ON CONVOLUTIONAL NEURAL NETWORKS, Hailiang Xu (Nanjing University), Feng Su (Nanjing University)

WedPM2a - Human Computer Interaction - 14:40-15:40

EMG BASED REHABILITATION SYSTEMS_APPROACHES FOR ALS PATIENTS IN DIFFERENT STAGES, Yu-Lin Wang (SCREAM Lab), Wen Yu Su, Tseng-Ying Han, Ching-Lun Lin, Ling-Chi Hsu

PET: AN EYE-TRACKING DATASET FOR ANIMAL-CENTRIC PASCAL OBJECT CLASSES, Syed Omer Gilani (National University of Sciences and Technology), Ramanathan Subramanian (Advanced Digital Sciences Cent), Yan Yan (University of Trento), David Melcher (University of Trento), Nicu Sebe, Stefan Winkler (Advanced Digital Sciences Center)

PICOZOOM: A CONTEXT SENSITIVE MULTIMODAL ZOOMING INTERFACE, Jens Maiero (Bonn-Rhein-Sieg University of Applied Sciences), Ernst Kruijff (Bonn-Rhein-Sieg University), Andr\xe9 Hinkenjann, Gheorghita Ghinea

WedPM2b - Social, user-generated, and cloud-based multimedia - 17:00-18:00

FLICKR CIRCLES: DISCOVERING SOCIALLY-AWARE AESTHETIC TENDENCY, Luming Zhang (National University of Singapo), Roger Zimmermann

JOINT LATENT DIRICHLET ALLOCATION FOR NON-IID SOCIAL TAGS, Jiangchao Yao (Shanghai Jiao Tong University), Ya Zhang (Shanghai Jiaotong University), Zhe Xu, Jun SUN, Jun Zhou (Shanghai Jiao Tong University), Xiao Gu

YOU ARE WHAT YOU TWEET...PIC! GENDER PREDICTION BASED ON SEMANTIC ANALYSIS OF SOCIAL MEDIA IMAGES, Michele Merler, Liangliang Cao (IBM), John Smith (IBM T.J. Watson Research Center, USA)

WedPM3a - Understanding from audio data - 14:40-15:40

EARLY EVENT DETECTION IN AUDIO STREAMS, Huy Phan (University of L󼯬k), Marco Maaß (University of L󼯬k), Radoslaw Mazur (University of L󼯬k), Alfred Mertins (University of L󼯬k)

SPATIAL PERCEPTION REPRODUCTION OF SOUND EVENTS BASED ON SOUND PROPERTY COINCIDENCES, Maosheng Zhang (Wuhan university), Ruimin Hu, Shihong Chen, Xiaochen Wang (Wuhan University), Dengshi Li (Wuhan University), Jiang Lin (East China Institute of Techno)

AUDIO-BASED AFFECT DETECTION IN WEB VIDEOS, Dave Chisholm (SRI International), Behjat Siddiquie (SRI International), Ajay Divakaran (SRI International), Elizabeth Shriberg (SRI International)

WedPMPoster - Poster session - 15:40-17:00

PAINTED FACE EFFECT REMOVAL BY A PROJECTOR-CAMERA SYSTEM WITH DYNAMIC AMBIENT LIGHT ADAPTABILITY, Po-Jung Chiu (National Taiwan University), Shao-Yi Chien (National Taiwan University, Taiwan)

A NOVEL METHOD ON OPTIMAL BIT ALLOCATION AT LCU LEVEL FOR RATE CONTROL IN HEVC, Shengxi Li (Beihang University), Mai Xu (Beihang University), Zulin Wang

REFINING GRAPH MATCHING USING INHERENT STRUCTURE INFORMATION, Wenzhao Li (Queen Mary Univ. of London), Yi-Zhe Song, Andrea Cavallaro (Queen Mary University of London)

AN ADAPTIVE DETECTING STRATEGY AGAINST MOTION VECTOR-BASED STEGANOGRAPHY, Peipei Wang (Chinese Academy of Sciences), Yun Cao (Institute of Information Engineering, Chinese Academy of Sciences), Xianfeng Zhao (Institute of Information Engineering, Chinese Academy of Sciences), Haibo Yu (Institute of Information Engineering, Chinese Academy of Sciences)

EVALUATING THE EFFICACY OF RGB-D CAMERAS FOR SURVEILLANCE, Suraj Raghuraman (UT Dallas), Kanchan Bahirat (The University of Texas at Dallas), Balakrishnan Prabhakaran (UT Dallas)

LEARNING SHARABLE MODELS FOR ROBUST BACKGROUND SUBTRACTION, Yingying Chen (NLPR), Jinqiao Wang (National lab of Automation), Hanqing Lu

VIDEO SHARPNESS PREDICTION BASED ON MOTION BLUR ANALYSIS, Jongyoo Kim, Junghwan Kim (Yonsei University), Woojae Kim, Jisoo Lee (Multidimensional insight lab.), Sanghoon Lee

FUSION OF TIME-OF-FLIGHT AND PHASE SHIFTING FOR HIGH-RESOLUTION AND LOW-LATENCY DEPTH SENSING, Yueyi Zhang (USTC), Zhiwei Xiong (Microsoft Research), Feng Wu (University of Science & Technology of China, China)

PREDICTING IMAGE CAPTION BY A UNIFIED HIERARCHICAL MODEL, Lin Bai (Beijing Institute of Technolog), Kan Li (BIT)

MULTI-GRAPH CROSS-MODAL HASHING FOR LARGE-SCALE MULTIMEDIA SEARCH, Liang Xie (HUST), Lei Zhu (HUST), Peng Pan (HUST), Yansheng Lu (HUST)

GEOLOCALIZATION USING MOBILE PHONE AND STREET GRID MAP IN DYNAMIC ENVIRONMENT, Tung Sing Leung (University of Southern Califor), Gerard Medioni (University of Southern California)

LOSS CONCENTRATION BASED CONTROLLED DELAY: AN ACTIVE QUEUE MANAGEMENT ALGORITHM FOR ENHANCED QUALITY OF EXPERIENCE FOR VIDEO TELEPHONY, Anantharaman Balasubramanian (Interdigital Communications), Liangping Ma (Interdigital Communications), Gregory Sternberg (Interdigital Communications)

UTILIZING IMAGE SOCIAL CLUES FOR AUTOMATED IMAGE TAGGING, Shiai Zhu (university of ottawa), Samah Aloufi (University of Ottawa), Abdulmotaleb El Saddik (University of Ottawa, Canada)

EGOCENTRIC HAND POSE ESTIMATION AND DISTANCE RECOVERY IN A SINGLE RGB IMAGE, Hui Liang (Nanyang Technological University), Junsong Yuan, Daniel Thalmann (Nanyang Technological University)

UNDERSAMPLED FACE RECOGNITION WITH ONE-PASS DICTIONARY LEARNING, Chia-Po Wei (Academia Sinica), Yu-Chiang Frank Wang (Academia Sinica)

VIEWPOINT DISTORTION COMPENSATION IN PRACTICAL SURVEILLANCE SYSTEMS, Ognjen Arandjelovic (Deakin University), Duc-Son Pham, Svetha Venkatesh (Deakin University)

Thursday, July 2

IEEE-TMM Poster Session - 10:00-11:20

A NEW REFERENCE FRAME RECOMPRESSION ALGORITHM AND ITS VLSI ARCHITECTURE FOR UHDTV VIDEO CODEC,
Li Guo, Dajiang Zhou, Satoshi Goto

CPCDN: CONTENT DELIVERY POWERED BY CONTEXT AND USER INTELLIGENCE,
Zhi Wang, Wenwu Zhu, Minghua Chen, Lifeng Sun and Shiqiang Yang

BM25 WITH EXPONENTIAL IDF FOR INSTANCE SEARCH,
Masaya Murata, Hidehisa Nagano, Ryo Mukai, Kunio Kashino, Shin'ichi Satoh

SIMPLE COUNTERMEASURES TO MITIGATE THE EFFECT OF POLLUTION ATTACKS IN NETWORK CODING BASED PEER-TO-PEER LIVE STREAMING,
Attilio Fiandrotti, Rossano Gaeta, Marco Grangetto

DISTRIBUTED SCHEDULING FOR LOW-DELAY AND LOSS-RESILIENT MEDIA STREAMING WITH NETWORK CODING,
Anooq Muzaffar Sheikh, Attilio Fiandrotti, Enrico Magli

AN H.264 HIGH-PROFILE INTRA-PREDICTION WITH ADAPTIVE SELECTION BETWEEN THE PARALLEL AND PIPELINED EXECUTIONS OF PREDICTION MODES,
Chae Eun Rhee, Tae Sung Kim and Hyuk-Jae Lee

PARSING THE HAND IN DEPTH IMAGES,
Hui Liang, Junsong Yuan, Daniel Thalmann

ThuAM1 - Multimedia Systems and Applications II - 11:20-12:40

AN INTELLIGENT NOTIFICATION SYSTEM USING CONTEXT FROM REAL-TIME PERSONAL ACTIVITY MONITORING, Hyungik Oh (UC Irvine), Laleh Jalali (UCI), Ramesh Jain

VISUALIZING VIDEO SOUNDS WITH SOUND WORD ANIMATION, Fangzhou Wang (The University of Tokyo), Hidehisa Nagano (NTT), Kunio Kashino (NTT), Takeo Igarashi (The University of Tokyo)

AUDIO INFORMED VISUAL SPEAKER TRACKING WITH SMC-PHD FILTER, Volkan Kilic (University of surrey), Mark Barnard (University of Surrey), Wenwu Wang (University of Surrey), Adrian Hilton (University of Surrey), Josef Kittler

ACTIVE CROSSTALK REDUCTION SYSTEM FOR MULTIVIEW AUTOSTEREOSCOPIC DISPLAYS, Philippe Hanhart (EPFL), Carmelo di Nolfo (EPFL), Touradj Ebrahimi

ThuAM2 - Special Session - 3D imaging for health monitoring and interventions - 11:20-12:40

ESTIMATING HEART RATE VIA DEPTH VIDEO MOTION TRACKING, Cheng Yang (University of Strathclyde), Gene Cheung (National Institute of Informatics), Vladimir Stankovic (University of Strathclyde)

MIRROR MIRROR ON THE WALL... AN INTELLIGENT MULTISENSORY MIRROR FOR WELL-BEING SELF-ASSESSMENT, Yasmina Andreu-Cabedo (uclan.ac.uk), Pedro Henriquez (uclan.ac.uk), Sara Colantonio (isti.cnr.it), Giuseppe Coppini (ifc.cnr.it), Riccardo Favilla (IFC-CNR), Danila Germanese (isti.cnr.it), Giorgos Giannakakis (ics.forth.gr), daniela Giorgi (isti.cnr.it), Marcus Larsson (liu.se), Paolo Marraccini (ifc.cnr.it), Massimo Martinelli (isti.cnr.it), Bogdan Matuszewski (uclan.ac.uk), matija Milanic (iet.ntnu.no), Maria Antonietta Pascali (CNR - ISTI ), Matthew Pediaditis (ics.forth.gr), Giovanni Raccichini (isti.cnr.it), Lise Randeberg (iet.ntnu.no), Ovidio Salvetti (isti.cnr.it), tomas Stromberg (liu.se)

A ROBUST REAL TIME SYSTEM FOR REMOTE HEART RATE MEASUREMENT VIA CAMERA, Nhan Tran (KAIST), hyukzae Lee (Korea Advanced Institute of Science and Technology), Changick Kim (KAIST)

MEBOOK: KINECT-BASED SELF-MODELING INTERVENTION FOR CHILDREN WITH AUTISM, Nkiruka Uzuegbunam (University of Kentucky), Wing-Hang Wong (University of Kentucky), Sen-ching Cheung (University of Kentucky), Lisa Ruble (University of Kentucky)

ThuAM3 - Multimedia Networking & Communication - 11:20-12:40

POLLUTION-RESILIENT PEER-TO-PEER VIDEO STREAMING WITH BAND CODES, Attilio Fiandrotti (Politecnico di Torino), Marco Grangetto (University of Torino, Torino, Italy), Rossano Gaeta (Universit\xe0 di Torino)

MACHINE LEARNING BASED RATE ADAPTATION WITH ELASTIC FEATURE SELECTION FOR HTTP STREAMING, Yu-Lin Chien (National Taiwan University), Kate Ching-Ju Lin, Ming-Syan Chen

OSCILLATION COMPENSATING DYNAMIC ADAPTIVE STREAMING OVER HTTP, Christopher Mueller (Bitmovin GmbH), Stefan Lederer (bitmovin GmbH), Reinhard Grandl (bitmovin GmbH), Christian Timmerer (Klagenfurt University)

A NEW QUALITY OPTIMIZATION FRAMEWORK FOR DASH STREAMING OVER WIRELESS CHANNELS, Leonardo Favario (Politecnico di Torino), Enrico Masala (Politecnico di Torino)

ThuPM1 - Multimedia Processing III - 15:00-16:40

SPARSE NONLINEAR REPRESENTATION FOR VOICE CONVERSION, Toru Nakashika (University of Electro-Communications), Tetsuya Takiguchi (Kobe University), Yasuo Ariki (Kobe University)

LIGHT FIELD IMAGE EDITING BY 4D PATCH SYNTHESIS, Ke-Wei Chen (National Taiwan University), Ming-Hsu Chang (National Taiwan University), Yung-Yu Chuang

IMPROVED PERFORMANCE OF INVERSE HALFTONING ALGORITHMS VIA COUPLED DICTIONARIES, Pedro Garcia Freitas (TU Delft), Mylene Farias (University of Bras\xedlia), Alet\xe9ia de Ara\xfajo (University of Bras\xedlia)

DISCONTINUOUS SEAM CUTTING FOR ENHANCED VIDEO STITCHING, Jie Hu (University at buffalo, SUNY), Dong-Qing Zhang, Heather Yu, Chang Wen Chen (State University of New York at Buffalo)

DISTRIBUTED COOPERATIVE VIDEO CODING FOR WIRELESS VIDEO BROADCAST SYSTEM, Mengyao Sun (BUPT, China), yumei Wang, Hao Yu, Yu Liu

ThuPM2 - Image/Video content analysis III - 15:00-16:40

ROBUST NONNEGATIVE MATRIX FACTORIZATION WITH DISCRIMINABILITY FOR IMAGE REPRESENTATION, Yuchen Guo (Tsinghua University), Guiguang Ding (Tsinghua University), Jile Zhou (Sohu Inc.)

GOMES: A GROUP-AWARE MULTI-VIEW FUSION APPROACH TOWARDS REAL-WORLD IMAGE CLUSTERING, Zhe Xue (Ucas), guorong Li, Shuhui Wang (VIPL, ICT, JDL), Chunjie Zhang, Weigang Zhang, Qingming Huang (ICT)

LEARNING CLASS-SPECIFIC POOLING SHAPES FOR IMAGE CLASSIFICATION, Jinzhuo Wang (Peking University), Wenmin Wang, Ronggang Wang, Wen Gao (Peking University)

SIGN LANGUAGE RECOGNITION USING 3D CONVOLUTIONAL NEURAL NETWORKS, Jie Huang (Ustc), Wengang Zhou (Univ of Science and Technology, China), Houqiang Li, Weiping Li

A PROBABILISTIC MODEL FOR FOOD IMAGE RECOGNITION IN RESTAURANTS, Luis Herranz (Chinese Academy of Sciences), Ruihan Xu (Chinese Academy of Sciences), Shuqiang Jiang

ThuPM3 - Multimedia Search and Retrieval II - 15:00-16:40

EVALUATING MUSIC RECOMMENDATION IN A REAL-WORLD SETTING: ON DATA SPLITTING AND EVALUATION METRICS, Szu-Yu Chou (Academia Sinica), Yi-Hsuan Yang (Academia Sinica), Yu-Ching Lin (kkbox)

DATA-ORIENTED MULTI-INDEX HASHING, Qingyun Liu, Hongtao Xie ( Institute of Information Engi), Yizhi Liu, Chuang Zhang, Li Guo

LEARNING COMPACT BINARY CODES VIA PAIRWISE CORRELATION RECONSTRUCTION, Xiao-Jiao Mao (Nanjing University), Yu-Bin Yang (Nanjing University), Ning Li

CONTENT-BASED MUSIC RECOMMENDATION USING UNDERLYING MUSIC PREFERENCE STRUCTURE, Mohammad Soleymani (University of Geneva), Anna Aljanaki (Utrecht University), Frans Wiering (Utrecht University), Remco Veltkamp (Utrecht University)

CROSS-MEDIA HASHING WITH CENTROID APPROACHING, Ruoyu Liu (Beijing Jiaotong University), Yao Zhao (Beijing Jiaotong University), Shikui Wei (Beijing Jiaotong University), Zhenfeng Zhu (Beijing Jiaotong University)

ThuAMPoster - Poster session - 10:00-11:20

LIVE FALLAS: A FUTURE INTERNET SMART CITY APP FOR LARGE-SCALE EVENTS, Benjamin Molina, Carlos Palau, Eneko Olivares, Manuel Esteve, Miguel Montesinos, Alberto Romeu

TWO-DIMENSIONAL DIGITAL WATER ART CREATION ON A NON-ABSORBENT HYDROPHILIC SURFACE, Pei-Shan Chen (National Chiao Tung University, Taiwan (ROC),), Sai-Keung Wong (National Chiao Tung University), Wen-Chieh Lin (National Chiao Tung University)

A VISUAL ANALYSIS ON RECOGNIZABILITY AND DISCRIMINABILITY OF ONOMATOPOEIA WORDS WITH DCNN FEATURES, Wataru Shimoda, Keiji Yanai (U. Electro-Comm)

DETECTING ABNORMAL BEHAVIORS IN SURVEILLANCE VIDEOS BASED ON FUZZY CLUSTERING AND MULTIPLE AUTO-ENCODERS, Zhengying Chen (Peking University), Yonghong Tian (Peking University), Wei Zeng, Tiejun Huang

MULTI-MODAL LEARNING FOR GESTURE RECOGNITION, Congqi Cao (NLPR), Yifan Zhang (Institute of Automation,Chinese Academy of Sciences), Hanqing Lu

OPTIMIZATION OF THE NUMBER OF RAYS IN INTERPOLATION FOR LIGHT FIELD BASED FREE VIEWPOINT SYSTEMS, Hooman Shidanshidi (University of Wollongong), Farzad Safaei (University of Wollongong), Wanqing Li

LEARNING GAUSSIAN MIXTURE MODEL FOR SALIENCY DETECTION ON FACE IMAGES, Yun Ren (Beihang University), Mai Xu (Beihang University), Ruihan Pan (Beihang University), Zulin Wang

CAPTURING THE VISUAL LANGUAGE OF SOCIAL MEDIA: EXPLOITING WEB IMAGE SEARCH FOR USER INTEREST PROFILING, Megha Pandey (Institute of Infocomm Research), Alex Chia (I2R)

LOCALLY REGULARIZED ANCHORED NEIGHBORHOOD REGRESSION FOR FAST SUPER-RESOLUTION, Junjun Jiang, Jican Fu (Wuhan University), Tao Lu, Ruimin Hu, Zhongyuan Wang (Wuhan University)

A METHOD TO COMPUTE SALIENCY REGIONS IN 3D VIDEO BASED ON FUSION OF FEATURE MAPS, Lino Ferreira (IPL/ESTG), Luis Cruz (Universidade Coimbra/DEEC), Pedro Assuncao (Instituto de Telecomunicacoes / IPLeiria)

SCENE SEGMENTATION USING TEMPORAL CLUSTERING FOR ACCESSING AND RE-USING BROADCAST VIDEO, Lorenzo Baraldi (University of Modena), Costantino Grana (University of Modena and Reggio Emilia), Rita Cucchiara (Universit\xe0 degli Studi di Modena e Reggio Emilia)

AFFECT-EXPRESSIVE HAND GESTURES SYNTHESIS AND ANIMATION, Elif Bozkurt (Koc University), Engin Erzin (Koc University, Istanbul, Turkey), Yucel Yemez (Koc University)

HUMAN INTERACTION RECOGNITION IN THE WILD : ANALYZING TRAJECTORY CLUSTERING FROM MULTIPLE-INSTANCE-LEARNING PERSPECTIVE , Bo Zhang (DISI, University of Trento), Paolo Rota, Nicola CONCI, Francesco De Natale

TEMPORAL SPOTTING OF HUMAN ACTIONS FROM VIDEOS CONTAINING ACTOR'S UNINTENTIONAL MOTIONS, Keita Hara (Osaka University), Kazuaki Nakamura (Osaka University), Noboru Babaguchi

A HYBRID APPROACH FOR RETRIEVING DIVERSE SOCIAL IMAGES OF LANDMARKS, Duc Tien Dang Nguyen (University of Cagliari), Luca Piras (DIEE - University of Cagliari, Italia), Giorgio Giacinto (DIEE - University of Cagliari), Giulia Boato (University of Trento), Francesco G.B Denatale (university of trento)

AUTORHYTHM: A MUSIC GAME WITH AUTOMATIC HIT-TIME GENERATION AND PERCUSSION IDENTIFICATION, Pei-Pei Chen (National Taiwan University), Tzu-Chun Yeh (National Tsing Hua University), Jyh-Shing Roger Jang (National Taiwan University), Wenshan Liou (Smart Network System Institute, III, Taipei, Taiwan, R.O.C.)

ThuPMPoster - Poster session - 16:40-18:00

IMPROVEMENT OF RE-SAMPLE TEMPLATE MATCHING FOR LOSSLESS SCREEN CONTENT VIDEO, Pin tao, Lixin Feng (Tsinghua University), SiChao Song, Jiang Tao Wen (Tsinghua University, China), ShiQiang Yang

TEXTUAL DESCRIPTION-BASED VIDEO SUMMARIZATION FOR VIDEO BLOGS, Mayu Otani (NAIST), Yuta Nakashima (NAIST), Tomokazu Sato (NAIST), Naokazu Yokoya (Graduate School of Information Science, Nara Institute of Science and Technology)

CODING OF PLENOPTIC IMAGES BY USING A SPARSE SET AND DISPARITIES, Yun Li (Mid Sweden University), M\xe5rten Sj\xf6str\xf6m (Mid Sweden University), Roger Olsson (Mid Sweden University)

FAST MODE SELECTION ALGORITHM BASED ON TEXTURE ANALYSIS FOR 3D-HEVC INTRA PREDICTION, Thaisa Silva (University of Coimbra), Luciano Agostini (Federal University of Pelotas), Luis Cruz (Universidade Coimbra/DEEC)

REAL-TIME FACE DETECTION IN FULL HD IMAGES EXPLOITING BOTH EMBEDDED CPU AND GPU, Chanyoung Oh (University of Seoul), Saehanseul Yi, Youngmin Yi

BEYOND BAG-OF-WORDS: FAST VIDEO CLASSIFICATION WITH FISHER KERNEL VECTOR OF LOCALLY AGGREGATED DESCRIPTORS, Ionut Mironica (University Politehnica of Bucharest), Ionut Cosmin Duta (University of Trento), Bogdan Ionescu (University Politechnica of Bucharest), Nicu Sebe

MUSIC IDENTIFICATION BASED ON MUSIC WORD MODEL, Wanyi Yang (Peking University), Deshun Yang (peking university), xiaoou Chen (peking university), haiqian He (Institute of Computer Science and Technology)

A MIXED NOISE REMOVAL ALGORITHM BASED ON THE MAXIMUM ENTROPY PRINCIPLE, Shang Wu (Tianjin University), Qing Xu (Tianjin University, China), Jialang Li (Tianjin University), Yuejun Guo (Tianjin University, China)

ADAPTIVE INTEGRATION OF DEPTH AND COLOR FOR OBJECTNESS ESTIMATION, Xiangyang Xu (Nanjing University), Ling Ge, Tongwei Ren, Gangshan Wu

RELATIVE LEARNING FROM WEB IMAGES FOR CONTENT-ADAPTIVE ENHANCEMENT, Parag Shridhar Chandakkar (Arizona State University), Qiongjie Tian (Arizona State University), Baoxin Li

MULTI-OBJECTIVE CONTENT PRESERVING WARPING FOR IMAGE STITCHING, Jie Hu (University at buffalo, SUNY), Dong-Qing Zhang, Heather Yu, Chang Wen Chen (State University of New York at Buffalo)

IMAGE INPAINTING WITH ADAPTIVE LINEAR PREDICTOR, Jing Liu (Shanghai Jiao Tong Univeristy), Guangtao Zhai (Shanghai Jiao Tong University), Xiaokang Yang, Chang Wen Chen (State University of New York at Buffalo)

PACKET-BASED PSNR TIME SERIES PREDICTION FOR VIDEO TELECONFERENCING, Liangping Ma (Interdigital Communications), Gregory Sternberg (Interdigital Communications)

PERCEIVING USER'S INTENTION-FOR-INTERACTION: A PROBABILISTIC MULTIMODAL DATA FUSION SCHEME, Christophe Mollaret (LAAS-CNRS IRIT), Alhayat Ali Mekonnen (LAAS - CNRS), Isabelle Ferrane (IRIT), Julien Pinquier (IRIT), Frederic Lerasle (LAAS-CNRS)

A FLEXIBLE PLATFORM FOR QOE-DRIVEN DELIVERY OF IMAGE-RICH WEB APPLICATIONS, Parvez Ahammad (Instart Logic), Rajaram Gaunker (Instart Logic Inc.), Brian Kennedy (Instart Logic Inc.), Mehrdad Reshadi (Instart Logic), Karan Kumar (Instart Logic Inc.), Ayub Pathan (Instart Logic Inc.), Hariharan Kolam (Instart Logic)

FAST AND ROBUST STOREFRONT LOGO RECOGNITION IN SHOPPING CENTERS, Frank Liu (Stanford University), Yanlin Chen