Skip to content

Pacific-Rim Conference on Multimedia (PCM)

September 16-18, 2015, Gwangju, Korea

Technical Program

Wednesday, September 16, 2015

 

10:20 – 12:00

Session W1A: Image and Audio Processing

[Chair: Shang-Hong Lai (National Tsinghua University)]

 

[W1A-1] Pattern Feature Detection for Camera Calibration Using Circular Sample

Dong-Won Shin, Yo-Sung Ho (Gwangju Institute of Science and Technology)

[W1A-2] Efficient Face Image Deblurring via Robust Face Salient Landmark Detection

Yinghao Huang, Hongxun Yao, Sicheng Zhao, Yanhao Zhang (Harbin Institute of Technology)

[W1A-3] Improved Salient Object Detection Based on Background Priors

Tao Xi, Yuming Fang, Weisi Lin, Yabin Zhang (Nanyang Technological University)

[W1A-4] Non-uniform Deblur Using Gyro Sensor and Long/Short Exposure Image Pair

Seungji Seo, Ho-hyoung Ryu, Dongyun Choi, Byung Cheol Song (Inha University)

[W1A-5] Object Searching with Combination of Template Matching

Wisarut Chantara, Yo-Sung Ho (Gwangju Institute of Science and Technology)

 

Session W1B: Multimedia Content Analysis

[Chair: Masaaki Fujiyoshi (Tokyo Metropolitan University)]

 

[W1B-1] Two-Step Greedy Subspace Clustering

Lingxiao Song, Man Zhang, Zhenan Sun, Jian Liang, Ran He (CASIA NLPR)

[W1B-2] Iterative Collection Annotation for Sketch Recognition

Kai Liu, Zhengxing Sun, Mofei Song, Bo Li, Ye Tian (Nanjing University)

[W1B-3] Supervised Dictionary Learning Based on Relationship Between Edges and Levels

Qiang Guo, Yahong Han (Tianjin University)

[W1B-4] Adaptive Margin Nearest Neighbor for Person Re-identification

Lei Yao, Jun Chen, Yi Yu, Zheng Wang, Wenxin Huang, Mang Ye, Ruimin Hu (Wuhan University)

[W1B-5] Compressed-Domain Based Camera Motion Estimation for Realtime Action Recognition

Huafeng Chen, Jun Chen, Hongyang Li, Zengmin Xu, Ruimin Hu (Wuhan University)

 

13:00 – 14:00

Poster Session P1

[Chair: Tongwei Ren (Nanjing University)]

 

[P1-1] Tuning Sparsity for Face Hallucination Representation

Zhongyuan Wang, Jing Xiao, Tao Lu, Zhenfeng Shao, Ruimin Hu (Wuhan University)

[P1-2] Visual Tracking by Assembling Multiple Correlation Filters

Tianyu Yang, ZhongChao Shi, Gang Wang (Ricoh Software Research Center)

[P1-3] A Unified Tone Mapping Operation for HDR Images Including Both Floating-Point and Integer Data

Toshiyuki Dobashi (Tokyo Metropolitan University), Masahiro Iwahashi (Nagaoka University of Technology), Hitoshi Kiya (Tokyo Metropolitan University)

[P1-4] Simplification of 3D Multichannel Sound System Based on Multizone Soundfield Reproduction

Bowei Fang, Song Wang, Xiaochen Wang, Ruimin Hu, Yuhong Yang, Cheng Yang (Wuhan University)

[P1-5] Multi-Channel Object-Based Spatial Parameter Compression Approach for 3D Audio

Cheng Yang, Ruimin Hu, Liuyue Su, Xiaochen Wang, Maosheng Zhang, Shenming Qu (Wuhan University)

[P1-6] A FPGA Based High-speed Binocular Active Vision System for Tracking Circle-shaped Target

Zhengyang Du, Hong Lu, Haowei Yuan, Wenqiang Zhang, Chen Chen, Kongye Xie (Fudan University)

[P1-7] The Extraction of Powerful and Attractive Video Contents Based on One Class SVM

Xingchen Liu (Tianjin University), Xiaonan Song (Hong Kong Bapitist University), Jianmin Jiang (Shenzhen University)

[P1-8] Blur Detection Using Multi-Method Fusion

Yinghao Huang, Hongxun Yao, Sicheng Zhao (Harbin Institute of Technology)

[P1-9] Motion Vector and Players’ Features based Particle Filter for Volleyball Players Tracking in 3D space

Xizhou Zhuang, Xina Cheng, Shuyi Huang, Masaaki Honda, Takeshi Ikenaga (Waseda University)

[P1-10] A Novel Edit Propagation Algorithm via L0 Gradient Minimization

Zhenyuan Guo, Haoqian Wang, Kai Li, Yongbing Zhang, Xingzheng Wang, Qionghai Dai (Tsinghua University)

[P1-11] Position-patch Based Face Hallucination via High-resolution Reconstructed-weights Representation

Danfeng Wan, Yao Lu, Javaria Ikram, Jianwu Li (Beijing Institute of Technology)

[P1-12] Real-Time Rendering of Layered Materials with Linearly Filterable Reflectance Model

Jie Guo, Jinghui Qian, Jingui Pan (Nanjing University)

[P1-13] Hybrid Lossless-Lossy Compression for Real-Time Depth-Sensor Streams in 3D Telepresence Applications

Yunpeng Liu, Stephan Beck, Renfang Wang, Jin Li, Huixia Xu, Shijie Yao, Xiaopeng Tong, Bernd Froehlich (Zhejiang Wanli University)

[P1-14] Marginal Fisher Regression Classification for Face Recognition

Zhong Ji, Yunlong Yu, Yanwei Pang (Tianjin University)

[P1-15] Temporally Adaptive Quantization Algorithm in Hybrid Video Encoder

Haibing Yin, Zhongxiao Wang, Zhelei Xia (China Jiliang University)

[P1-16] Semi-Automatic Labeling with Active Learning for Multi-Label Image Classification

Jian Wu, Chen Ye, Victor S. Sheng, Yufeng Yao, Pengpeng Zhao, Zhiming Cui (Soochow University)

[P1-17] A New Multi-Spectral Fusion Method for Degraded Video Text Frame Enhancement

Shivakumara Palaiahnakote (University of Malaya), Yangbing Weng, Tong Lu (Nanjing University), Liang Meng, Hon Woon (MIMOS)

[P1-18] A Robust Video Text Extraction and Recognition Approach with OCR Feedback Information

Guangyu Gao, He Zhang, Hongting Chen (Beijing Institute of Technology)

[P1-19] Color and Active Infrared Vision: Estimate Infrared Vision of Printed Color Using Bayesian Classifier and K-Nearest Neighbor Regression

Thitirat Siriborvornratanakul (National Institute of Development Administration)

[P1-20] Low Bitrates Audio Bandwidth Extension Using a Deep Auto-Encoder

Lin Jiang, Ruimin Hu, Xiaochen Wang, Maosheng Zhang (Wuhan University)

[P1-21] Part-aware Segmentation for Fine-grained Categorization

Cheng Pang, Hongxun Yao, Zhiyuan Yang, XiaoShuai Sun, Sicheng Zhao, Yanhao Zhang (Harbin Institute of Technology)

[P1-22] Improved Compressed Sensing Based 3D Soft Tissue Surface Reconstruction

Sijiao Yu, Zhiyong Yuan, Qianqian Tong, Xiangyun Liao, Yaoyi Bai (Wuhan University)

[P1-23] Constructing Learning Maps for Lecture Videos by Exploring Wikipedia Knowledge

Feng Wang, Xiaoyan Li, Wenqiang Lei, Chen Huang, Min Yin, Ting-Chuen Pong (East China Normal University)

[P1-24] Object Tracking via Combining Discriminative Global and Generative Local Models

Liujun Zhao, Qingjie Zhao (Beijing Institute of Technology)

[P1-25] Tracking Deformable Target via Multi-Cues Active Contours

Peng Lv, Qingjie Zhao (Beijing Institute of Technology)

[P1-26] Person Re-identification via Attribute Confidence and Saliency

Jun Liu, Chao Liang, Mang Ye, Zheng Wang, Yang Yang, Zhen Han, Kaimin Sun (Wuhan University)

[P1-27] Light Field Edit based on Reparameterization

Hongbo Ao, Yongbing Zhang (Tsinghua University), Yebin Liu, Adrian Jarabo, Belen Masia (Universidad de Zaragoza), Qionghai Dai (Tsinghua University), Diego Gutierrez (Universidad de Zaragoza)

[P1-28] Interactive Animating Virtual Characters with the Human Body

Hao Jiang, Lei Zhang (TsingHua University)

 

14:00 – 15:40

Session W2A: Visual Understanding and Recognition on Big Data

[Chair: Xianglong Liu (Beihang University)]

 

[W2A-1] Fast Graph Similarity Search via Locality Sensitive Hashing

Boyu Zhang, Xianglong Liu, Bo Lang (Beihang University)

[W2A-2] Text Localization with Hierarchical Multiple Feature Learning

Yanyun Qu, Li Lin, Weiming Liao, Junran Liu, Yang Wu, Hanzi Wang (Xiamen University)

[W2A-3] Recognizing Human Actions by Sharing Knowledge in Implicit Action Groups

RuiShan Liu, YanHua Yang, Cheng Deng (Xidian University)

[W2A-4] Human Parsing via Shape Boltzmann Machine Networks

Qiurui Wang, Chun Yuan, Feiyue Huang, Chengjie Wang (Tsinghua University)

[W2A-5] Depth-based Stereoscopic Projection Approach for 3D Saliency Detection

Hongyun Lin, Chunyu Lin, Yao Zhao (Beijing Jiaotong University), Jimin Xiao, Tammam Tillo (Xi'an Jiaotong-Liverpool University)

 

Session W2B: Coding and Reconstruction of Multimedia Data with Spatial-Temporal Information

[Chair: Zhongyuan Wang (Wuhan University)]

 

[W2B-1] Revisiting Single Image Super-Resolution Under Internet Environment: Blur Kernels and Reconstruction Algorithms

Kai Zhang, Xiaoyu Zhou, Hongzhi Zhang, Wangmeng Zuo (Harbin Institute of Technology)

[W2B-2] Prediction Model of Multi-channel Audio Quality Based on Multiple Linear Regression

Jing Wang, Yi Zhao, Wenzhi Li, Fei Wang, Zesong Fei, Xiang Xie (Beijing Institute of Technology)

[W2B-3] Physical Properties of Sound Field Based Estimation of Phantom Source in 3D

Shanfa Ke, Xiaochen Wang, Li Gao, Tingzhao Wu (National Engineering Research Center for Multimedia Software), Yuhong Yang (Wuhan University)

[W2B-4] Non-overlapped Multi-source Surveillance Video Coding Using Two-Layer Knowledge Dictionary

Yu Chen, Jing Xiao, Liang Liao, Ruimin Hu (Wuhan University)

[W2B-5] Global Motion Information Based Depth Map Sequence Coding

Fei Cheng, Jimin Xiao, Tammam Tillo (Xi'an Jiaotong-Liverpool University), Yao Zhao (Beijing Jiaotong University)

 

16:00 – 17:40

Session W3A: 3D Image/Video Processing and Applications

[Chair: Xin Jin (Tsinghua University)]

 

[W3A-1] Motion and Depth Assisted Workload Prediction for Parallel View Synthesis

Zhanqi Liu, Xin Jin, Qionghai Dai (Tsinghua University)

[W3A-2] Graph Cuts Stereo Matching Based on Patch-Match and Ground Control Points Constraint

Xiaoshui Huang (UTS), Chun Yuan (Tsinghua University), Jian Zhang (University of Technology at Sydney)

[W3A-3] Synthesized Views Distortion Model Based Rate Control in 3D-HEVC

Songchao Tan (JDL), Siwei Ma (PKU), Shanshe Wang (JDL), Wen Gao (Peking University)

[W3A-4] Efficient Depth Map Upsampling Method using Standard Deviation

Su-Min Hong, Yo-Sung Ho (Gwangju Institute of Science and Technology)

[W3A-5] Orthogonal and Smooth Subspace based on Sparse Coding for Image Classification

Fushuang Dai, Dongxia Chang, Yao Zhao, Chunyu Lin (Beijing Jiaotong University)

 

Session W3B: Video/Image Quality Assessment & Processing

[Chair: Jinjian Wu (Xidian University), Leida Li (China University of Mining and Technology)]

 

[W3B-1] Sparse Representation Based Image Quality Assessment with Adaptive Sub-Dictionary Selection

Leida Li, Hao Cai (China University of Mining and Technology), Yabin Zhang (Nanyang Technological University), Jiansheng Qian (China University of Mining and Technology)

[W3B-2] Single Image Super-Resolution via Iterative Collaborative Representation

Yulun Zhang, Yongbing Zhang (Tsinghua University), Jian Zhang (Peking University), Haoqian Wang, Qionghai Dai (Tsinghua University)

[W3B-3] Influence of Spatial Resolution on State-of-the-Art Saliency Models

Zhaohui Che, Guangtao Zhai, Xiongkuo Min (Shanghai Jiao Tong University)

[W3B-4] Depth Map Upsampling via Progressive Manner Based on Probability Maximization

Rongqun Lin, Yongbing Zhang, Haoqian Wang, Xingzheng Wang, Qionghai Dai (Tsinghua University)

[W3B-5] Perceptual Quality Improvement for Synthesis Imaging of Chinese Spectral Radioheliograph

Long Xu, Lin Ma, Zhuo Chen, Yihua Yan, Jinjian Wu (Xidian University)

 

Thursday, September 17, 2015

 

10:20 – 12:00

Session T1A: Image and Audio Processing 2

[Chair: Shoko Imaizumi (Chiba University)]

 

[T1A-1] On the Security of Image Manipulation Forensics

Gang Cao (Communication University of China), Yongbin Wang, Yao Zhao, Rongrong Ni, Chunyu Lin (Beijing Jiaotong University)

[T1A-2] A Sparse Representation-Based Label Pruning for Image Inpainting Using Global Optimization

Hak Gu Kim, Yong Man Ro (KAIST)

[T1A-3] Interactive RGB-D Image Segmentation Using Hierarchical Graph Cut and Geodesic Distance

Ling Ge, Ran Ju, Tongwei Ren, Gangshan Wu (Nanjing University)

[T1A-4] Face Alignment with Two-Layer Shape Regression

Qilong Zhang, Lei Zhang (Tsinghua University)

[T1A-5] 3D Panning Based Sound Field Enhancement Method for Ambisonics

Song Wang, Ruimin Hu, Shihong Chen, Xiaochen Wang, Yuhong Yang, Weiping Tu (Wuhan University)

 

Session T1B: Multimedia Applications and Services

[Chair: Chunyu Lin (Beijing Jiaotong University)]

 

[T1B-1] Multi-target Tracking via Max-Entropy Target Selection and Heterogeneous Camera Fusion

Jingjing Wang, Nenghai Yu (University of Science and Technology of China)

[T1B-2] Adaptive Multiple Appearances Model Framework for Long-Term Robust Tracking

Shuo Tang, Longfei Zhang, Jiapeng Chi, Zhufan Wang, Gangyi Ding (Beijing Institute of Technology)

[T1B-3] On-line Sample Generation for In-air Written Chinese Character Recognition Based on Leap Motion Controller

Ning Xu, Weiqiang Wang, Xiwen Qu (University of Chinese Academy of Sciences)

[T1B-4] Progressive Image Segmentation Using Online Learning

Jiagao Hu, Zhengxing Sun, Kewei Yang, Yiwen Chen (Nanjing University)

[T1B-5] A Study of Interactive Digital Multimedia Applications

Chutisant Kerdvibulvech (National Institute of Development Administration)

 

13:00 – 14:00

Poster Session P2

[Chair: Kwan-Jung Oh (ETRI)]

 

[P2-1] High-Speed Periodic Motion Reconstruction Using an Off-the-shelf Camera with Compensation for Rolling Shutter Effect

Jeong-Jik Seo, Wissam J. Baddar, Hyung-Il Kim, Yong Man Ro (KAIST)

[P2-2] Robust Feature Extraction for Shift and Direction Invariant Action Recognition

Younghan Jeon, Tushar Sandhan, Jin Young Choi (Seoul National University)

[P2-3] Scalable Tamper Detection and Localization Scheme for JPEG2000 Codestreams

Takeshi Ogasawara, Shoko Imaizumi, Naokazu Aoki (Chiba University)

[P2-4] Developing a Visual Stopping Criterion for Image Mosaicing using Invariant Color Histograms

Armagan Elibol, Hyunjung Shim (Yonsei University)

[P2-5] Intelligent Reconstruction and Assembling of Pipeline from Point Cloud Data in Smart Plant 3D

Pavitra Holi, Seong Sil Park, Ashok Kumar Patil, Ajay Kumar Kumar, Young Ho Chai(Chung-Ang University)

[P2-6] A Rotational Invariant Non-local Mean

Rassulzhan Poltayev, Byung-Woo Hong (Chung-Ang University)

[P2-7] Adaptive Layered Video Transmission with Channel Characteristics

Fan Zhang, Anhong Wang (Taiyuan University of Science and Technology), Xiaoli Ma (Georgia Institute of Technology), Bing Zeng (University of Electronic Science and Technology of China)

[P2-8] An Accurate and Efficient Nonlinear Depth Quantization Scheme

Jian Jin, Yao Zhao, Chunyu Lin (Beijing Jiaotong University), Anhong Wang (Taiyuan University of Science and Technology)

[P2-9] Synthesis-Aware Region-Based 3D Video Coding

Xing Zhiwei, Anhong Wang, Fan Zhang (Taiyuan University of Science and Technology)

[P2-10] A Paradigm for Dynamic Adaptive Streaming over HTTP for Multi-view Video

Jimin Xiao (Xi'an Jiaotong-Liverpool University), Miska Hannuksela (Nokia Researcher Center), Tammam Tillo (Xi'an Jiaotong-Liverpool University), Moncef Gabbouj (Tampere University of Technology)

[P2-11] Adaptive Model for Background Extraction Using Depth Map

Boyuan Sun (University of Liverpool), Tammam Tillo, Ming Xu (Xi'an Jiaotong-Liverpool University)

[P2-12] An Efficient Partition Scheme for Depth-based Block Partitioning in 3D-HEVC

Zhang Yuhua, Ce Zhu, Yongbing Lin, Jianhua Zheng, Wang Yong (University of Electronic Science and Technology of China)

[P2-13] Image Classification with Local Linear Decoding and Global Multi-feature Fusion

Ping Wu, Hong Zhang (Wuhan University of Science and Technology)

[P2-14] Hashing with Inductive Supervised Learning

Mingxing Zhang, Fumin Shen, Hanwang Zhang, Ning Xie, Wankou Yang (University of Electronic Science and Technology of China)

[P2-15] Graph Based Visualization of Large Scale Microblog Data

Yue Guan, Kaidi Meng, Haojie Li (Dalian University of Technology)

[P2-16] Boosting Accuracy of Attribute Prediction via SVD and NMF of Instance-Attribute Matrix

Donghui Li, Zhuo Su, Hanhui Li, Xiaonan Luo (Sun Yat-sen University)

[P2-17] Fatigue Detection Based on Fast Facial Feature Analysis

Ruijiao Zheng, Chunna Tian, Haiyang Li, Minglangjun Li, Wei Wei (Xidian University)

[P2-18] A Packet-Layer Model with Content Characteristics for Video Quality Assessment of IPTV

Qian Zhang (Xian University of Architecture and Technology), Lin Ma (Huawei Noah's Ark Lab), Fan Zhang, Long Xu

[P2-19] Implementation of Human Action Recognition System using Multiple Kinect Sensors

Beom Kwon, Doyoung Kim, Junghwan Kim, Inwoong Lee, Jongyoo Kim, Heeseok Oh, Haksub Kim, Sanghoon Lee (Yonsei University)

[P2-20] Temporal Consistency Enhancement for Digital Holographic Video

Kwan-Jung Oh, Hyon-Gon Choo, Jinwoong Kim (ETRI)

 

14:00 – 15:40

Session T2A: Video Coding and Processing

[Chair: Byung Cheol Song (Inha University)]

 

[T2A-1] Particle Filter with Ball Size Adaptive Tracking Window and Ball Feature Likelihood Model for Ball’s 3D Position Tracking in Volleyball Analysis

Xina Cheng, Xizhou Zhuang, Yuan Wang, Masaaki Honda, Takeshi Ikenaga (Waseda University)

[T2A-2] Block-Based Global and Multiple-Reference Scheme for Surveillance Video Coding

Liming Yin, Ruimin Hu, Shihong Chen, Jing Xiao, Minsheng Ma (Wuhan University)

[T2A-3] Global Object Representation of Scene Surveillance Video Based on Model and Feature Parameters

Minsheng Ma, Ruimin Hu, Shihong Chen, Jing Xiao, Zhongyuan Wang, Shenming Qu (Wuhan University)

[T2A-4] A Sparse Error Compensation based Incremental Principal Component Analysis Method for Foreground Detection

Ming Qin, Yao Lu, Huijun Di, Tianfei Zhou (Beijing Institute of Technology)

 

Session T2B: Multimedia Representation Learning

[Chair: Hyunjung Shim (Yonsei University)]

 

[T2B-1] Convolutional Neural Networks Features: Principal Pyramidal Convolution

Yanming Guo (Leiden University), Songyang Lao (National University of Defense Technology), Yu Liu (Leiden University), Liang Bai (National University of Defense Technology), Shi Liu (Beijing Normal University), Michael S. Lew (Leiden University)

[T2B-2] Gaze Shifting Kernel: Engineering Perceptually- Aware Features for Scene Categorization

Luming Zhang, Richang Hong, Meng Wang (Hefei University of Technology)

[T2B-3] Two-Phase Representation Based Classification

Jianping Gou, Yongzhao Zhan, Xiangjun Shen, Qirong Mao, Liangjun Wang (Jiangsu University)

[T2B-4] Deep Feature Representation via Multiple Stack Auto-encoders

Mingfu Xiong, Jun Chen, Zheng Wang, Chao Liang, Qi Zheng, Zhen Han, Kaimin Sun (Wuhan University)

[T2B-5] Beyond HOG: Learning Local Parts for Object Detection

Chenjie Huang, Zheng Qin, Kaiping Xu, Guolong Wang, Tao Xu (Tsinghua University)

 

16:00 – 17:40

Session T3A: Recent Advances in Image/Video Processing

[Chair: Sangkeun Lee (Chung-Ang University)]

 

[T3A-1] Score Level Fusion of Multibiometrics Using Local Phase Array

Luis Marval Perez, Shoichiro Aoyama, Koichi Ito, Takafumi Aoki (Tohoku University)

[T3A-2] Histogram-Based Near-Lossless Data Hiding and Its Application to Image Compression

Masaaki Fujiyoshi, Hitoshi Kiya (Tokyo Metropolitan University)

[T3A-3] Hierarchical Learning for Large-Scale Image Classification via CNN and Maximum Confidence Path

Chang Lu (XMU_ICA), Yanyun Qu, Cuiting Shi, Yang Wu, Hanzi Wang (Xiamen University), Jianping Fan (University of North Carolina at Charlotte)

[T3A-4] Single Camera-Based Depth Estimation and Improved Continuously Adaptive Mean Shift Algorithm for Tracking Occluded Objects

Jaehyun Im, Jaehoon Jung, Joonki Paik (Chung-Ang University)

[T3A-5] A Flexible Programmable Camera Control and Data Acquisition Hardware Platform

Fei Cheng, Jimin Xiao, Tammam Tillo (Xi'an Jiaotong-Liverpool University), Yao Zhao (Beijing Jiaotong University)

 

Session T3B: Human Action Recognition in Social Robotics and Video Surveillance

[Chair: Hale Kim (Inha University), Lu Yang (University of Electronic Science and Technology of China)]

 

[T3B-1] Recognition of Human Group Activity for Video Analytics

Jaeyong Ju, Cheoljong Cheoljong, Hanseok Ko (Korea University), Sebastian Scherer (Carnegie Mellon University)

[T3B-2] An Incremental SRC Method for Face Recogn

Junjian Ye, Ruoyu Yang (Nanjing University)

[T3B-3] A Survey on Media Interaction in Social Robotics

Lu Yang, Hong Cheng, Jiasheng Hao, Yanli Ji, Yiqun Kuang (University of Electronic Science and Technology of China)

[T3B-4] Recognizing 3D Continuous Letter Trajectory Gesture Using Dynamic Time Warping

Tang Jingren, Hong Cheng, Lu Yang (University of Electronic Science and Technology of China)

[T3B-5] Real-Time Human Action Recognition Using CNN Over Temporal Images for Static Video Surveillance Cameras

Cheng-Bin Jin, Shengzhe Li, Trung Dung Do, Hakil Kim (Inha University)

 

Friday, September 18, 2015

 

9:00 – 10:00

Poster Session P3

[Chair: Luming Zhang (Hefei University of Technology)]

 

[P3-1] Frame Rate and Perceptual Quality for HD Video

Yutao Liu, Guangtao Zhai, Debin Zhao, Xianming Liu (Harbin Institute of Technology)

[P3-2] No-reference Image Quality Assessment Based on Singular Value Decomposition without Learning

Jonghee Kim, Hyunjun Eun, Changik Kim (KAIST)

[P3-3] An Improved Brain MRI Segmentation Method Based on Scale-space Theory and Expectation Maximization Algorithm

Yuqing Song, Xiang Bao, Zhe Liu (Jiangsu University), Deqi Yuan (Zhenjiang First People’s Hospital), Minshan Song (Jiangsu University)

[P3-4] User-Driven Sports Video Customization System for Mobile Devices

Jian Qin, Jun Chen, Zheng Wang, Jiyang Zhang, Xinyuan Yu, Qi Zheng (Wuhan University), Chunjie Zhang (University of Chinese Academy of Sciences)

[P3-5] Auditory Spatial Localization Studies with Different Stimuli

Tao Zhang, Shuting Sun, Chunjie Zhang (Tianjin University)

[P3-6] Multichannel Simplification Based on Deviation of Loudspeaker Positions

Dengshi Li, Ruimin Hu, Xiaochen Wang, Shanshan Yang, Weiping Tu (Wuhan University)

[P3-7] Real-time Perception of Abnormal Crowd Behavior for Social Robotics

Dekun Hu, BingHao Meng, Shengyin Fan, Lu Yang, Hong Cheng, Yuanli Ji (University of Electronic Science and Technology of China)

[P3-8] Sparse Representation Based Approach for RGB-D Hand Gesture Recognition

Te-Feng Su, Chin-Yun Fan, Meng-Hsuan Lin, Shang-Hong Lai (National Tsinghua University)

[P3-9] Eye Gaze Correction for Video Conferencing Using Kinect v2

Eunsang Ko, WooSeok Jang, Yo-Sung Ho (Gwangju Institute of Science and Technology)

[P3-10] Temporally Consistence Depth Estimation from Stereo Video Sequences

Ji-Hun Mun, Yo-Sung Ho (Gwangju Institute of Science and Technology)

[P3-11] A New Low-Complexity Error Concealment Method for Stereo Video Communication

Kesen Yan, Mei Yu, Zongju Peng, Feng Shao, Gangyi Jiang (Ningbo University)

[P3-12] Hole Filling Algorithm using Spatial-Temporal Background Depth Map for View Synthesis in Free View Point Television

Huu Noi Doan, Beomsu Kim, Min-Cheol Hong (Soongsil University)

[P3-13] Efficient Disparity Map Generation Using Stereo and Time-of-Flight Depth Cameras

WooSeok Jang, Yo-Sung Ho (Gwangju Institute of Science and Technology)

[P3-14] Super-resolution of depth map exploiting planar surfaces

Tammam Tillo, Zhi Jin, Fei Cheng (Xi'an Jiaotong-Liverpool University)

[P3-15] Hierarchical Interpolation-Based Disocclusion Region Recovery for Two-View to N-View Video Conversion

Wun-Ting Lin, Chen-Ting Yeh, Shang-Hong Lai (National Tsinghua University)

[P3-16] UEP network coding for SVC streaming

Seongyeon Kim, Yong-woo Lee, Jitae Shin (Sungkyunkwan University)

[P3-17] Overview on MPEG MMT Technology and Its Application to Hybrid Media Delivery over Heterogeneous Networks

Tae-Jun Jung, Hong-rae Lee, Kwang-deok Seo (Yonsei University)

[P3-18] A Framework for Extracting Sports Video Highlights using Social Media

Yao-Chung Fan, Huan Chen, Wei-An Chen (National Chung Hsing University)

[P3-19] Internal Generative Mechanism Based Otsu Multilevel Thresholding Segmentation for Medical Brain Images

Yuncong Feng, Xuanjing Shen, Haipeng Chen, Xiaoli Zhang (Jilin University)

[P3-20] A New Multi-Modal Technique for Bib Number/Text Detection in Natural Images

Sangheeta Roy, Palaiahnakote Shivakumara (University of Malaya), Prabir Mondal (Indian Statistical Institute), R Raghavendra (Norwegian Biometric Laboratory), Umapada Pal (Indian Statistical Institute), Tong Lu (Nanjing University)

[P3-21] Rapid 3D Face Modeling from Video

Hong Song, Jie Lv, Yanming Wang (Beijing Institute of Technology)

 

10:20 – 12:00

Session F1A: Social Media Computing

[Chair: Wei-Ta Chu (National Chung Cheng University), Keiji Yanai (University of Electro-Communications)]

 

[F1A-1] Real-life Voice Activity Detection based on Audio-visual Alignment

Jin Wang, Chao Liang, Xiaochen Wang, Zhongyuan Wang (Wuhan University)

[F1A-2] Emotion Recognition from EEG Signals by Leveraging Stimulus Videos

Zhen Gao, Shangfei Wang (University of Science and Technology of China)

[F1A-3] Twitter Event Photo Detection Using Geotagged Tweets and Non-geotagged Photo Tweets

Takamu Kaneko, Nga Do Hang, Keiji Yanai (University of Electro-Communications)

[F1A-4] Weather-Adaptive Distance Metric for Landmark Image Classification

Ding-Shiuan Ding, Wei-Ta Chu (National Chung Cheng University)

[F1A-5] Power of Tags: Predicting Popularity of Social Media in Geo-Spatial and Temporal Contexts

Toshihiko Yamasaki, Jiani Hu, Kiyoharu Aizawa (University of Tokyo), Tao Mei (Microsoft Research)

 

Session F1B: New Media Representation and Transmission Technologies for Emerging UHD Services

[Chair: Jewon Kang (Ewha Womans University)]

 

[F1B-1] Comparison of Real-time Streaming Performance between UDP and TCP based delivery over LTE

SooKyung Park, KyeongWon Kim, Doug Young Suh (Kyung Hee University)

[F1B-2] Video Streaming for Multi-Cloud Game

Yoonseok Heo, Taeseop Kim, Doug Young Suh (Kyung Hee University)

[F1B-3] Performance Analysis of Scaler Soc for 4K Video Signal

Soon-Jin Lee, Jong-Ki Han (Sejong University)

[F1B-4] Deblocking Filter for Depth Videos in 3D Video Coding Extension of HEVC

Yunseok Song, Yo-Sung Ho (Gwangju Institute of Science and Technology)

[F1B-5] Sparcity-Induced Structured Transform in Intra Video Coding for Screen Contents

Je-won Kang (Ewha Womans University)