2019 IEEE International Conference on Visual Communications and Image Processing (VCIP)

December 1-4, 2019 • Sydney, AUSTRALIA

Preliminary Conference Program

Monday, 2 December

08:45-09:00 Opening Ceremony

09:00-10:00 Keynote 1 - Title Thomas Sikora
Director of the Communication Systems Lab, Technische Universität Berlin, Germany
Session Chair: TBA, affiliation

10:00-10:30 Coffee Break

10:30-12:30 Oral Session 1 – Multimedia Analysis, Representation & Understanding I Session Chair: TBA, affiliation 1. Unpaired Images based Generator Architecture for Facial Expression Recognition
     Xi Zhang (CASIA);
     Feifei Zhang (Jiangsu University);
     Changsheng Xu (CASIA)*
2. Facial Motion Prior Networks for Facial Expression Recognition
     Yuedong Chen (Nanyang Technological University)*;
     Jianfeng Wang (Lenovo); ShiKai Chen (Southeast University);
     zhongchao shi (lenovo company);
     Jianfei Cai (Nanyang Technological University)
3. GRNet: An Efficient Group Ranking Network for Face Attribute Recognition
     Dingchang hu (Beijing University of Posts and Telecommunications)*;
     Pingyu Wang (Beijing University of Posts and Telecommunications);
     Yiwei Liu (Beijing University of Posts and Telecommunications);
     Fei Su (Beijing University of Posts and Telecommunications); Zhicheng Zhao (bupt)
4. Joint Learning of Dictionary and Convolutional Network for Pedestrian Attribute Recognition
     Yan Sha (Beijing Jiaotong University);
     Congyan Lang (Beijing Jiaotong University)*;
     Peixi Peng (Institute of Automation, Chinese Academy of Sciences);
     Junliang Xing (Institute of Automation, Chinese Academy of Sciences);
     Danxia Li (Peking University)
5. Part-guided Network for Pedestrian Attribute Recognition
     Haoran An (Beihang University);
     Haonan Fan (Beihang University);
     Kaiwen Deng (Beihang University);
     Hai-Miao Hu (Beihang University)*
6. Spatial and Semantic Relations for Pedestrian Attribute Recognition
     Lei Li (Beijing University of Posts and Telecommunications)*;
     Yuan Dong ( Beijing University of Posts and Telecommunications);
     Fengye Xiong (Beijing Faceall Technology Co.,Ltd);
     Hongliang Bai (Beijing Faceall Technology Co.,Ltd)

10:30-12:30 Oral Session 2 – Deep Learning I Session Chair: TBA, affiliation 1. Making Large Ensemble of Convolutional Neural Networks via Bootstrap Re-sampling
     Jiawei Li (Tsinghua University)*;
     Xingchun Xiang (Tsinghua University);
     Tao Dai (Tsinghua University);
     Shutao Xia (Tsinghua University)
2. Gradient-Based Pooling for Convolutional Neural Networks
     Mohammad Nikzad (Griffith University)*;
     Yongsheng Gao (Griffith university, Australia);
     Jun Zhou (Griffith University)
3. Pyramid Real Image Denoising Network
     Yiyun Zhao (Beijing University of Posts and Telecommunications)*;
     Zhuqing jiang (Beijing University of Posts and Telecommunications);
     Aidong men (Beijing University of Posts and Telecommunications);
     Guodon Ju (GuangDong TUS-TuWei Technology Co.,Ltd)
4. PGAN: Prediction Generative Adversarial Nets for Meshes
     Tingting Li (Beijing University of technology)*;
     Yunhui Shi (Beijing University of Technology);
     Xiaoyan Sun (Microsoft Research Asia);
     Jin Wang (Beijing University of Technology);
     Baocai Yin (Dalian University of Technology)
5. No-Reference Stereoscopic Image Quality Assessment Based on Dilation Convolution
     Ping Zhao (Tianjin University)*;
     Sumei Li (Tianjin University);
     Yongli Chang (Tianjin University)
6. Privacy-Preserving Fall Detection with Deep Learning on mmWave Radar Signal
     Yangfan Sun (University of Missouri-Kansas City);
     Renlong Hang (University of Missouri-Kansas City);
     Zhu Li (University Of Missouri-Kansas City)*;
     Mouqing Jin (RiC Semiconductor);
     Kelvin Xu (RiC Semiconductor)

12:30-13:30 Lunch

13:30-14:30 Keynote 2 - Title Wen Gao
Director of Faculty of Information and Engineering Sciences, Peking University, China
Session Chair: TBA, affiliation

14:30-15:30 Oral Session 3 – Classification Session Chair: TBA, affiliation 1. Competing Ratio Loss for Multi-class image Classification
     Ke Zhang (North China Electric Power University);
     Xinsheng Wang (North China Electric Power University)*;
     Yurong Guo (North China Electric Power University);
     Zhenbing Zhao (North China Electric Power University);
     Zhanyu Ma (Beijing University of Posts and Telecommunications)
2. FICAL: Focal Inter-Class Angular Loss for Image Classification
     Xinran Wei (Beijing University of Posts and Telecommunications);
     Dongliang Chang (Beijing University of Posts and Telecommunications);
     Jiyang Xie (Beijing University of Posts and Telecommunications);
     Yixiao Zheng (Beijing University of Posts and Telecommunications);
     Chen Gong (Nanjing University of Science and Technology);
     Chuang Zhang (Beijing University of Posts and Telecommunications);
     Zhanyu Ma (Beijing University of Posts and Telecommunications)*
3. A Single-stage Multi-class Object Detection Method for Remote Sensing Images
     Liping Hou (University of Chinese Academy of Sciences);
     Jian Xue (University of Chinese Academy of Sciences);
     Ke Lu (University of Chinese Academy of Sciences)*;
     Li Hao (University of Chinese Academy of Sciences);
     Mohammad Muntasir Rahman (University of Chinese Academy of Sciences)

14:30-15:30 Oral Session 4 – Multimedia Analysis, Representation & Understanding II Session Chair: TBA, affiliation 1. Toward Intelligent Visual Sensing and Low-cost Analysis: A Collaborative Computing Approach
      Yan Bai (Peking University);
      Lingyu Duan (Peking University)*;
      Yong Luo (Nanyang Technological University);
      Shiqi Wang (CityU);
      Yonggang Wen (Nanyang Technological University);
      Wen Gao (PKU)
2. An End-To-End Future Frame Prediction Method For Vehicle-Centric Driving Videos
      Li Du (Beijing University of Posts and Telecommunications)*;
      kaikun ji (BUPT);
      Zhicheng Zhao (bupt);
      Fei Su (Beijing University of Posts and Telecommunications);
      Bojin Zhuang (Ping An Technology (Shenzhen) Co., Ltd.)
3. Underwater image enhancement based on the iteration of a Generalization of Dark Channel Prior
     Yosuke Ueki (Keio university)*;
     Masaaki Ikehara (Keio university)

15:30-16:00 Coffee Break

16:00-17:30 Demonstration & Poster Session 1 Session Chair: TBA, affiliation Demonstration
1. Angel Girl of Visually Impaired Artists: Painting Navigation System for Blind or Visually Impaired Painters
     Hang Liu (East China Normal University);
     Menghan Hu (East China Normal University)*;
     Guangtao Zhai (Shanghai Jiao Tong University);
     Huijing Huang (East China Normal University);
     Wa Zhang (East China Normal University);
     Qingli Li (East China Normal University);
     Yinghong Tian (East China Normal University);
     Yanling Shi (East China Normal University)
2. Visualization of Dynamic Resource Allocation for HEVC Encoding in FPGA-Accelerated SDN Cloud
     Panu Sjövall (Tampere University)*;
     Mikko Teuho (Tampere University);
     Arto Oinonen (Tampere University);
     Jarno Vanne (Tampere University);
     Timo Hämäläinen (Tampere University)
3. FPGA Based Video Transcoding System with 2K-4K Super-Resolution Conversion
     yuzhuo wei (shanghai jiaotong university)*;
     Li Chen (Shanghai Jiao Tong University);
     Rong Xie (Shanghai Jiao Tong University);
     Li Song (Shanghai Jiao Tong University);
     Xiaoyun Zhang (Shanghai Jiao Tong University);
     Zhiyong Gao (Shanghai Jiao Tong University)
4. Wireless Cooperative Caching System
     Chaoyu Gu (SHANGHAI JIAO TONG UNIVERSITY)*;
     Jian Xiong (SHANGHAI JIAO TONG UNIVERSITY);
     Haonan Xie (SHANGHAI JIAO TONG UNIVERSITY);
     Peng Cheng (THE UNIVERSITY OF SYDNEY)
Poster
1. Fast Image Deblurring Based on Dual-Exposure Prior
     Xu Zhang (Beihang University);
     Hai-Miao Hu (Beihang University)*;
     Jialin Chen ( Beihang University)
2. Transcoding-Enabled Edge Caching and Delivery for Tile-Based Adaptive 360-Degree Video Streaming
     Qiaoyu Lu (Shanghai Jiao Tong University)*;
     Chenglin Li (Shanghai Jiao Tong University);
     Junni Zou (Shanghai Jiao Tong University);
     Kexin Tang (Shanghai Jiao Tong University);
     Qi Wang (Shanghai Jiao Tong University);
     Hongkai Xiong (Shanghai Jiao Tong University)
3. An Optimal Coverage Model for the Deployment of IoT Devices in Feature-based Video Transmission Systems
     Yuqin Wang (Chinese Academy of Sciences)*;
     Jingce Xu (Institute of Computing Technology Chinese Academy of Sciences);
     Wen Ji (Institute of Computing Technology, Chinese Academy of Sciences)
4. A QoE-oriented Saliency-aware Approach for 360-degree Video Transmission
     Wang Shen (Shanghai Jiao Tong University)*;
     Lianghui Ding (Shanghai Jiao Tong University);
     Guangtao Zhai (Shanghai Jiao Tong University);
     Ying Cui (Shanghai Jiao Tong University);
     Zhiyong Gao (Shanghai Jiao Tong University)
5. Multiuser Video Streaming Rate Adaptation: A Physical Layer Resource-Aware Deep Reinforcement Learning Approach
     Kexin Tang (Shanghai Jiao Tong University)*;
     Nuowen Kan (Shanghai Jiao Tong University);
     Junni Zou (Shanghai Jiao Tong University);
     Xiao Fu (Oregon State University);
     Mingyi Hong (University of Minnesota);
     Hongkai Xiong (Shanghai Jiao Tong University)
6. An Improved QoE Evaluation Model for HTTP Adaptive Streaming
     Zaixin Yang (Shanghai Jiao Tong University);
     Tiantian He (Shanghai Jiao Tong University);
     Li Song (Shanghai Jiao Tong University)*;
     Rong Xie (Shanghai Jiao Tong University);
     Xiao Gu (Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University)
7. Weakly Supervised Learning for Blind Image Quality Assessment
     Weiquan He (Xidian University)*;
     Xinb Gao (Xidian University);
     Wen Lu (Xidian University);
     Ruoxuan Guan (Xidian University)
8. Blind Panoramic Image Quality Assessment via the Asymmetric Mechanism of Human Brain
     Yumeng Xia (School of Communication and information Engineering, Shanghai University);
     yongfang wang (School of Communication and information Engineering, Shanghai University)*;
     Peng Ye (School of Communication and information Engineering, Shanghai University)
9. Deep Quad Path Quality Evaluator Combined Aesthetic Estimation for Multi-Exposure Image Fusion
     Ruoxuan Guan (Xidian University)*;
     Wen Lu (Xidian University);
     Weiquan He (Xidian University);
     Furui Bai (Xidian University)
10. Protection and Hiding Algorithm of QR Code Based on Multi-channel Visual Masking
     Jiahe Zhang (Shanghai Jiao Tong University)*;
     Duo Li (Shanghai Jiao Tong University);
     Jun Jia (Shanghai Jiao Tong University);
     Wenjie Sun (Shanghai Jiao Tong University);
     Guangtao Zhai (Shanghai Jiao Tong University)
11. A novel approach to image steganography based on the image colorization
     Kazunori Uruma (Kogakuin University)*;
     Katsumi Konishi (Hosei University);
     Tomohiro Takahashi (Tokai University);
     Toshihiro Furukawa (Tokyo University of Science)
12. Progressive Semantic Image Synthesis via Generative Adversarial Network
     Ke Yue (Beijing Jiaotong University)*;
     Yidong Li (Beijing Jiaotong Univeristy, China);
     Huifang Li ( Beijing Jiaotong University)
13. Occlusion Deep Alignment Network
     Yang Li (School of Information and Communication Engineering, University of Electronic Science and Technology of China);
     Chang Shu (School of Information and Communication Engineering, University of Electronic Science and Technology of China)*;
     Ning Zhou (School of Information and Communication Engineering, University of Electronic Science and Technology of China);
     Jianyu Hong (School of Information and Communication Engineering, University of Electronic Science and Technology of China);
     Xiaofeng Li (University of Electronic Science and Technology of China)
14. Deep tone mapping network in HSV color space
     Ning Zhang (Peking University)*;
     Chao Wang (Peking University);
     Yang Zhao (Hefei University of Technology);
     Ronggang Wang (Peking University)
15. Multi-path Convolutional Neural Network based on Rectangular Kernel with Path Signature Features for Gesture Recognition
     Lufan Liao (South China University of Technology);
     Xin Zhang (South China University of Technology)*;
     Chenyang Li (South China University of Technology)
16. Advertisement Logo Compositing via Adversarial Geometric Consistency Pursuit
     Xiang Li (Shanghai University);
     Guowei Teng (Shanghai University)*;
     Ping An (Shanghai University);
     Haiyan Yao (Shanghai University);
     Yilei Chen (Shanghai University)
17. A Dataset and Evaluation Framework for Deep Learning Based Video Stabilization Systems
     Maria Silvia Ito (Queen Mary University of London UK)*;
     Ebroul Izquierdo (Queen Mary University of London)
18. Importance-Aware Filter Selection for Convolutional Neural Network Acceleration
     Zikun Liu (University of Science and Technology of China)*;
     Zhen Chen (City University of Hong Kong);
     Weiping Li (University of Science and Technology of China)
19. Unpaired Image-to-Sketch Translation Network for Sketch Synthesis
     Yue Zhang (Beijing University of Posts and Telecommunications)*;
     Guoyao Su (Beijing University of Posts and Telecommunications);
     Yonggang Qi (Beijing University of Posts and Telecommunications);
     Jie Yang (BUPT)
20. Learning a Reliable Decision Making Policy for Robust Tracking
     Xiaofeng Huang (Hangzhou Dianzi University);
     Kanghao Wang (Hangzhou Dianzi University);
     Haibing Yin* (Hangzhou Dianzi University);
     Shengsheng Zheng (Hangzhou Dianzi University);
     Xiang Meng (Hangzhou Dianzi University);
     Shengping Zhang (Harbin Institute of Technology)
21. Multi-view Rank Pooling for 3D Object Recognition
     Chaoda Zheng (South Chine University of Technology);
     Yong Xu (South China University of Technology)*;
     Ruotao Xu (South China University of Technology);
     Hongyu Chi (South China University of Technology);
     Yuhui Quan (South China University of Technology)
22. Feature Map Alignment: Towards Efficient Design of Mixed-precision Quantization Scheme
     Yukun Bao (Shanghai Jiaotong University)*;
     Yuhui Xu (Shanghai Jiao Tong University);
     Hongkai Xiong (Shanghai Jiao Tong University)
23. CodedRetrieval: Joint image compression and retrieval with neural networks
     Linfeng Liu (Nanjing University);
     Haojie Liu (Nanjing University);
     Tong Chen (Nanjing University);
     Qiu Shen (Nanjing University);
     Zhan Ma (Nanjing University)*
24. Improving Action Recognition with the Graph-Neural-Network-based Interaction Reasoning
     Wu Luo (Shanghai Jiao Tong University);
     Chongyang Zhang (Shanghai Jiao Tong University)*;
     Xiaoyun Zhang (Shanghai Jiao Tong University);
     Haiyan Wu (Railway Police College)
25. Low Resolution Recognition of Aerial Images
     Raghunath Puttagunta (University of Missouri, Kansas City)*;
     Renlong Hang (University of Missouri-Kansas City);
     Zhu Li (University of Missouri-Kansas City);
     Shuvra Bhattacharyya (University of Maryland)
26. Feature-based Patch Matching for Moving Object Detection
     Mosin Russell (Western Sydney University)*;
     Ju Jia Zou (Western Sydney University);
     Gu Fang (Western Sydney University);
     Weidong Cai (University of Sydney)

Time TBC - Welcome Reception


Tuesday, 3 December

09:00-10:00 Keynote 3 - Title Jianbo Shi
Professor of GRASP Laboratory, University of Pennsylvania, United States
Session Chair: TBA, affiliation

10:00-10:30 Coffee Break

10:30-12:30 Oral Session 5 – Multimedia Analysis, Representation & Understanding III Session Chair: TBA, affiliation 1. Enhanced Semantic Features via Attention for Real-Time Visual Tracking
     Mingjin Geng (Beijing University of Posts and Telecommunications )*;
     Haiying Wang (Beijing University of Posts and Telecommunications);
     Yingsen Zeng (Beijing University of Posts and Telecommunications)
2. Improving Small-Scale Pedestrian Detection Using Informed Context
     Zexiang Liu (Shanghai Jiao Tong University);
     Chongyang Zhang (Shanghai Jiao Tong University)*;
     Yan Luo (Shanghai Jiao Tong University);
     Kai Chen (sjtu);
     Qiping Zhou (State Grid Jiangxi Power Co.Ltd);
     Yunyu Lai (State Grid Jiangxi Power Co.Ltd)
3. Enhanced Initialization with Multi-Stage Learning for Robust Visual Tracking
     Jin Feng (Beijing University of Posts and Telecommunications)*;
     Shi Pu (Beijing University of Posts and Telecommunications);
     Kaili Zhao (Beijing University of Posts and Telecommunications);
     Honggang Zhang (Beijing University of Posts and Telecommunications);
     Tianming Du (Beijing University of Posts and Telecommunications)
4. DSAN: Double Supervised Network with Attention Mechanism for Scene Text Recognition
     Yuting Gao (Shanghai Jiao Tong University)*;
     Zheng Huang (Shanghai Jiao Tong University);
     Yuchen Dai (Shanghai Jiao Tong University);
     Cheng Xu (Shanghai Jiao Tong University);
     Kai Chen (sjtu);
     Jie Guo (Shanghai Jiao Tong University)
5. Hybrid Regularization with Elastic Net and Linear Discriminant Analysis for Zero-Shot Image Recognition
     Zhen Qin (Beijing University of Posts and Telecommunications);
     Yan Li (Beijing Institute of Technology)*
6. RSNet:A Compact Relative Squeezing Net for Image Recognition
     Qi Zhao (Beihang University);
     Nauman Raoof (Beihang University);
     Shuchang LYU (Sensetime)*;
     Boxue Zhang (Beihang University);
     Wenquan Feng (Beihang University)

10:30-12:30 Oral Session 6 – Segmentation Session Chair: TBA, affiliation 1. Learn Image Object Co-segmentation with Multi-scale Feature Fusion
     Lina Li (University of Technology,Sydney);
     Zhi Liu (Shanghai University)*;
     Jian Zhang (UTS);
     Xiaofei Zhou (Hangzhou Dianzi University)
2. Semantic Segmentation via Domain Adaptation with Global Structure Embedding
     Tianyi Zhang (Nanyang Technological University)*;
     Guosheng Lin (Nanyang Technological University);
     Jianfei Cai (Nanyang Technological University);
     Alex Kot (Nanyang Technological University)
3. A Coarse-to-fine Cascading Model for Cataract Nuclear Segmentation in Slit-lamp Photographs
     Jun Wu (Northwestern Polytechnical University)*;
     Zongjiang Shang (Northwestern Polytechnical University);
     Kaiwei Wang (Northwestern Polytechnical University);
     XiXi He (Visionary Intelligence Ltd.);
     Xiangjia Zhu (Eye and ENT Hospital of Fudan University);
     Wenwen He (Eye and ENT Hospital of Fudan University);
     Yi Lu (Eye and ENT Hospital of Fudan University);
     Keke Zhang (Eye and ENT Hospital of Fudan University);
     Yinglei Zhang (Eye and ENT Hospital of Fudan University);
     Xianfang Rong (Eye and ENT Hospital of Fudan University);
     Zhennan Zhao (Eye and ENT Hospital of Fudan University);
     Lei Cai (Eye and ENT Hospital of Fudan University);
     Dayong Ding (Vistel Inc.);
     Xirong Li (Renmin University of China)
4. Task-in-all Domain Adaptation for Semantic Segmentation
     Tianyi Zhang (Nanyang Technological University)*;
     Jingyi Yang (Nanyang Technological University);
     Chuanxia Zheng (Nanyang Technological University);
     Guosheng Lin (Nanyang Technological University);
     Jianfei Cai (Nanyang Technological University);
     Alex Kot (Nanyang Technological University)
5. PPML: Metric Learning with Prior Probability for Video Object Segmentation
     Hangshi Zhong (University of Science and Technology of China);
     Zhentao Tan (University of Science and Technology of China);
     Bin Liu (University of Science and Technology of China)*;
     Weihai Li (University of Science and Technology of China);
     Nenghai Yu (University of Science and Technology of China)
6. A New Few-shot Segmentation Network Based on Class Representation
     Yuwei Yang (University Of Electronic Science And Technology Of China);
     Fanman Meng (University of Electronic Science and Technology of China)*;
     Hongliang Li (University of Electronic Science and Technology of China);
     King N. Ngan (CUHK, UESTC);
     Qingbo Wu (University of Electronic Science and Technology of China)

12:30-13:30 Lunch

13:30-15:30 Oral Session 7 – Coding I Session Chair: TBA, affiliation 1. Edge-Detection Based Fast Intramode Selection for Depth Map Coding in 3D-HEVC
     Ruyi Zhang (Beijing University of Technology)*;
     Kebin Jia (Beijing University of Technology);
     Pengyu Liu (Beijing University of Technology);
     Zhonghua Sun (Beijing University of Technology)
2. Dual-Streams Global Guided Learning for High Dynamic Range Image Reconstruction
     Junjie Lian (Shanghai University);
     Yongfang Wang (Shanghai University)*;
     Chuang Wang (Shanghai University)
3. Color Image Compression with Transform Domain Down-Sampling and Deep Convolutional Reconstruction Yan Wang (UESTC);
     Shuyuan Zhu (University of Electronic Science and Technology of China)*;
     Xiandong Meng (Hong Kong University of Science and Technology);
     Bing Zeng (University of Electronic Science and Technology of China);
     Yuanfang Guo (Beihang University);
     Ruiqin Xiong (Peking University)
4. Spherical Video Coding with Motion Vector Modulation to Account for Camera Motion
     Bharath Vishwanath (UCSB)*;
      Kenneth Rose (UCSB)
5. Extreme Image Coding via Multiscale Autoencoders with Generative Adversarial Optimization
     Chao Huang (Nanjing University)*;
     Haojie Liu (Nanjing University);
     Tong Chen (Nanjing University);
     Qiu Shen (Nanjing University);
     Zhan Ma (Nanjing University)
6. Image segmentation based graph-cut approach to fast color image coding via graph Fourier transform
     Kaito Abiko (Tokyo University of Science)*;
     Kazunori Uruma (Kogakuin University);
     Mamoru Sugawara (Tokyo Univercity of Science);
     Seiichirou Hangai (Tokyo University of Science);
     Takayuki Hamamoto (Tokyo University of Science)

13:30-15:30 Oral Session 8 – Stereo and Multi-View Session Chair: TBA, affiliation 1. DVONet: Unsupervised Monocular Depth Estimation and Visual Odometry
     Xiangyu Li (Tianjin University)*;
     Yonghong Hou (Tianjin University);
     Qi Wu (Tianjin University);
     Pichao Wang (Alibaba Group (U.S.) Inc.);
     Wanqing Li (University of Wollongong)
2. Image-Based End-to-End Neural Network for Dense Disparity Estimation
     Shuqiao Sun (BUAA)*;
     Rongke Liu (Beihang University);
     Qiuchen Du (BUAA);
     Shantong Sun (Beihang University);
     Shaoli Kang (Beihang University)
3. Depth Estimation with Multi-Resolution Stereo Matching
     Qiuchen Du (Beihang University)*;
     Rongke Liu (Beihang University);
     Yu Pan (Beihang University);
     Shantong Sun (Beihang University);
     Shuqiao Sun (Beihang University);
     Zheng Zheng (Beihang University)
4. Frequency Descriptor based Light Field Depth Estimation
     Junke Li (Tsinghua University);
     Xin Jin (Tsinghua University)*
5. Modified Baseline for Light Field Stitching
     Yilei Chen (Shanghai University);
     Ping An (Shanghai University)*;
     Xinpeng Huang (Shanghai University);
     Chunli Meng (Shanghai University);
     Qiang Wu (University of Technology Sydney)
6. Light Field Reconstruction Based on Compressed Sensing via Deep Learning
     Linhui Wei (Beijing University of Posts and Telecommunications)*;
     Yu Liu (Beijing University of Posts and Telecommunications);
     Yumei Wang (Beijing University of Posts and Telecommunications)

15:30-16:00 Coffee Break

16:00-17:30 Poster Session 2 Session Chair: TBA, affiliation 1. Asymmetric supervised deep autoencoder for depth image based 3D model retrieval
     Ayesha Siddiqua (Oklahoma State University)*;
     Guoliang Fan (Oklahoma State University)
2. LF-TSP: Traveling salesman problem for HEVC-based light-field coding
     Kota Imaeda (Nagoya University)*;
     Kohei Isechi (Nagoya University);
     Keita Takahashi (Nagoya University);
     Toshiaki Fujii (Nagoya University);
     Yukihiro Bandoh (Nippon Telegraph and Telephone Corporation);
     Takehito Miyazawa (Nippon Telegraph and Telephone Corporation);
     Seishi Takamura (Nippon Telegraph and Telephone Corporation);
     Atsushi Shimizu (Nippon Telegraph and Telephone Corporation)
3. Deep Learning Based In-Loop Filter for Video Coding
     Yue Yu (Fuzhou University);
     Xiuzhi Yang (Fuzhou University);
     Jian Chen (Fuzhou University)*;
     Bo Huang (Fuzhou University);
     JunYi Wu (Fuzhou University)
4. Adaptive CU Split Decision with Pooling-variable CNN for VVC Intra Encoding
     genwei tang (Fudan University)*;
     Ming'e Jing (Fudan University);
     Xiaoyang Zeng (Fudan University );
     Yibo Fan (Fudan University)
5. Bit Allocation based on Visual Saliency in HEVC
     ChungWen Ku (Peking university)*;
     Guoqing Xiang (Peking university);
     Feng Qi (Institute of Computing Technology of the Chinese Academy of Sciences);
     Wei Yan (Peking university);
     Yuan Li (Peking University);
     Xiaodong Xie (Peking University)
6. CR-U-Net: Cascaded U-Net with Residual Mapping for Liver Segmentation in CT Images
     Yiwei Liu (Beijing University of Technology)*;
     Na Qi (Beijing University of Technology);
     Qing Zhu (Beijing University of Technology);
     Weiran Li (Beijing University of Technology)
7. Morphology Reconstruction of Obstructed Coronary Artery in Angiographic Images
      Tianming Du (Beijing University of Posts and Telecommunications)*;
      Xiaotong Shi (Beijing University of Posts and Telecommunications);
      Ruijia Wu (Beijing University of Posts and Telecommunication);
      Honggang Zhang (Beijing University of Posts and Telecommunications);
      Xiaolin Song (Beijing University of Posts and Telecommunications);
      Jin Feng (Beijing University of Posts and Telecommunications);
      Fuzhuo Sun (Beijing Normal University)
8. Scale-Informed Density Estimation for Dense Crowd Counting
     Zirui Li (Peking University);
     Yuexian Zou (Peking University)*;
     Guoshuai Wang (Peking University);
     Jian Zhang (UTS)
9. Distribution Context Aware Loss for Person Re-identification
     Zhigang Chang (Shanghai Jiao Tong University);
     Qin Zhou (Alibaba Group);
     Mingyang Yu (Shanghai Jiao Tong University);
     Shibao Zheng (Shanghai Jiao Tong University)*;
     Hua Yang (Shanghai Jiao Tong University);
     Tai-Pang Wu (Suzhou 1000Viseo Technology Co. Limited)
10. Corner-Line-Prediction based Water-tank Detection and Localization
     Haoning Chen (Shanghai Jiao Tong University)*;
     Chongyang Zhang (Shanghai Jiao Tong University);
     Yan Luo (Shanghai Jiao Tong University);
     Bingkun Zhao (Shanghai Jiao Tong University);
     Jiahao Bao (Shanghai Jiao Tong University)
11. Stereoscopic Video Quality Assessment Based on The Two-step-training Binocular Fusion Network
     Shuai Ma (Tianjin University)*;
     Sumei Li (Tianjin University);
     Jianwei Xue (School of Electrical and Information Engineering, Tianjin University);
     Yixiu Ding (Tianjin University);
     Guanghui Yue (Shenzhen University)
12. Online Manhattan Keyframe-based Dense Reconstruction from Indoor Depth Sequences
     Mahdi Yazdanpour (Oklahoma State University)*;
     Guoliang Fan (Oklahoma State University);
     Weihua Sheng (Oklahoma State University)
13. A Statistical Model for Disocclusions in Depth-based Novel View Synthesis
     Jayant Thatte (Stanford University)*;
     Bernd Girod (Stanford University)
14. Stereoscopic Image Quality Assessment Weighted Guidance by Disparity Map Using Convolutional Neural Network
     Yixiu Ding (Tianjin University)*;
     Sumei Li (Tianjin University);
     Yongli Chang (Tianjin University)
15. Efficient Dual Attention Module for Real-Time Visual Tracking Yingsen Zeng (Beijing University of Posts and Telecommunications)*;
     Xiaoqiang Guo (Academy of Broadcasting Science, SAPPRET);
     Haiying Wang (Beijing University of Posts and Telecommunications);
     Mingjin Geng (Beijing University of Posts and Telecommunications );
     Ting Lu (Beijing University of Posts and Telecommunications )
16. Improving Person Search by Adaptive Feature Pyramid-based Multi-Scale Matching
     Binbin Song (University of Electronic Science and Technology of China);
     Xue Zhou (University of Electronic Science and Technology of China)*;
     Wei Xiang (University of Electronic Science and Technology of China);
     Hao Wen (CloudWalk Technology)
17. Weather Data Integrated Mask R-CNN for Automatic Road Surface Condition Monitoring
     Junyong You (Norwegian Research Centre)*
18. RGB-thermal Imaging System Collaborated with Marker Tracking for Remote Breathing Rate Measurement
     Lushuang Chen (Shanghai Jiao Tong University)*;
     Ning Liu (Shanghai Jiao Tong University);
     Menghan Hu (East China Normal University);
     Guangtao Zhai (Shanghai Jiao Tong University)
19. A Progressive Network Based on Residual Multi-scale Aggregation for Image Super-Resolution
     Anqi Liu (Tianjin University);
     Sumei Li (Tianjin University)*;
     Sheng Chen (Tianjin University)
20. 3D Human Skeleton Data Compression for Action Recognition
     Sheng Li (Peking University);
     Tingting Jiang (Peking University)*;
     Yonghong Tian (PKU);
     Tiejun Huang (Peking University)
21. Deep Feature Guided Image Retargeting
     Jinan Wu (Shanghai Jiaotong University);
     Rong Xie (Shanghai Jiao Tong University);
     Li Song (Shanghai Jiao Tong University)*;
     Bo Liu (La Trobe University)
22. Parallax-tolerant 360 Live Video Stitcher
     Miko Atokari (Tampere University);
     Marko Viitanen (Tampere University);
     Alexandre MERCAT (Tampere University)*;
     Emil Kattainen (Tampere University);
     Jarno Vanne (Tampere University)
23. Finding Salient Context based on Semantic Matching for Relevance Ranking
     Qi Yuanyuan (Beijing University of Posts and Telecommunications)*;
     Jiayue Zhangjia (Beijing University of Technology);
     Weiran Xu (Beijng University of Posts and Telecommunications);
     Jun Guo (Beijing University of Posts and Telecommunications);
     Yan Li (Beijing Institute of Technology)
24. Pose Recognition for Dense Vehicles under Complex Street Scenario
     Zhenjia Fan (Fuzhou University)*;
     Zhifeng Chen (Fuzhou University);
     JunYi Wu (Fuzhou University);
     Chenhao Pei (Fuzhou University)
25. No-Reference Stereoscopic Image Quality Assessment Based On Shuffle-Convolutional Neural Network
     Sumei Li (Tianjin University)*;
     Mingyi Wang (Tianjin University);
     Chunping Hou (Tianjin University)
26. FR-IQA - Permutation Entropy Deviation Index
     Mohtashim Baqar (Sunway University)*;
     Sian Lun Lau (Sunway University);
     Mansoor Ebrahim (Iqra University)
27. Learning to predict where people with VIMS look
     Jiawei Yang (Shanghai Jiao Tong University)*;
     Guangtao Zhai (Shanghai Jiao Tong University);
     Huiyu Duan (Shanghai Jiao Tong University)
28. Convolutional Neural Network Based Up-Sampling for Depth Video Intra Coding
     Jianjun Lei (Tianjin University)*;
     Liu Xiaohuan (Tianjin University);
     Kaiming Zhang (Tianjin University);
     Ge Li (Tianjin University);
     Nam Ling (Department of Computer Engineering Santa Clara University)
29. Quality Assessment for Omnidirectional Video with Consideration of Temporal Distortion Variations
     Pengwei Zhang (Nanjing University of Aeronautics and Astronautics)*;
     Pan Gao (Nanjing University of Aeronautics and Astronautics)
30. Frequency Domain Analysis based exploitation of color-difference and residual interpolation for Color Image Demosaicking
     Sunil Jaiswal (K-Lens)*; Vinit Jakhetiya (IIT JAMMU);
     Ke Gu (Beijing University of Technology);
     Sharath Chandra Guntuku (University of Pennsylvania);
     Ashutosh Singla (TU Ilmenau)
31. Multi-view high dynamic range reconstruction via gain estimation
     Firas Abedi (Huazhong University of Science and Technology)*;
     Qiong Liu (Huazhong University of Science and Technology);
     You Yang (Huazhong University of Science and Technology)
32. Light Field Images Compression Based on Graph Convolution Networks
     Jingming Shan (Beijing University of Posts and Telecommunications)*;
     Yu Liu (Beijing University of Posts and Telecommunications);
     Yumei Wang (Beijing University of Posts and Telecommunications)
33. Macropixel-constrained Collocated Position Search for Plenoptic Video Coding
     Lingjun LI (Tsinghua University);
     Xin Jin (Tsinghua University)*
34. An Improved Gaussian Mixture Model Based Hole Filling Algorithm Exploiting Depth Information
     Tiantian Zhu (Nanjing University of Aeronautics and Astronautics)*;
     Pan Gao (Nanjing University of Aeronautics and Astronautics)
35. Stereo Image Quality Assessment Based on Sparse Binocular Fusion Convolution Neural Network
     Sumei Li (Tianjin University);
     Xu Han (Tianjin University)*;
     Muhammad Zubair (Tianjin University);
     Shuai Ma (Tianjin University)
36. Det2Seg: A Two-Stage Approach for Road Object Segmentation from 3D Point Clouds
     Chen Zuo (Shanghai Jiao Tong University)*;
     Wei Zhang (Noah's Ark Lab, Huawei Inc.);
     Lingxi Xie (Huawei Noah's Ark Lab);
     Qi Tian (Huawei Noah’s Ark Lab);
     Hongkai Xiong (Shanghai Jiao Tong University)
37. Enhanced Intra Prediction Scheme in Point Cloud Attribute Compression
     Honglian Wei (Peking University Shenzhen Graduate School);
     Yiting Shao (Peking University Shenzhen Graduate School);
     Jing Wang (Artificial Intelligence Research Center Peng Cheng Laboratory);
     Shan Liu (Tencent America);
     Ge Li (SECE, Shenzhen Graduate School, Peking University)*
38. Intra-Frame Compression of Point Cloud Geometry using Boolean Decomposition
     Rodrigo Rosário (Universidade de Brasília);
     Eduardo Peixoto (Universidade de Brasília)*
39. Multi-heads Attention Graph Convolutional Networks for Skeleton-Based Action Recognition
     Guowei Zhang (South China University Of Technology);
     Xin Zhang (South China University of Technology)*
40. A Spatio-temporal Hybrid Network for Action Recognition
     Song Li (Beijing University of Posts and Telecommunications);
     Zhicheng Zhao (Beijing University of Posts and Telecommunications)*;
     Fei Su (Beijing University of Posts and Telecommunications)
41. A Framework for Real-Time Face-Recognition
     Samadhi Wickrama Arachchilage (Queen Mary University of London)*;
     Ebroul Izquierdo (Queen Mary University of London)
42. Facial Attention based Convolutional Neural Network for 2D+3D Facial Expression Recognition
     Yang Jiao (Xidian University)*;
     Yi Niu (Xidian University);
     Yuting Zhang (Xidian university);
     Fu Li (Xidian University); chunbo zou (Xi'an Institute of Optics and precision Mechanics);
     Guangming Shi (Xidian University)
43. Comparative Convolutional Neural Network for Younger Face Identification
     Liangliang Wang (Nanyang Technological University);
     Deepu Rajan (Nanyang Technological University)*

Time TBC - Conference Banquet


Wednesday, 4 December

09:00-10:00 Keynote 3 - Title Ramesh Jain
Director of Institute for Future Health, University of California, United States
Session Chair: TBA, affiliation

10:00-10:30 Coffee Break

10:30-12:30 Oral Session 9 – Coding II Session Chair: TBA, affiliation
1. Water-Bottom Video Coding Based on Coding-Oriented Reference Frame Generation
     Seishi Takamura (NTT)*;
     Atsushi Shimizu (Nippon Telegraph and Telephone Corporation)
2. Prediction Refinement with Optical Flow for Affine Motion Compensation
     Jiancong Luo (Alibaba)*;
     Yuwen He (InterDigital Communications);
     Wei Chen (InterDigital Communications)
3. Reference Picture Synthesis for Video Sequences Captured with a Monocular Moving Camera
Hossein Bakhshi Golestani (RWTH Aachen University)*;
     Christian Rohlfing (RWTH Aachen University, Germany);
     Jens-Rainer Ohm (RWTH Aachen University)
4. Fast Variance- and Gradient-based QTMT Partition Decision Algorithm in VVC Intra Coding
     Junan Chen (Fudan University);
     Heming Sun (Waseda University, Japan)*;
     Jiro Katto (Waseda University);
     Xiaoyang Zeng (Fudan University );
     Yibo Fan (Fudan University)
5. SSIM Prediction for H.265/HEVC based on Convolutional Neural Networks
     Sihan Wang (Wuhan University);
     Yingxue Zhang (Wuhan University);
     Daiqin Yang (Wuhan University);
     Zhenzhong Chen (Wuhan University)*
6. A Progressive Background Updating Based Coding Scheme for Surveillance Videos
     Meng Li (Beijing University of Technology);
     Yunhui Shi (Beijing University of Technology);
     Wenpeng Ding (Baidu);
     XIaojie Liu (Beijing University of Technology);
     Jiaying Liu (Peking University)*;
     Baocai Yin (Dalian University of Technology)

10:30-12:30 Oral Session 10 – Deep Learning II Session Chair: TBA, affiliation 1. Local Convex Representation with Pruning for Manifold Clustering
     Tao Yang (Beijing University of Posts & Telecommunications);
     Chun-Guang Li (Beijing University of Posts & Telecommunications)*
2. Identifying and Pruning Redundant Structures for Deep Neural Networks
     Wenyao Gan (Shanghai Jiao Tong University);
     Li Song (Shanghai Jiao Tong University)*;
     Li Chen (Shanghai Jiao Tong University);
     Rong Xie (Shanghai Jiao Tong University);
     Xiao Gu (Shanghai Jiao Tong University)
3. Depthwise Separable Convolutional Neural Network for Image Forensics
     Yifang Chen (Sun Yat-sen university);
     Feng Peng ( Sun Yat-sen university );
     Xiangui Kang (Sun Yat-Sen University)*;
     Z. Jane Wang (University of British Columbia)
4. A Multiple Triplet-Ranking Model for Fine-Grained Sketch-based Image Retrieval
     Jingyi Xue (Beijing University of Posts and Telecommunications)*;
     Yun Zhou (Academy of Broadcasting Science);
     Zhuqing Jiang (Beijing University of Posts and Telecommunications);
     Yao Xie (Beijing University of Posts and Telecommunications);
     XiaoYu Li (Academy of Broadcasting Science)
5. Adaptive Fusion of RGBD Data for two-stream FCN-based Level Set Tracking
     Jie Yang (University of Electronic Science and Technology of China);
     Xue Zhou (University of Electronic Science and Technology of China)*;
     Zheng Zhou (University of Electronic Science and Technology of China);
     Hao Wen (CloudWalk Technology)
6. Decomposed-Excitatory Antagonistic Model for Reliable Retinal Vessel Detection
     Mohsin Challoob (Griffith University)*;
     Yongsheng Gao (Griffith University, Australia)

12:30-13:30 Lunch

13:30-15:00 Oral Session 11 – Person Re-Identification and Tracking Session Chair: TBA, affiliation 1. Saliency-based Deep Multi-level Semantic Feature Fusion for Person Re-identification
     Yinhao Wang (Beijing University of Posts and Telecommunications)*;
     Chenggang Li (Beijing University of Posts and Telecommunications);
     Qingwen Hu (Beijing University of Posts and Telecommunications);
     Zhicheng Zhao (bupt);
     Fei Su (Beijing University of Posts and Telecommunications)
2. Attentional Part-based Network for Person Re-identification
     Yinsong xu (Beijing University of Posts and Telecommunications )*;
     zhuqing jiang (Beijing University of Posts and Telecommunications);
     aidong men (Beijing University of Posts and Telecommunications);
     Jiangbo Pei (Beijing University of Posts and Telecommunications);
     Guodong Ju (GuangDong TUS-TuWei Technology Co.,Ltd);
     Bo Yang (Beijing University of Posts and Telecommunications)
3. Improving Person Re-Identification Performance Using Body Mask Via Cross-Learning Strategy
     JunYi Wu (Fuzhou University)*;
     Lingxiang Yao ( University of Technology Sydney);
     Yan Huang (University of Technology Sydney);
     JingSong Xu (University of Technology Sydney );
     Qiang Wu (University of Technology Sydney);
     Liqin Huang (Fuzhou University)
4. Real-Time Multi-Target Multi-Camera Tracking with Spatial-Temporal Information
     Xindi Zhang (Queen Mary University of London)*;
     Ebroul Izquierdo (Queen Mary University of London)

13:30-15:00 Oral Session 12 – SS for GC Session Chair: TBA, affiliation 1. Vehicle Re-Identification: Logistic Triplet Embedding Regularized by Label Smoothing
     Chenggang Li (Beijing University of Posts and Telecommunications)*;
     Yinhao Wang (Beijing University of Posts and Telecommunications);
     Zhicheng Zhao (bupt);
     Fei Su (Beijing University of Posts and Telecommunications)
2. Global and Local Deep Feature Representation Fusion for Vehicle Re-Identification
     Xing Zhao Lee (Pensees Pte Ltd)*;
     Hao Wang (Pensees Pte Ltd);
     Jiangtao Kong (Pensees Pte Ltd);
     Chi Su (Kingsoft Cloud);
     Junliang Xing (Institute of Automation, Chinese Academy of Sciences);
     Shengmei Shen (Pensees AI institute of Singapore)
3. Stronger Baseline for Vehicle Re-Identification in the Wild
     Chih-Chung Hsu (Department of Management Information Systems, National Pingtung University of Science and Technology)*;
     Cing-Hao Hung (Department of Management Information Systems, National Pingtung University of Science and Technology );
     Chih-Yu Jian (Department of Management Information Systems, National Pingtung University of Science and Technology );
     Yi-Xiu Zhuang (Department of Management Information Systems, National Pingtung University of Science and Technology )

15:00-15:30 Coffee Break

15:30 -17:30 Industry Forum Session Chair: TBA, affiliation

17:30-18:00 Closing Ceremony Session Chair: TBA, affiliation

2019 IEEE International Conference on Visual Communications and Image Processing (VCIP)

http://www.vcip2019.org