Detailed Program



Sunday, December 10, 2017

09:00 - 12:00 (Sunday, December 10, 2017)
Tutorial 1: Point cloud coding: techniques, applications and standardization 
Dr. Rufael Mekuria, Unified Streaming and Point Cloud Compression, Netherlands
Location: St. Petersburg ballroom 2 

09:00 - 12:00 (Sunday, December 10, 2017)
Tutorial 2: Deep Learning in Image Processing 
Prof. Seon Joo Kim, Yonsei University, Korea 
Location: St. Petersburg ballroom 3

14:00 - 17:00 (Sunday, December 10, 2017)
Tutorial 3: An Overview of Omnidirectional MediA Format (OMAF) 
Dr. Ye-Kui Wang Qualcomm, USA 
Location: St. Petersburg ballroom 2 



Monday, December 11, 2017

08:30 - 09:00
Opening ceremony
Location: St. Petersburg ballroom 1 
Session chair: TBA

09:00 - 10:00 (Monday, December 11, 2017)
Keynote: Tittle TBA, Prof. Shih Fu Chang, Columbia University, USA
Location: St. Petersburg ballroom 1 
Session Chair: TBA

10:00 - 10:30
Coffee break

10:30 - 12:30 (Monday, December 11, 2017)
Oral session 1
Special Session: VR Video Coding and Transmission
Location: Petersburg ballroom 2
Session Chair: TBA
  1. Stacked Omnistereo for Virtual Reality with Six Degrees of Freedom — Jayant Thatte, Stanford University; Trisha Lian, Stanford University; Brian Wandell, Stanford University; Bernd Girod, Stanford University
  2. An Optimal Spatial-temporal Smoothness Approach for Tile-based 360-degree Video Streaming — Yixuan Ban, Peking University; Lan Xie; Zhimin Xu, Peking University; Xinggong Zhang; Zongming Guo
  3. Coding Optimization based on Weighted-to-Spherically-Uniform Quality Metric for 360 Video— Yule Sun, Zhejiang University; Lu Yu, Zhejiang University
  4. Standardization Status of 360 Degree Video Coding and Delivery— Robert Skupin, Fraunhofer HHI; Yago Sanchez, Fraunhofer HHI; Ye-Kui Wang, Qualcomm Inc.; Miska Hannuksela, Nokia; Jill Boyce; Mathias Wien, RWTH Aachen University
  5. Motion Compensated Prediction with Geometry Padding for 360 Video Coding — Yuwen He, InterDigital Communications; Yan Ye; Philippe Hanhart; Xiaoyu Xiu, InterDigital
  6. An Evaluation Framework for 360-degree Video Compression — Xiaoyu Xiu, InterDigital; Yuwen He, InterDigital Communications; Yan Ye; Bharath Vishwanath

10:30 - 12:30 (Monday, December 11, 2017)
Oral session 2
Machine Learning for Visual Information Processing I
Location: Petersburg ballroom 3
Session Chair: TBA
  1. Two-Stream Deep Encoder-Decoder Architecture for Fully Automatic Video Object Segmentation — Jingwei Xu, Shanghai Jiao Tong University; Li Song, Shanghai Jiao Tong University; Rong Xie
  2. Supervised Hashing with Extreme Learning Machine — Tongtong Yuan, BUPT; Weihong Deng; Jiani Hu
  3. Phase-based Learning for Micro-baseline Depth Estimation — Qiuyan Tao, Zhejiang University; Lianghao Wang; Dongxiao Li; Ming Zhang
  4. Rain Removal via Residual Generation Cascading — Qiaobo Chen, Shanghai Jiao Tong University; yi Xu; Bingbing NI; zan Shen; Xiaokang Yang
  5. A New Spherical Hashing Method in a Low-Dimensional Isotropic Space — Yinhe Lan, Peking University Shenzhen Graduate School; Zhenyu Weng, Peking University Shenzhen Graduate School; Yuesheng Zhu, Peking University Shenzhen Graduate School
  6. Deep Transfer Network for Face Recognition Using 3D Synthesized Face —  An Zhanfu, Bupt; Weihong Deng; Jiani Hu

13:30 - 15:30 (Monday, December 11, 2017)
Oral session 3
Special Session: Astronomical Big Data Processing
Location: Petersburg ballroom 2
Session Chair: TBA
  1. Learning Solar Flare Forecasting Model From Magnetograms — Xin Huang, National Astronomical Observat; Huaning Wang; Long Xu, Chinese Academy of Sciences; Wenqing Sun, National Astronomical Observatories, Chinese Academy of Sciences
  2. Machine Learning for Astronomical Big Data Processing — Long Xu, Chinese Academy of Sciences; Yihua Yan, National Astronomical Observatories, Chinese Academy of Sciences
  3. Bidirectional LSTM for Ionospheric Vertical Total Electron Content (TEC) Forecasting —Wenqing Sun, National Astronomical Observatories, Chinese Academy of Sciences; Long Xu, Chinese Academy of Sciences; Xin Huang, National Astronomical Observat; Weiqiang Zhang, Shenzhen University; Tianjiao Yuan, National Space Science Center, Chinese Academy of Sciences
  4. Auto-flag the baseline for Mingantu Ultrawide  Spectral Radioheliograph with LSTM — Jun Cheng, National Astronomical Observatories, Chinese Academy of Sciences; Long Xu, Chinese Academy of Sciences; Xuexin Yu, National Astronomical Observatories, Chinese Academy of Sciences; Wei Wang, National Astronomical Observatories, Chinese Academy of Sciences; Yihua Yan, National Astronomical Observatories, Chinese Academy of Sciences
  5. Data Processing and Imaging for MingantU SpEctral Radioheliograph — Linjie Chen, National Astronomical Observatories, Chinese Academy of Sciences; Wei Wang, National Astronomical Observatories, Chinese Academy of Sciences; Yihua Yan, National Astronomical Observatories, Chinese Academy of Sciences; Long Xu, Chinese Academy of Sciences
  6. Application of Guided Filter and Support Vector Machine in Real-Time Solar Flare Detection — Fei Yuan, National Space Science Center, Chinese Academy of Sciences; Jiaben Lin, National Astronomical Observatories, Chinese Academy of Sciences; jingjing Guo; Gang Wang

13:30 - 15:30 (Monday, December 11, 2017)
Oral session 4
Image and Video Coding
Location: Petersburg ballroom 3
Session Chair: TBA
  1. ** Rate Control With Delay Constraint For Screen Content Coding — Junshi Xiao, BUPT; Bin Li; Songlin Sun, Beijing University of Posts and Telecommunications; Jizheng Xu
  2. Complexity-Driven Rate-Control for Parallel HEVC Coding — Juliette Carter, BBC R&D; Saverio Blasi; Marta Mrak, "BBC Research, UK"
  3. Multi-Class Ranking Based Most Probable Prediction Unit Selection for HEVC Encoding — Linwei ZHU, City University of Hong Kong; Sam Kwong; Yun Zhang, SIAT; Xu Wang, Shenzhen University; Shiqi Wang
  4. Multi-model Based Cross-component Linear Model Chroma Intra-prediction for Video Coding — Kai Zhang, Qualcomm Inc.; Jianle Chen, Qualcomm Inc.; Li Zhang, Qualcomm; Xiang Li, Qualcomm Inc.; Marta  Karczewicz, Qualcomm Inc.
  5. Neural Network-Based Arithmetic Coding of Intra Prediction Modes in HEVC — Rui Song; Dong Liu, USTC; Houqiang Li; Feng Wu
  6. Improved Intra Boundary Filters for HEVC — Kui Fan, Peking University; Ronggang Wang, PKUSZ; Yueming Wang, Peking University; Ge Li, Peking University; Wen Gao

15:30 - 16:00
Coffee break

16:00 - 18:00 (Monday, December 11, 2017)
Oral session 5
Special Session: Immersive Video Coding
Location: Petersburg ballroom 2
Session Chair: TBA
  1. Weight-Based Bit Allocation Scheme for VR Videos in HEVC — BiJia Li, Shanghai Jiao Tong University; Li Song, Shanghai Jiao Tong University; Rong Xie; WenJun Zhang
  2. ** SIFT-Based Adaptive Prediction Structure for Light Field Compression — Wei Zhang; Dong Liu, USTC; Zhiwei Xiong, USTC; Jizheng Xu
  3. Multiple Direct Mode for Intra Coding — Li Zhang, Qualcomm; Wei-Jung Chien, Qualcomm Technologies Inc; Jianle Chen, Qualcomm Inc.; Xin Zhao, Qualcomm Technologies Inc; Marta  Karczewicz, Qualcomm Inc.
  4. Polar Square Projection for Panoramic Video — Yueming Wang, Peking University; Ronggang Wang, PKUSZ; Zhenyu Wang, Peking University; Kui Fan, Peking University; Yufan Deng, Shenzhen China Star Optoelectronics Technology Co., Ltd., Guangdong, China; Shensian SYU, Shenzhen China Star Optoelectronics Technology Co., Ltd., Guangdong, China; Ming-Jong Jou, Shenzhen China Star Optoelectronics Technology Co., Ltd., Guangdong, China
  5. A Fast Intra Prediction Algorithm for 360-Degree Equirectangular Panoramic Video — Yingbin Wang, Wuhan University; Yiming Li, Wuhan University; Daiqin Yang, Wuhan University; Zhenzhong  Chen, WHU

16:00 - 18:00 (Monday, December 11, 2017)
Oral session 6
Multimedia Content Analysis I
Location: Petersburg ballroom 3
Session Chair: TBA
  1. Illumination Invariant Feature Based on Neighboring Radiance Ratio — Xi Zhang, Shanghai Jiao Tong University; Xiaolin Wu
  2. Learning Discriminative Supplementary Features to Attributes for Novel-Category Classification — Qiuli Liu; Zechao Li, School of Computer Science, Na; Jinhui Tang
  3. Facial Age Estimation through Self-paced Learning — Li Sun, East China Normal University
  4. Learning Multi-view Embedding in Joint Space for Bidirectional Image-Text Retrieval — Lu Ran, Peking University; Wenmin Wang, Peking University
  5. Joint Facial Landmark Detection and Action Estimation Based on Deep Probabilistic Random Forest — Jun Yu; Chang Wen Chen, The State University of New York at Buffalo
  6. ** An Aligned Bidirectional Feature Representation for Person Re-identification — Daiyin Wang, Peking University; Lei Hao, Peking University; Yuesheng Zhu, Peking University



Tuesday, December 12, 2017

09:00 - 10:00 (Tuesday, December 12, 2017)
Keynote: The New Horizon for Video Coding, Dr. Gary Sullivan, Microsoft, USA
Location: St. Petersburg ballroom 1
Session Chair: TBA

10:00 - 10:30
Coffee break

10:30 - 12:30 (Tuesday, December 12, 2017)
Oral session 7
Special Session: Transparent Media Computing
Location: Petersburg ballroom 2
Session Chair: TBA
  1. NDMP- An Emerging MPEG Standard for Network Distributed Media Processing — Ming Cheng, Shanghai Jiaotong University; Yiling Xu, SJTU; Jun Sun, SJTU; Yanfeng Wang, SJTU; Jaeyeon Song, samsung; Kyungmo  Park
  2. Perceptual Optimized Adaptive HTTP Streaming — Huaying Xue, CUC; Yuan Zhang;  Jinyao  Yan
  3. A Novel Image Compression Framework at Edges — Long Ye, CUC; Qianhan Liu; Wei Zhong; Qin Zhang
  4. TC-CCS: A Cooperative Caching Strategy in Mobile Transparent Computing System — Hong Song, Central South University; Dacheng Wang, CSU; Jianxin Wang, CSU; Wenhao Zhang, CSU
  5. QoE-Based Node Selection Strategy for Edge Computing Enabled Internet-of-Vehicles (EC-IoV) — Yang Cao, HUST; Yulong Chen, Huazhong University of Science and Technology
  6. Non-invasive Imaging Based on Speckle Pattern Estimation and Deconvolution — Zhouping Wang, Tsinghua University; Xin  Jin; Yifu Hu, Tsinghua University; Qionghai Dai, Tsinghua University

10:30 - 12:30 (Tuesday, December 12, 2017)
Oral session 8
Machine Learning for Visual Information Processing  II
Location: Petersburg ballroom 3
Session Chair: TBA
  1. Deep Probabilities for Age Estimation — Tianyue Zheng, BUPT; Weihong Deng; Jiani Hu, bupt.edu
  2. Object Localization in Weakly Labeled Data Using Regularized Attention Networks — Eu Wern Teh, University of Manitoba; Zhenyu Guo, Sengled Canada; Yang Wang
  3. Learning Biased Distance Metric with Diversity Regularizer for Person Re-identification — Lei Hao, Peking University; Daiyin Wang, Peking University; Yuesheng Zhu, Peking University
  4. Exponential Decay Sine Wave Learning Rate for Fast Deep Neural Network Training — Wangpeng An, Tsinghua University; Haoqian Wang, Graduate School at Shenzhen, Tsinghua University; yulun Zhang, Graduate School at Shenzhen, Tsinghua University; Qiong hai Dai, Tsinghua University
  5. CNN-Based Text Image Super-Resolution Tailored for OCR — Haochen Zhang; Dong Liu, USTC; Zhiwei Xiong, USTC
  6. Adaptive Anchor-Point Selection for Single Image Super-Resolution — Xuesen Shang, Tsinghua Universtiy; Wenming Yang, Tsinghua University; Shuifa Sun; Yapeng Tian; Hai Chen; Kaiquan Chen

13:30 - 15:00 (Wednesday, December 13, 2017)
Oral session 9
Special Session: Point Cloud Compression
Location: Petersburg ballroom 2
Session Chair: TBA
  1. Rate-Distortion Optimized Scan for Point Cloud Color Compression — Yiqun Xu, ICT; Shanshe Wang, PKU; Xinfeng Zhang, NTU; Shiqi Wang, Nanyang Technological University; Siwei Ma, Peking University; Wen Gao
  2. Embedded Binary Tree For Dynamic Point Cloud Geometry Compression with Graph Signal Resampling and Prediction — Karthik Ainala, University of Missouri, Kansas City; Birendra Kathariya, University of Missouri, Kansas City; Zhu Li; Rajan Joshi, Qualcomm
  3. Attribute Compression of 3D Point Clouds Using Laplacian Sparsity Optimized Graph Transform — Yiting Shao, Peking University; ZHAOBIN ZHANG, University of Missouri - Kansa; Zhu Li; Kui Fan, Peking University; Ge Li, Peking University
  4. Performance Assessment of Point Cloud Compression — Rufael Mekuria, Unified Streaming; Sebastien Laserre, Technicolor; Christian Tulvan, Institut Mines Telecom

13:30 - 15:00 (Wednesday, December 13, 2017)
Oral session 10
Quality Assessment
Location: Petersburg ballroom 3
Session Chair: TBA
  1. An objective assessment method based on multi-level factors for panoramic videos — Shu Yang, Beijing Institute of Technology; Junzhe Zhao, Beijing Institute of Technology; Tingting Jiang, Peking University; Jing Wang, Beijing Institute of Technology; Tariq Rahim, Beijing Institute of Technology; Bo Zhang, Beijing Institute of Technology; Zhaoji Xu, China Mobile Communications Corporation Research Institute; Zesong Fei, Beijing Institute of Technology
  2. Internal Generative Mechanism Inspired Reduced Reference Image Quality Assessment with Entropy of Primitive — Shanshe Wang, PKU; shiqi Wang, NTU; Ke Gu, BJUT; Siwei Ma, Peking University; Wen Gao
  3. Subjective Quality Assessment of Animation Images — Guanghui Yue, Tianjin University; Chunping Hou; Ke Gu, BJUT
  4. Objective Quality Assessment for Video Retargeting Based on Spatio-Temporal Distortion Analysis — Chih-Chung Hsu; Chia-Wen Lin, National Tsing Hua University

15:00 - 15:30
Coffee break

15:30 - 17:00 (Tuesday, December 12, 2017)
Poster session 1
Location: TBA
Session Chair: TBA
  1. A Novel Egocentric Pointing System  Based on Smart Glasses — Yi-Yu Hsieh, National Chiao Tung University; Yu-Han Wei; Kuan-Wen Chen, National Chaio Tung University; Jen-Hui Chuang, National Chiao Tung University
  2. Multimodal 3D Visible Articulation System for Syllable Based Mandarin Chinese Training — Rui Li, Clemson University; Jun Yu
  3. Enhancing Pulmonary Nodule Detection via Cross-Modal Alignment — Yumeng Zhu, SJTU; yi Xu; Bingbing NI; Jie Zhang, SJTU; Xiaokang Yang, Shanghai JiaoTong University
  4. Human Tracking by Employing the Scene Information in Underground Coal Mines — Xue Zhou, UESTC; KeXin Chen, UESTC; Qidong Zhou
  5. Joint Multi-Feature Fusion and Attribute Relationships for Facial Attribute Prediction — Pingyu Wang, Beijing University of Posts and Telecommunications; Fei Su, Beijing University of Posts and Telecommunications; Zhicheng Zhao, Beijing University of Posts and Telecommunications
  6. Deep Hashing with Triplet Quantization Loss — Yuefu Zhou, Shanghai Jiao Tong University; Shanshan Huang, Shanghai Jiao Tong University; Ya Zhang, Shanghai Jiao Tong University; Yanfeng Wang, Shanghai Jiao Tong University
  7. Depth Super-Resolution via Fully Edge-Augmented Guidance — Jingyu Yang, Tianjin University; Hao Lan, Tianjin University; Xiaolin Song; Kun Li
  8. Superpixel-Based Level Set Tracking by Integrating Appearance and Motion — Xue Zhou, UESTC; KeXin Chen, UESTC; Qidong Zhou
  9. Detecting Closely Spaced and Occluded Pedestrians Using Specialized Deep Models for Counting — Sanjukta Ghosh, Friedrich-Alexander-University; Peter Amon, Siemens Corporate Technology; Andreas Hutter, Siemens Corporate Technology; André Kaup
  10. Real-Time Deep Image Super-Resolution via Global Context Aggregation and Local Queue Jumping — Yueyu Hu, Peking University; Wenhan Yang, Peking University; Shihong Deng, Peking University; Jiaying Liu
  11. A Novel Subspace Spatial-spectral Low Rank Learning Method for Hyperspectral Denoising — Le Sun, Nanjing University of Informat; Byeungwoo Jeon, Sungkyunkwan University
  12. Improve Object Detection via a Multi-feature and Multi-Task CNN Model — Yingxin Lou, BUPT; Guangtao Fu, Academy of Broadcasting Science; Zhuqing Jiang; Aidong Men; Yun Zhou
  13. Cascaded Convolutional Neural Networks for Object Detection — Yajing Guo, BUPT; Xiaoqiang Guo, Academy of Broadcasting science; Zhuqing Jiang; Yun Zhou
  14. Deep Discriminative Network with Inception Module for Person Re-identification — Yihao Zhang, Peking University; Wenmin Wang, Peking University; jinzhuo Wang, Peking University
  15. Deep Fully Convolutional Regression Networks for Single Image Haze Removal — Xi Zhao, Xidian University; Keyan Wang, Xidian University; Yunsong Li, Xidian University; Jiaojiao Li, Xidian University
  16. DeepCoder: A Deep Neural Network Based Video Compression — Tong Chen, NJU; Haojie Liu, NJU; Qiu Shen, NJU; Tao Yue, NJU; Xun Cao, NJU; Zhan Ma, NJU
  17. Graphic Logo Detection with Deep Region-based Convolutional Networks — Yuanyuan Li, BUPT; Qiuyue Shi; Jiangfan Deng; Fei Su, Beijing University of Posts and Telecommunications
  18. Endoscopic Video Deblurring via Synthesis — Lingbing Peng, uestc.edu.cn; Shuaicheng Liu; Dehua Xie, uestc.edu.cn; Shuyuan Zhu, uestc.edu.cn; Bing Zeng, UESTC
  19. Adaptive Difference Modelling for Background Subtraction — Xianghao Zang, Peking Uninversity; Ge Li, Peking University; Jun Yang, Peking University; Wenmin Wang, Peking University
  20. A New Underwater Image Enhancing Method via Color Correction and Illumination Adjustment — Wenhao Zhang, Shenzhen Graduate School, Peking University; Ge Li; Zhenqiang Ying, Peking University
  21. Long-Term Video Interpolation with Bidirectional Predictive Network — Xiongtao Chen, Peking University; Wenmin Wang, Peking University; jinzhuo Wang, Peking University
  22. Parameter-free Hierarchical Image Segmentation — SM Abdullah, Monash University; Peter Tischer, Monash University; Sudanthi Wijewickrema , University of Melbourne; Andrew Paplinski, Monash University
  23. Fast Multi-View People Localization Using a Torso-High Reference Plane — Chun-Chieh Hsu, NCTU, Hsinchu, Taiwan; Hua-Tsung Chen; Wen-Jiin Tsai; Suh-Yin Lee
  24. Scale-aware Hierarchical Loss: A Multipath RPN for Multi-scale Pedestrian Detection — Xiaowei Zhang, Beihang University; Bo Li, School of Computer Science and Engineering, Beihang University; Hai-Miao Hu, School of Computer Science and Engineering, Beihang University
  25. Mask-Streaming CNN for Pedestrian Detection — Peilei Dong, Peking University; Wenmin Wang, Peking University; Mengdi Fan, PKU; Ronggang Wang, PKUSZ; Ge Li, Peking University
  26. Demoiréing for Screen-shot Images with Muti-channel Layer Decomposition — Jingyu Yang, Tianjin University; Xue Zhang, Tianjin University; Changrui Cai, Tianjin University; Kun Li
  27. Improved Tensor Voting for Missing Edge Inference — Xiangyu Hu, Shanghai University; Ran Ma, Shanghai University; Tong Li, Shanghai University
  28. A Spatio-temporal Deep Architecture for Surveillance Event Detection Based on ConvLSTM — KaiHui Zhou, BUPT; YanDong Zhu; YanYun Zhao
  29. Simultaneous Physical and Conceptual Ball State Estimation in Volleyball Game Analysis — Xina Cheng, Waseda University; Norikazu Ikoma, Nippon Institute of Technology; Masaaki Honda, Waseda University; Takeshi Ikenaga, Waseda University
  30. Real-Time Volumetric Reconstruction of Manhattan Indoor Scenes from Depth Sequences — Mahdi Yazdanpour, Oklahoma State University; Guoliang Fan, Oklahoma State University; Weihua Sheng, Oklahoma State University
  31. 3D Convolutional Neural Network with Selective Training and Balanced Linear Mapping for Person Re-identification — Sutong Zheng, Beijing University of Posts an; Xiaoyu Li; Zhuqing Jiang; Xiaoqiang Guo, Academy of Broadcasting science
  32. LOMO3D Descriptor for Video-Based Person Re-identification — Sutong Zheng, Beijing University of Posts an; Xiaoyu Li; Zhuqing Jiang; Xiaoqiang Guo, Academy of Broadcasting science
  33. Comparative Evaluation of Facial Fiducial Point Detection Approaches — Vinícius de Sousa, UFCG; Herman Gomes, UFCG; Eustáquio de Queiroz, UFCG
  34. Selective Face Encryption in H.264 Encoded Videos — Christoph Gerhardt, Fraunhofer IDMT; Patrick Aichroth, Fraunhofer IDMT; Sebastian Mann, Fraunhofer IDMT
  35. Convolutional Neural Network Steganalysis's Application to Steganography — Mehdi Sharifzadeh, University of Illinois at Chic; Chirag Agarwal, University of Illinois at Chicago; Mohammed Aloraini, University of Illinois at Chicago; Dan Schonfeld, University of Illinois at Chicago

17:00 - 18:30
Panel: TITLE: TBA
Location: St. Petersburg ballroom 1 
Moderator: TBA
Panelists: TBA

18:30 - 21:30
Banquet
Location: TBA



Wednesday, December 13, 2017

09:00 - 10:00 (Wednesday, December 13, 2017)
Keynote: How did "DRC-HUBO+" win the DARPA Robotics Challenge? – Robust Computer Vision Algorithms for “DRC-HUBO+, Prof. In So Kweon, KAIST, South Korea
Location: St. Petersburg ballroom 1 
Session Chair: TBA

10:00 - 10:30
Coffee break

10:30 - 12:30 (Wednesday, December 13, 2017)
Oral session 11
Special Session: Regularization Techniques for High-Dimensional Visual Data Processing and Analysis
Location: Petersburg ballroom 2
Session Chair: TBA
  1. Learning Robust Latent Subspace for Discriminative Regression — Zheng Zhang, Bio-Computing Research Center,; Zuofeng Zhong; Jinrong Cui; Lunke Fei
  2. Edge-Guided Generative Adversarial Network for Image Inpainting — Shunxin Xu; Dong Liu, USTC; Zhiwei Xiong, USTC
  3. Action Proposals Using Hierarchical Clustering of Super-trajectories — Tianyi Zhang, Nanyang Technological Univ.; Li Niu; Jianfei Cai; Alex Kot
  4. Segmentation Quality Evaluation based on Multi-Scale Convolutional Neural Networks — Wen Shi, UESTC; Fanman Meng, University of Electronic Science and Technology of China; Qingbo Wu, UESTC
  5. Image Denoising via Low Rank Regularization Exploiting Intra and Inter Patch Correlation — Hangfan Liu, Peking University; Ruiqin Xiong, Peking University
  6. ** Image Super-Resolution Based on Adaptive Joint Distribution Modeling — Hangfan Liu, Peking University; Ruiqin Xiong, Peking University

10:30 - 12:30 (Wednesday, December 13, 2017)
Oral session 12
Machine Learning for Visual Information Processing III
Location: Petersburg ballroom 3
Session Chair: TBA
  1. LLCNN: A Convolutional Neural Network for  Low-light Image Enhancement — Li Tao, Peking University; Chuang Zhu, Peking University; Huizhu Jia; Xiaodong Xie
  2. Clothing Retrieval with Visual Attention Model — Zhonghao Wang, Shanghai Jiaotong University; Yujun Gu; Ya Zhang, Shanghai Jiao Tong University; Jun Zhou; Xiao Gu
  3. Multi-scale Mutual Feature Convolutional Neural Network for Depth Image Denoise and Enhancement — Xuan Liao, South China University of Technology; Xin Zhang, South China University of Technology
  4. ** Two-Stream Binocular Network: Accurate Near Field Finger Detection Based On Binocular Images — Yi Wei, Tsinghua University; Guijin Wang, Tsinghua University; Cairong  Zhang, Tsinghua University; Hengkai Guo, Tsinghua University; Xinghao Chen, Tsinghua University; Huazhong Yang
  5. Dual Graph Regularized Sparse Coding for Image Representation — Lingdao Sha, University of Illinois at Chic; Dan Schonfeld, University of Illinois at Chicago
  6. LinkNet: Exploiting Encoder Representations for Efficient Semantic Segmentation — Abhishek Chaurasia, Purdue University; Eugenio Culurciello, Purdue University

13:30 - 15:30 (Tuesday, December 12, 2017)
Oral session 13
Special Session: Deep Learning for Image and Video Compression
Location: Petersburg ballroom 2
Session Chair: TBA
  1. Spatial-Temporal Residue Network Based In-Loop Filter for Video Coding — Chuanmin Jia, Peking University; Shiqi Wang; Xinfeng Zhang, NTU; Shanshe Wang, PKU; Siwei Ma, Peking University
  2. A CNN Cascade for Quality Enhancement of Compressed Depth images — Zhi Jin, Shenzhen University; Lei Luo; Yi Tang; Wenbin Zou; Xia Li
  3. ** CNN-Based Rate-Distortion Modeling for H.265/HEVC — Bin Xu, Wuhan University; Xiang Pan, Wuhan University; Yan Zhou, Wuhan University; Yiming Li, Wuhan University; Daiqin Yang, Wuhan University; Zhenzhong  Chen, WHU
  4. Learning a Convolutional Neural Network for Fractional Interpolation in HEVC Inter Coding — Han Zhang, Shanghai Jiao Tong Uinversity; Li Song, Shanghai Jiao Tong University; zhengyi Luo; Xiaokang Yang, Shanghai JiaoTong University
  5. Sketch-Based Cross-Domain Image Retrieval Via Heterogeneous Network — Hao Zhang, BUPT; Chuang Zhang, School of Information and Communication Engineering, BUPT, Beijing, China; Ming Wu, School of Information and Communication Engineering, BUPT, Beijing, China
  6. Hierarchical Piece-Wise Linear Projections for Efficient Intra-Prediction Coding — Yue Li, University of Science and Technology of China; Li Li; Zhu Li; Houqiang Li

13:30 - 15:30 (Tuesday, December 12, 2017)
Oral session 14
Multimedia Content Analysis II
Location: Petersburg ballroom 3
Session Chair: TBA
  1. A Joint Compression Scheme for Local Binary Feature Descriptors and their Corresponding Bag-of-Words Representation — Dominik Van Opdenbosch, Technical University of Munich; Martin Oelsch, Technical University of Munich; Adrian Garcea, Technical University of Munich; Eckehard Steinbach, Technical University Munich, Germany
  2. ** Motion Energy Guided Multi-scale  Heterogeneous Features for 3D Action Recognition — Chengwu Liang, Zhengzhou University; Ling Guan, Ryerson University; Lin  Qi, Zhengzhou University
  3. Image Retrieval by Dense Caption Reasoning — Xinru Wei, BUPT; Yonggang Qi; Jun Liu; fang Liu
  4. Depth Map Super-Resolution via Multiclass Dictionary Learning with Geometrical Directions — Wei Xu, Beijing University of Technolo; Jin Wang; Qing Zhu, Beijing University of Technology; Xi Wu, Beijing University of Technology; Yifei Qi
  5. ** Robust Object Detection by Cuboid Matching with Local Plane Optimization in Indoor RGB-D Images — Lin Guo, Oklahoma State University; Guoliang Fan, Oklahoma State University; Weihua Sheng, Oklahoma State University
  6. Gram Matrix Based Representation for Image Retrieval — Shanwei Zhao, BUPT MCPRL; Zhicheng Zhao, Beijing University of Posts and Telecommunications; Fei Su, Beijing University of Posts and Telecommunications

15:30 - 16:00
Coffee break

16:00 - 17:30 (Wednesday, December 13, 2017)
Poster session 2
Location: TBA
Session Chair: TBA
  1. Dictionary Learning based High Frequency Inter-Layer prediction for Scalable HEVC — Jens Schneider, IENT RWTH Aachen University; Johannes Sauer, RWTH Aachen University; Mathias Wien, RWTH Aachen University 
  2. HEVC-Compliant Screen Content Transcoding Based on Mode Mapping and Fast Termination — Fanyi Duanmu, New York University; Meng Xu, Ubilinx Technology, Inc.; Yao Wang, NYU; Zhan Ma, NJU
  3. CG-Cast: Compressive Gradient Based Scalable Image SoftCast — Hangfan Liu, Peking University; Ruiqin Xiong, Peking University
  4. Wireless Image and Video Soft Transmission via Perception-Inspired Power Distortion Optimization — Jing Zhao, Peking University; Ruiqin Xiong, Peking University
  5. A Reduced-Reference Color Distortion Metric for Enhanced Low-light Images — Yurui Ren, Dalian University of Technolog; Ge Li, Peking University; Zhenqiang Ying, Peking University; Xiaoqiang Guo, Academy of Broadcasting science
  6. Saliency Change Based Reduced Reference Image Quality Assessment — Jinjian Wu, Xidian University; Yongxu Liu; Guangming Shi, Xidian University; Weisi Lin, Nanyang Technological University, Singapore
  7. A Generic Method to Improve No-Reference Image Blur Metric Accuracy in Video Contents — Yankai Liu, Shanghai Jiao Tong University; Li Song, Shanghai Jiao Tong University; Rong Xie; zhang wenjun
  8. SSIM-based Binocular Perceptual Model for Quality Assessment of Stereoscopic Images — Jian Ma, Shanghai University; Ping An; Liquan Shen; Kai Li, Shanghai university; Jialu Yang, Shanghai University
  9. Assessment and Classification of Singing Quality Based on Audio-Visual Features — Marigona Bokshi, The University of Texas at Dallas; Fei  Tao, The University of Texas at Dallas; Carlos Busso, University of Texas at Dallas, USA; John  Hansen, The University of Texas at Dallas
  10. Modeling Peripheral Vision Impact on Perceptual Quality of Immersive Images — Peiyao Guo, Nanjing University; Qiu Shen, NJU; Mingkai Huang, Nanjing University; Rongbing Zhou, Nanjing University; Xun Cao, NJU; Zhan Ma, NJU
  11. LF-Fusion: Dense and Accurate 3D Reconstruction from Light Field Images — Jiayong Peng; Zhiwei Xiong, USTC; Yueyi Zhang, Microsoft; Dong Liu, USTC; Feng Wu
  12. A Common feature-based Disparity Control Strategy in Stereoscopic Panorama Generation — Haoyu Wang, Univ of Illinois at Chicago;  Daniel  Sandin, University of Illinois at Chicago; Dan Schonfeld, University of Illinois at Chicago
  13. Portable Information Security Display System via Spatial PsychoVisual Modulation — Xiang Li, Shanghai Jiao Tong University; Guangtao Zhai, SJTU; jia Wang; Ke Gu, NTU
  14. Exemplar-based Framework for 3D Point Cloud Hole Filling — Chinthaka Dinesh, Simon Fraser University; Ivan Bajic, Simon Fraser University; Gene Cheung, NII
  15. A visual sensitivity based bit allocation scheme for λ-domain rate control in HEVC — Zheng long Yang, Shang hai university; Guo wei Teng; Guo zhong Wang; Ling zhi Yu
  16. Quantitative Evaluation for Dehazing Algorithms on Synthetic Outdoor Hazy Dataset — Yufei Li, Xidian University; Keyan Wang, Xidian University; Ning Xu, Xi'an Institute of Space Radio Technology; Yunsong Li, Xidian University
  17. CNN oriented fast QTBT partition algorithm  for JVET intra coding — Zhipeng Jin, School of Communication and In; Ping An; Liquan Shen; chao Yang, School of Communication and Information Engineering, Shanghai University
  18. Geometry-Adaptive Motion Partitioning Using Improved Temporal Prediction — Max Blaeser, RWTH Aachen University; Cordula Heithausen, RWTH Aachen University; Mathias Wien, RWTH Aachen University
  19. Extending HEVC Using Texture Synthesis — Bastian Wandt, Leibniz Universität Hannover; Thorsten Laude, LUH; Yiqun Liu, Leibniz Universität Hannover; Bodo Rosenhahn, Leibniz Universität Hannover; Jörn Ostermann
  20. Low-complexity Compression of High Dynamic Range Infrared Images with JPEG compatibility — Evgeny Belyaev, DTU; Claire Mantel; Soren  Forchammer, Technical University of Denmark
  21. Bilateral Filtering for Video Coding — Per Wennersten, Ericsson Research; Jacob Ström, Ericsson Research; Ying Wang, Skype; Kenneth Andersson, Ericsson Research; Rickard Sjöberg, Ericsson Research; Jack Enhorn, Ericsson Research
  22. Rate Control Model for High Dynamic Range Video — Lixun Bai, Shanghai Jiao Tong University; Li Song, Shanghai Jiao Tong University; Rong Xie; liang zhang; zhengyi Luo
  23. Just-Noticeable-Quantization-Distortion Based Preprocessing for Perceptual Video Coding — Sehwan Ki, KAIST VIC lab; Munchurl    Kim, Korea Advanced Institute of Science and Technology; Hyunsuk Ko, Electronics and Telecommunications Research Institute
  24. A Convolutional Neural Network-Based Approach to Rate Control in HEVC Intra Coding — Ye Li, USTC; Bin Li; Dong Liu, USTC; zhibo Chen, University of Science and Technology of China
  25. Feature Based Inter Prediction Optimization For Non-Translational Video Coding In Cloud — Xuelin Shen,  Sun Yat-sen University; Jun Wang, Sun Yat-sen University ; Qing Yang, Sun Yat-sen University; Pielin Chen, Sun Yat-sen University; Fan Liang, Sun Yat-sen University
  26. Scalable Near-Lossless Video Compression Based on HEVC — Andreas Heindel, FAU Erlangen-Nürnberg; André Kaup
  27. Fast Encoding of Surveillance Videos Based on HEVC — Fangdong Chen, USTC; Dong Liu, USTC; Houqiang Li
  28. Coefficient-Group Level Modeling for Low Complexity RDO in HEVC — Bo Huang, Fuzhou university; Zhifeng Chen; qi Cai; Min Chen
  29. An LSTM Method for Predicting CU Splitting in H.264 to HEVC Transcoding — Yanan Wei, Buaa university; Zulin Wang; Mai Xu; shuhao Qiao
  30. An improved MRF model for robust color guided depth up-sampling — Yi Chen, Huazhong Univ. of Sci. & Tech.; li yu; Shengwei Wang , HUST
  31. A Robust 3D Visual Saliency Computation Model for Human Fixation Prediction of stereoscopic videos — qiong Liu; You Yang, Huazhong University of Science and Technology; Pian Li, HUST; Bei Li
  32. Bivariate Statistics and Binocular Energy Induced Stereo-pair Quality Evaluator — Yang Yao, Shanghai University; Liquan Shen; Ping An
  33. Monocular Camera Semi-Dense Mapping Based on ORB-SLAM — Boshi Wang, Beijing University of Posts an; Haiying Wang, BUPT
  34. Depth Estimation for Outdoor Image Using Coupled Dictionary Learning and Region Detection — Qiqi Yao, Shenzhen graduate school,Pekin; guibo luo, shenzhen graduate school, Peking university; Yuesheng Zhu, Peking University

16:00 - 17:30 (Wednesday, December 13, 2017)
Demo session
Location: TBA
Session Chair: TBA
  1. Fast SW Decoding: HEVC Tile-based Parallel Decoding on Asymmetric Mobile Cores — Yeongil Ryu, Gachon University; Eun-Seok Ryu, Gachon University
  2. A MPEG-DASH toolchain for dynamic content orchestration and ad-insertion through manifest manipulation — Robert Seeliger, Fraunhofer FOKUS; Daniel Silhavy, Fraunhofer Institute for Open Communication Systems FOKUS; Stefan Arbanowski, Fraunhofer Institute for Open Communication Systems FOKUS

17:30 - 18:00
Closing

** candidate papers for best paper awards