Regular Paper Arrangement

Best Paper Session

Time: 2019/12/17 10:30~12:00, Location: Auditorium
Session Chair: Wen-Huang Cheng

• Efficient Dense Modules of Asymmetric Convolution for Real-Time Semantic Segmentation (43)

  Shao-Yuan Lo (National Chiao Tung University); Hsueh-Ming Hang (National Chiao Tung University); Sheng-Wei Chan (Industrial Tech Research Inst.); Jing-Jhih Lin (Industrial Tech Research Inst.)

• Adaptive Bilinear Pooling for Fine-grained Representation Learning (39)

  Shaobo Min (University of Science and Technology of China); Youliang Tian (Guizhou University); Hongtao Xie (University of Science and Technology of China); Hantao Yao ( Institute of Automation, Chinese Academy of Sciences); Yongdong Zhang (University of Science and Technology of China)

• Weakly Supervised Video Summarization by Hierarchical Reinforcement Learning (91)

  Yiyan Chen (The University of Tokyo); Li Tao (The University of Tokyo); Xueting Wang (The University of Tokyo); Toshihiko Yamasaki (The University of Tokyo)

• Semantic Prior Guided Face Inpainting (164)

  Zeyang Zhang (College of Electronics and Information Engineering, Tongji University); Xiaobo Zhou (College of Electronics and Information Engineering, Tongji University); Xiaoyan Zhang (College of Computer Science and Software Engineering, Shenzhen University)

Oral Session 1: Multimedia Search

Time: 2019/12/17 14:00~15:30, Location: 301AB
Session Chair: Weiqing Min

• Attention-Aware Feature Pyramid Ordinal Hashing for Image Retrieval (99)

  Xie Sun (Nanjing University of Science and Technology ); Lu Jin (Nanjing University of Science and Technology ); Zechao Li (Nanjing University of Science and Technology)

• Measuring Similarity between Brands using Social Media Content (40)

  Yiwei Zhang (The University of Tokyo); Xueting Wang (The University of Tokyo); Yoshiaki Sakai (Geomarketing Co.,Ltd.); Toshihiko Yamasaki (The University of Tokyo)

• Social Font Search by Multimodal Feature Embedding (146)

  Saemi Choi (University of Tokyo); Shun Matsumura (The University of Tokyo); Kiyoharu Aizawa (The University of Tokyo)

• Video Summarization based on Sparse Subspace Clustering with Automatically Estimated Number of Clusters (150)

  Pengyi Hao (Zhejiang University of Technology); Edwin Manhando (Zhejiang University of Science and Technology); Taotao Ye (Zhejiang University of Technology); Cong Bai (Zhejiang University of Technology)

Oral Session 2: Multimedia Service

Time: 2019/12/17 16:00~17:30 Location: 301AB
Session Chair: Toshihiko Yamasaki

• Multiple Fisheye Camera Tracking via Real-Time Feature Clustering (46)

  Chon Hou Sio (National Chiao Tung University); Hong-Han Shuai (National Chiao Tung University); Wen-Huang Cheng (EE, NCTU)

• Salient Time Slice Pruning and Boosting for Person-Scene Instance Search in TV Series (41)

  Zheng Wang (National Institute of Informatics); Fan Yang (The University of Tokyo); Shin'ichi Satoh (National Institute of Informatics)

• Stop Hiding Behind Windshield: A Windshield Image Enhancer Based on a Two-way Generative Adversarial Network (81)

  Chi-Rung Chang (NCTU); Kuan-Yu Lung (NCTU); Yi-Chung Chen (NCTU); Zhi-Kai Huang (NCTU); Hong-Han Shuai (National Chiao Tung University); Wen-Huang Cheng (EE, NCTU)

• A Performance-Aware Selection Strategy for Cloud-based Video Services with Micro-Service Architecture (76)

  Zhengjun Xu (Beijing University of Posts and Telecommunications); Haitao Zhang (Beijing University of Posts and Telecommunications); Han Huang (Beijing University of Posts and Telecommunications)

Oral Session 3: Human Analysis in Multimedia

Time: 2019/12/18 14:00~15:30, Location: 301AB
Session Chair: Bing-Kun Bao

• Dense Attention Network for Facial Expression Recognition in the Wild (184)

  Cong Wang (University of Chinese Academy of Sciences); Ke Lu (University of Chinese Academy of Sciences); Jian Xue (University of Chinese Academy of Sciences); Yanfu Yan (University of Chinese Academy of Sciences)

• Make Skeleton-based Action Recognition Model Smaller, Faster and Better (23)

  Fan Yang (Nara Institute of Science and Technology / RIKEN AIP); Yang Wu (Kyoto University); Sakriani Sakti (Nara Institute of Science and Technology / RIKEN AIP); Satoshi Nakamura (Nara Institute of Science and Technology / RIKEN AIP)

• A Cascade Sequence-to-Sequence Model for Chinese Mandarin Lip Reading (56)

  Ya Zhao (Zhejiang University); Rui Xu (Zhejiang University); Mingli Song (Zhejiang University)

• Learn to Gesture: Let Your Body Speak (80)

  Tian Gan (Shandong University); Zhixin Ma (Shandong University); Yuxiao Lu (Shandong University); Xuemeng Song (Shandong University); Liqiang Nie (Shandong University)

Oral Session 4: Vision in Multimedia

Time: 2019/12/18 16:00~17:30, Location: 301AB
Session Chair: Hsueh-Ming Hang

• Multi-Dilation Network for Crowd Counting (63)

  Shuheng Wang (Tongji University); Hanli Wang (Tongji University); Qinyu Li (Tongji University)

• Excluding the Misleading Relatedness Between Attributes in Multi-Task Attribute Recognition Network (113)

  Sirui Cai ( Shanghai University); Yuchun Fang (Shanghai University)

• Robust Visual Tracking via Statistical Positive Sample Generation and Gradient Aware Learning (60)

  Lijian Lin (Xiamen University); Haosheng Chen (Xiamen University); Yanjie Liang (Xiamen University); Yan Yan (Xiamen University); Hanzi Wang (Xiamen University)

• Exploring Semantic Segmentation on the DCT Representation (42)

  Shao-Yuan Lo (National Chiao Tung University); Hsueh-Ming Hang (National Chiao Tung University)

Poster Session 1

Time: 2019/12/17 15:30~16:30, Location: 302AB
Session Chair: Tian Gan

• Residual Graph Convolutional Networks for Zero-Shot Learning (62)

  Jiwei Wei (University of Electronic Science and Technology of China); Yang Yang (University of Electronic Science and Technology of China); Jingjing Li (University of Electronic Science and Technology of China); Lei Zhu (Shandong Normal Unversity); Lin Zuo (University of Electronic Science and Technology of China); Heng Tao Shen (University of Electronic Science and Technology of China (UESTC))

• L0 Gradient Smoothing and Bimodal Histogram Analysis: A Robust Method for Sea-sky-line Detection (38)

  Jian Jiao (Fudan University); Zijian Wang (Fudan University); Hong Lu (Fudan University)

• Deep Distillation Metric Learning (24)

  Jiaxu Han (Tianjin University); Tianyu Zhao (Tianjin University); Changqing Zhang (Tianjin university)

• Self-balance motion and appearance model for multi-object tracking in UAV (98)

  Hongyang Yu (Harbin Institute of Technology); Guorong Li (University of Chinese Academy of Sciences); Weigang Zhang (Harbin Institute of Technology, Weihai); Hongxun Yao (Harbin Institute of Technology); Qingming Huang (University of Chinese Academy of Sciences)

• Deep Spherical Gaussian Illumination Estimation for Indoor Scene (92)

  Mengtian Li (Nanjing University); Jie Guo (Nanjing University); Xiufen Cui (Samsung Electronics (China）R&D Center); Rui Pan (Samsung Electronics (China）R&D Center); Yanwen Guo (Nanjing University); Chenchen Wang (Nanjing University); Piaopiao Yu (Nanjing University); Fei Pan (Nanjing University)

• NRQQA: A No-Reference Quantitative Quality Assessment Method for Stitched Images (116)

  shengju yu (Huazhong University of Science and Technology); XiaoYu Xu (Huazhong University of Science and Technology); hao tao (HuaZhong University of science and technology); Li Yu (HUST); yixuan wang (HuaZhong University of science and technology)

• Gradient Guided Image Deblocking Using Convolutional Neural Networks (19)

  Jiawei Feng (Xidian University); Cheolkon Jung (Xidian University); Zhu Li (University of Missouri, Kansas City)

• Color Recovery from Multi-Spectral NIR Images Using Gray Information (90)

  Qingtao Fu (Xidian University); Cheolkon Jung (Xidian University)

• An EERM Efficient Parameter Optimization Algorithm and Its Application to Image Denoising (117)

  yinhao liu (Hangzhou Dianzi University); mengting fan (China Jiliang University); Xiaofeng Huang (xfhuang@hdu.edu.cn); Haibing Yin (Hangzhou Dianzi University)

• WaveCSN: Cascade Segmentation Network for Hip Landmark Detection (64)

  Hai Wu (University of Science and Technology of China); Hongtao Xie (University of Science and Technology of China); Fanchao Lin (University of Science and Technology of China); Sicheng Zhang (Anhui Provincial Children's Hospital); Jun Sun (Anhui Provincial Children's Hospital); Yongdong Zhang (University of Science and Technology of China)

• Shifted Spatial-Spectral Convolution for Deep Neural Networks (50)

  Yuhao Xu (The University of Tokyo); Hideki Nakayama (The University of Tokyo)

• Multi-Scale Invertible Network for Image Super-Resolution (57)

  Zhuangzi Li (School of Computer and Information Engineering, Beijing Technology and Business University); Shanshan Li (Beijing Technology and Business University); Naiguang Zhang (Information Technology Institute, Academy of Broadcasting Science); Lei Wang (Academy of Broadcasting Science, SAPPRFT); Ziyu Xue (Information Technology Institute, Academy of Broadcasting Science, SART)

• Feature fusion adversarial learning network for liver lesion classification (26)

  peng chen (jiangsu university); Yuqing Song (JIANGSU UNIVERSITY); Zhe Liu (Jiangsu University); Deqi Yuan (Zhenjiang First People’s Hospital Branch)

• Fast and Accurately Measuring Crack Width via Cascade Principal Component Analysis (66)

  HuiLing GENG (Beijing University of Technology)

• Active Perception Network for Salient Object Detection (94)

  Jun Wei (Institute of Computing Technology, Chinese Academy of Sciences); Shuhui Wang (VIPL,ICT,Chinese academic of science); Liang Li (Chinese Academy of Sciences); Qingming Huang (University of Chinese Academy of Sciences)

• Surface Normal Data Guided Depth Recovery with Graph Laplacian Regularization (100)

  Longhua Sun (Beijing University of Technology); Jin Wang (Beijing University of Technology); Yunhui Shi (Beijing University of Technology); Qing Zhu (Beijing University of Technology); Baocai Yin ( Dalian University of Technology)

• An Adaptive Dark Region Detail Enhancement Method for Low-light Images (108)

  Wengang Cheng (North China Electric Power University); Caiyun Guo (North China Electric Power University); Haitao Hu (North China Electric Power University)

Poster Session 2

Time: 2019/12/18 15:30~16:30, Location: 302AB
Session Chair: Cong Bai

• Deep Structural Feature Learning: Vehicle Re-Identification In Structure-Aware Map Space (58)

  Wenqian Zhu (Wuhan University); Ruimin Hu (Wuhan University); Zhongyuan Wang (National Engineering Research Center for Multimedia Software, Wuhan University, China); Dengshi Li (Jianghan University); Xiyue Gao (Wuhan Univ.)

• Selective Attention Network for Single Image Dehazing and Deraining (173)

  Xiao Liang (School of Computer Science and Engineering, Nanjing University of Science and Technology); runde li (Nanjing University of Science & Technology); Jinshan Pan (Nanjing University of Science and Technology); Jinhui Tang (Nanjing University of Science and Technology)

• Manifold Alignment with Multi-graph Embedding (87)

  Chang-Bin Huang (Jiangsu University); Timothy Apasiba Abeo (Jiangsu University); Xiang-Jun Shen (Jiangsu University)

• Multi-Label Image Classification with Attention Mechanism and Graph Convolutional Networks (119)

  Quanling Meng (Harbin Institute of Technology, Weihai); Weigang Zhang (Harbin Institute of Technology, Weihai)

• RSC-DGS: Fusion of RGB and NIR Images Using Robust Spectral Consistency and Dynamic Gradient Sparsity (20)

  Shengtao Yu (Huawei Technologies); Cheolkon Jung (Xidian University)

• Multi-Feature Fusion for Multimodal Attentive Sentiment Analysis (103)

  Man A (Yunnan University); Pu yuanyuan (yunnan university); Dan Xu (Yunnan University); Wenhua Qian (Yunnan University); Zhengpeng Zhao (Yunnan University); Qiuxia Yang (Yunnan University)

• Multimodal Attribute and Feature Embedding for Activity Recognition (168)

  Weiming Zhang (Beijing Jiaotong University); Yi Huang (Chinese Academy of Sciences); WanTing Yu (Beijing Jiaotong University); XiaoShan Yang (Chinese Academy of Sciences); JiTao Sang (Beijing Jiaotong University)

• Representative Feature Matching Network for Image Retrieval (31)

  Zhuangzi Li (School of Computer and Information Engineering, Beijing Technology and Business University); Feng Dai (Beijing Technology and Business University); Naiguang Zhang (Information Technology Institute, Academy of Broadcasting Science); Lei Wang (Academy of Broadcasting Science, SAPPRFT); Ziyu Xue (Information Technology Institute, Academy of Broadcasting Science, SART)

• Deep Feature Interaction Embedding for Pair Matching Prediction (93)

  Luwei Zhang (The University of Tokyo); Xueting Wang (The University of Tokyo); Toshihiko Yamasaki (The University of Tokyo)

• Multi-source User Attribute Inference based on Hierarchical Auto-encoder (67)

  Boyu Zhang (Beijing Jiaotong University); Xiangguo Ding (Beijing Jiaotong University); Xiaowen Huang (National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences,); Jitao Sang (Beijing Jiaotong University, China); Jian Yu (Beijing Jiaotong University)

• Comprehensive Event Storyline Generation from Microblogs (48)

  wenjin sun (Beijing Jiaotong University); yuhang wang (Beijing Jiaotong University); Yuqi Gao (Nanjing University); Jitao Sang (Beijing Jiaotong University, China); Jian Yu (Beijing Jiaotong University)

• Domain specific and idiom adaptive video summarization (34)

  Yi Dong (Nanyang Technological University); Chang Liu (Nanyang Technological University); Zhiqi Shen (NTU); Zhanning Gao (Alibaba Group); Pan Wang (Alibaba Group); Changgong Zhang (Alibaba Group); Peiran Ren (Alibaba Group); Xuansong Xie (Alibaba); Han Yu (Nanyang Technological University (NTU)); Qingming Huang (University of Chinese Academy of Sciences)

• An Automated Lung Nodule Segmentation Method Based On Nodule Detection Network and Region Growing (169)

  Yanhao Tan (University of Chinese Academy of Sciences); Ke Lu (University of Chinese Academy of Sciences); Jian Xue (University of Chinese Academy of Sciences)

• Food Photo Enhancement with Single Domain Generative Adversarial Networks (47)

  Shudan Wang (University of Science and Technology Beijing); Liang Sun (University of Science and Technology Beijing); Weiming Dong (NLPR, Institute of Automation, Chinese Academy of Sciences); Yong Zhang (Tencent AI Lab)

• Generalizing Rate Control Strategies for Real-time Video Streaming via Learning from Deep Learning (25)

  Tianchi Huang (Tsinghua University); Ruixiao Zhang (Tsinghua University); Chenglei Wu (Tsinghua University); Xin Yao (Tsinghua University); Chao Zhou (Beijing Kuaishou Technology Co., Ltd); Bing Yu ( Beijing Kuaishou Technology Co., Ltd); Lifeng Sun (Tsinghua University)

• IKDMM: Iterative Knowledge Distillation Mask Model for Robust Acoustic Beamforming (65)

  Zhaoyi Liu (Peking university); Yuexian Zou (Peking University)

• Multi-Objective Particle Swarm Optimization for ROI based Video Coding (77)

  Guangjie Ren (Wuhan University); Feiyang Liu (Wuhan University); Daiqin Yang (Wuhan University); Yiyong Zha (Tencent); Yunfei Zhang (Tencent); Xin Liu (Tencent)

• An LSTM based rate and distortion prediction method for low-delay video coding (69)

  Feiyang Liu (Wuhan University); Guiyan Cao (Wuhan University); Daiqin Yang (Wuhan University); Yiyong Zha (Tencent); Yunfei Zhang (Tencent); Xin Liu (Tencent)

• Chaos to Order, Can GANs Make It? (22)

  Sanbi Luo (Institute of Information Engineering,Chinese Academy of Sciences)); Tao Guo (Institute of Information Engineering,Chinese Academy of Sciences), Jizhong Han (Institute of Information Engineering,Chinese Academy of Sciences); Yonggang Huang (Beijing Institue of Technology)