Fast Forward

In the Fast Forward presentations for poster papers, the papers are grouped almost the same as the Poster sessions, except that due to time constraints some papers in Poster session #3 are presented in Fast Forward session #4. Please note that in the Booklet the poster papers are grouped according to Fast Forward sessions.

Tuesday 23 October – Conference Day 2


9:00 – 9:30 Crystal Ballroom 1-3

Fast Forward 1

  • SCRATCH: A Scalable Discrete Matrix Factorization Hashing for Cross-Modal Retrieval Chuan-Xiang Li (Shandong University), Zhen-Duo Chen (Shandong University), Peng-Fei Zhang (Shandong University), Xin Luo (Shandong University), Liqiang Nie (Shandong University), Wei Zhang (Shandong University), Xin-Shun Xu (Shandong University)
  • Predicting Visual Context for Unsupervised Event Segmentation in Continuous Photo-Streams Ana García del Molino (Nanyang Technological University), Joo-Hwee Lim (A*STAR), Ah-Hwee Tan (Nanyang Technological University)
  • Video-to-Video Translation with Global Temporal Consistency Xingxing Wei (Tsinghua University), Jun Zhu (Tsinghua University), Sitong Feng (Macau University of Science and Technology), Hang Su (Tsinghua University)
  • Shared Linear Encoder-Based Gaussian Process Latent Variable Model for Visual Classification Jinxing Li (Hong Kong Polytechnic University), Bob Zhang (University of Macau), Guangming Lu (Harbin Institute of Technology Shenzhen Graduate School), David Zhang (Chinese University of Hong Kong (Shenzhen)
  • Step-by-Step Erasion, One-by-One Collection: A Weakly Supervised Temporal Action Detector Jia-Xing Zhong (Peking University), Nannan Li (Peking University), Weijie Kong (Peking University), Tao Zhang (Peking University), Thomas H. Li (Peking University), Ge Li (Peking University)
  • Multi-Human Parsing Machines Jianshu Li (National University of Singapore and SAP Machine Learning), Jian Zhao (National University of Singapore), Yunpeng Chen (National University of Singapore), Sujoy Roy (SAP Machine Learning), Shuicheng Yan (National University of Singapore), Jiashi Feng (National University of Singapore), Terence Sim (National University of Singapore)
  • Fast Parameter Adaptation for Few-Shot Image Captioning and Visual Question Answering Xuanyi Dong (Southern University of Science and Technology and University of Technology Sydney), Linchao Zhu (Southern University of Science and Technology and University of Technology Sydney), De Zhang (China Electronics Technology Group Corporation), Yi Yang (Southern University of Science and Technology and University of Technology Sydney), Fei Wu (Zhejiang University)
  • Hierarchical Memory Modelling for Video Captioning Junbo Wang (Center for Research on Intelligent Perception and Computing, NLPR, CASIA and University of Chinese Academy of Sciences), Wei Wang (Center for Research on Intelligent Perception and Computing, NLPR, CASIA and University of Chinese Academy of Sciences), Yan Huang (Center for Research on Intelligent Perception and Computing, NLPR, CASIA and University of Chinese Academy of Sciences), Liang Wang (Center for Research on Intelligent Perception and Computing, NLPR, and CEBSIT, CASIA and University of Chinese Academy of Sciences), Tieniu Tan (Center for Research on Intelligent Perception and Computing, NLPR, and CEBSIT, CASIA and University of Chinese Academy of Sciences)
  • Incremental Deep Hidden Attribute Learning Zheng Wang (National Institute of Informatics, Japan), Xiang Bai (Huazhong University of Science of Technology, China), Mang Ye (Hong Kong Baptist University, China), Shin’ichi Satoh (National Institute of Informatics, Japan and University of Tokyo)
  • CropNet: Real-Time Thumbnailing Huarong Chen (Tsinghua University), Bin Wang (Tsinghua University), Tianxiang Pan (Tsinghua University), Liwang Zhou (Tsinghua University), Hua Zeng (Tsinghua University)
  • Learning to Transfer: Generalizable Attribute Learning with Multitask Neural Model Search Zhi-Qi Cheng (Southwest Jiaotong University and Carnegie Mellon University), Xiao Wu (Southwest Jiaotong University), Siyu Huang (Zhejiang University and Carnegie Mellon University), Jun-Xiu Li (Southwest Jiaotong University), Alexander G. Hauptmann (Carnegie Mellon University), Qiang Peng (Southwest Jiaotong University)
  • Attention-Based Pyramid Aggregation Network for Visual Place Recognition Yingying Zhu (Shenzhen University), Jiong Wang (Shenzhen University), Lingxi Xie (Johns Hopkins University), Liang Zheng (Australian National University)
  • Semi-Supervised Deep Generative Modelling of Incomplete Multi-Modality Emotional Data Changde Du (Institute of Automation, Chinese Academy of Sciences), Changying Du (360 Search Lab), Hao Wang (360 Search Lab), Jinpeng Li (Institute of Automation, Chinese Academy of Sciences), Wei-Long Zheng (SJTU), Bao-Liang Lu (SJTU), Huiguang He (Institute of Automation, Chinese Academy of Sciences)
  • Twitter Sentiment Analysis via Bi-Sense Emoji Embedding and Attention-Based LSTM Yuxiao Chen (University of Rochester), Jianbo Yuan (University of Rochester), Quanzeng You (Microsoft Research AI), Jiebo Luo (University of Rochester)
  • Facial Expression Recognition in the Wild: A Cycle-Consistent Adversarial Attention Transfer Approach Feifei Zhang (Jiangsu University, Chinese Academy of Sciences), Tianzhu Zhang (Chinese Academy of Sciences and University of Chinese Academy of Sciences), Qirong Mao (Jiangsu University), Lingyu Duan ( Peking University), Changsheng Xu (Chinese Academy of Sciences and University of Chinese Academy of Sciences)
  • Inferring User Emotive State Changes in Realistic Human-Computer Conversational  Dialogs Runnan Li (Tsinghua University), Zhiyong Wu (Tsinghua University), Jia Jia (Tsinghua University), Jingbei Li (Tsinghua University), Wei Chen (Sogou, Inc.), Helen Meng (Chinese University of Hong Kong)
  • Self-Boosted Gesture Interactive System with ST-Net Zhengzhe Liu (DJI), Xiaojuan Qi (CUHK), Lei Pang (DJI)
  • Slackliner – An Interactive Slackline Training Assistant Felix Kosmalla (Saarland Informatics Campus | DFKI), Christian Murlowski (Saarland Informatics Campus), Florian Daiber (Saarland Informatics Campus | DFKI), Antonio Krüger (Saarland Informatics Campus | DFKI)
  • A Unified Generative Adversarial Framework for Image Generation and Person Re-Identification Yaoyu Li (Chinese Academy of Sciences and University of Chinese Academy of Sciences), Tianzhu Zhang (Chinese Academy of Sciences and University of Chinese Academy of Sciences), Lingyu Duan (Peking University), Changsheng Xu (Chinese Academy of Sciences and University of Chinese Academy of Sciences)
  • FoV-Aware Edge Caching for Adaptive 360° Video Streaming Anahita Mahzari (University of Texas at Dallas), Afshin Taghavi Nasrabadi (University of Texas at Dallas), Aliehsan Samiei (University of Texas at Dallas), Ravi Prakash (University of Texas at Dallas)

13:30 – 14:00 Crystal Ballroom 1-3

Fast Forward 2

  • Style Separation and Synthesis via Generative Adversarial Networks Rui Zhang (Chinese Academy of Sciences and University of Chinese Academy of Sciences), Sheng Tang (Chinese Academy of Sciences), Yu Li (Chinese Academy of Sciences and University of Chinese Academy of Sciences), Junbo Guo (Chinese Academy of Sciences), Yongdong Zhang (Chinese Academy of Sciences), Jintao Li (Chinese Academy of Sciences), Shuicheng Yan (Qihoo 360 Artificial Intelligence Institute and National University of Singapore)
  • Group Re-Identification: Leveraging and Integrating Multi-Grain Information Hao Xiao (Shanghai Jiao Tong University), Weiyao Lin (Shanghai Jiao Tong University), Bin Sheng (Shanghai Jiao Tong University), Ke Lu (University of Chinese Academy of Sciences), Junchi Yan (Shanghai Jiao Tong University), Jingdong Wang (Microsoft Research), Errui Ding (Baidu Inc.), Yihao Zhang (Tencent YouTu Lab), Hongkai Xiong (Shanghai Jiao Tong University)
  • OSMO: Online Specific Models for Occlusion in Multiple Object Tracking under Surveillance Scene Xu Gao (Peking University), Tingting Jiang (Peking University)
  • Video Forecasting with Forward-Backward-Net: Delving Deeper into Spatiotemporal Consistency Yuke Li (York University)
  • Feature Constrained by Pixel: Hierarchical Adversarial Deep Domain Adaptation Rui Shao (Hong Kong Baptist University), Xiangyuan Lan (Hong Kong Baptist University), Pong C. Yuen (Hong Kong Baptist University)
  • Fast and Light Manifold CNN based 3D Facial Expression Recognition across Pose Variations Zhixing Chen (Beihang University), Di Huang (Beihang University), Yunhong Wang (Beihang University), Liming Chen (Beihang University; LIRIS, Ecole Centrale de Lyon)
  • Explore Multi-Step Reasoning in Video Question Answering Xiaomeng Song (Tianjin University), Yucheng Shi (Tianjin University), Xin Chen (Tianjin University), Yahong Han (Tianjin University)
  • Attention and Language Ensemble for Scene Text Recognition with Convolutional Sequence Modeling Shancheng Fang (Institute of Information Engineering, Chinese Academy of Sciences and University of Chinese Academy of Sciences), Hongtao Xie (University of Science and Technology of China), Zheng-Jun Zha (University of Science and Technology of China), Nannan Sun (Institute of Information Engineering, Chinese Academy of Sciences and University of Chinese Academy of Sciences), Jianlong Tan (Institute of Information Engineering, Chinese Academy of Sciences and University of Chinese Academy of Sciences), Yongdong Zhang (University of Science and Technology of China)
  • Temporal Sequence Distillation: Towards Few-Frame Action Recognition in Videos Zhaoyang Zhang (Wuhan University and SenseTime Research), Zhanghui Kuang (Sensetime Research), Ping Luo (Chinese University of Hong Kong), Litong Feng (Sensetime Research), Wei Zhang (Sensetime Research)
  • Previewer for Multi-Scale Object Detector Zhihang Fu (Zhejiang University), Zhongming Jin (Alibaba Group), Guo-Jun Qi (University of Central Florida), Chen Shen (Zhejiang University), Rongxin Jiang (Zhejiang University), Yaowu Chen (Zhejiang University), Xian-Sheng Hua (Alibaba Group)
  • Learning Discriminative Features with Multiple Granularities for Person Re-Identification Guanshuo Wang (Shanghai Jiao Tong University), Yufeng Yuan (CloudWalk Technology), Xiong Chen (CloudWalk Technology), Jiwei Li (CloudWalk Technology), Xi Zhou (Shanghai Jiao Tong University and CloudWalk Technology)
  • StripNet: Towards Topology Consistent Strip Structure Segmentation Guoxiang Qu (Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences), Wenwei Zhang (Sensetime Group Limited), Zhe Wang (Sensetime Group Limited), Xing Dai (Sensetime Group Limited), Jianping Shi (Sensetime Group Limited), Junjun He (Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences), Fei Li (Zhongshan Ophthalmic Center, State Key Laboratory of Ophthalmology, Sun Yat-Sen University), Xiulan Zhang (Zhongshan Ophthalmic Center, State Key Laboratory of Ophthalmology, Sun Yat-Sen University), Yu Qiao (Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences)
  • Emotion Recognition in Speech using Cross-Modal Transfer in the Wild Samuel Albanie (University of Oxford), Arsha Nagrani (University of Oxford), Andrea Vedaldi (University of Oxford), Andrew Zisserman (University of Oxford)
  • Personalized Multiple Facial Action Unit Recognition through Generative Adversarial Recognition Network Can Wang (University of Science and Technology of China), Shangfei Wang (University of Science and Technology of China)
  • Investigation of Small Group Social Interactions Using Deep Visual Activity-Based Nonverbal Features Cigdem Beyan (Istituto Italiano di Tecnologia), Muhammad Shahid (Istituto Italiano di Tecnologia and University of Genoa), Vittorio Murino (Istituto Italiano di Tecnologia and University of Verona)
  • Cross-Species Learning: A Low-Cost Approach to Learning Human Fight from Animal Fight Eugene Yujun Fu (Hong Kong Polytechnic University), Michael Xuelin Huang (Max Planck Institute for Informatics, Saarland Informatics Campus), Hong Va Leong (Hong Kong Polytechnic University), Grace Ngai (Hong Kong Polytechnic University)
  • Personalized Serious Games for Cognitive Intervention with Lifelog Visual Analytics Qianli Xu (Institute for Infocomm Research, A*STAR), Vigneshwaran Subbaraju (Singapore Bioimaging Consortium, A*STAR), Chee How Cheong (SP Design School), Aijing Wang (National University of Singapore), Kathleen Kang (National University of Singapore), Munirah Bashir (National University of Singapore), Yanhong Dong (National University of Singapore), Liyuan Li (Institute for Infocomm Research, A*STAR), Joo-Hwee Lim (Institute for Infocomm Research, A*STAR)
  • Drawing in a Virtual 3D Space – Introducing VR Drawing in Elementary School Art Education Wendy Bolier (Utrecht University and ING Bank N.V.), Wolfgang Hürst (Utrecht University), Guido van Bommel (ING Bank N.V.), Joost Bosman (ING Bank N.V.), Harriët Bosman (KLEURinCULTUUR)
  • CIRCE: Real-Time Caching for Instance Recognition on Cloud Environments and Multi-Core Architectures Luca Lovagnini (University of Pisa), Wenxiao Zhang (Hong Kong University of Science and Technology), Farshid Hassani Bijarbooneh (Hong Kong University of Science and Technology), Pan Hui (University of Helsinki and Hong Kong University of Science and Technology)
  • Jaguar: Low Latency Mobile Augmented Reality with Flexible Tracking Wenxiao Zhang (Hong Kong University of Science and Technology), Bo Han (AT&T Labs — Research), Pan Hui (University of Helsinki and Hong Kong University of Science and Technology)

Wednesday 24 October – Conference Day 3

8:30 – 9:00 Crystal Ballroom 1-3

Fast Forward 3

  • High-Quality Exposure Correction of Underexposed Photos Qing Zhang (Sun Yat-sen University), Ganzhao Yuan (Sun Yat-sen University), Chunxia Xiao (Wuhan University), Lei Zhu (Chinese University of Hong Kong), Wei-Shi Zheng (Sun Yat-sen University and Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education, China)
  • A Margin-Based MLE for Crowdsourced Partial Ranking Qianqian Xu (Chinese Academy of Sciences), Jiechao Xiong (Tencent AI Lab), Xinwei Sun (Peking University and DeepWise AI Lab), Zhiyong Yang (Chinese Academy of Sciences), Xiaochun Cao (Chinese Academy of Sciences), Qingming Huang (University of Chinese Academy of Sciences), Yuan Yao (Hong Kong University of Science and Technology)
  • PHD-GIFs: Personalized Highlight Detection for Automatic GIF Creation  Ana García del Molino (Nanyang Technological University), Michael Gygli (Google Research)
  • Cross-Domain Adversarial Feature Learning for Sketch Re-Identification Lu Pang (Peking University Shenzhen Graduate School and Peking University), Yaowei Wang (Beijing Institute of Technology), Yi-Zhe Song (Queen Mary University of London), Tiejun Huang (Peking University Shenzhen Graduate School and Peking University), Yonghong Tian (Peking University Shenzhen Graduate School and Peking University)
  • Semantic Human Matting Quan Chen (Alibaba Group), Tiezheng Ge (Alibaba Group), Yanyu Xu (Alibaba Group and ShanghaiTech University), Zhiqiang Zhang (Alibaba Group), Xinxin Yang (Alibaba Group), Kun Gai (Alibaba Group)
  • Geometry Guided Adversarial Facial Expression Synthesis Lingxiao Song (CASIA), Zhihe Lu (CAS and University of Chinese Academy of Sciences), Ran He (CASIA, CAS, and University of Chinese Academy of Sciences), Zhenan Sun (CASIA, CAS, and University of Chinese Academy of Sciences), Tieniu Tan (CASIA, CAS, and University of Chinese Academy of Sciences)
  • Detecting Abnormality without Knowing Normality: A Two-Stage Approach for Unsupervised Video Abnormal Event Detection Siqi Wang (National University of Defense Technology), Yijie Zeng (Nanyang Technological University), Qiang Liu (National University of Defense Technology), Chengzhang Zhu (National University of Defense Technology), En Zhu (National University of Defense Technology), Jianping Yin (Dongguan University of Technology)
  • BeautyGAN: Instance-Level Facial Makeup Transfer with Deep Generative Adversarial Network Tingting Li (Tsinghua University), Ruihe Qian (Chinese Academy of Sciences), Chao Dong (Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences), Si Liu (Beihang University), Qiong Yan (SenseTime Research), Wenwu Zhu (Tsinghua University), Liang Lin (Sun Yat-sen University)
  • Trusted Guidance Pyramid Network for Human Parsing Xianghui Luo (Sun Yat-sen University), Zhuo Su (Sun Yat-sen University), Jiaming Guo (Sun Yat-sen University), Gengwei Zhang (Sun Yat-sen University), Xiangjian He (University of Technology Sydney)
  • I Read, I Saw, I Tell: Texts Assisted Fine-Grained Visual Classification Jingjing Li (University of Electronic Science and Technology of China), Lei Zhu (Shandong Normal University), Zi Huang (University of Queensland), Ke Lu (University of Electronic Science and Technology of China), Jidong Zhao (University of Electronic Science and Technology of China)
  • Look Deeper See Richer: Depth-Aware Image Paragraph Captioning Ziwei Wang (University of Queensland), Yadan Luo (University of Queensland), Yang Li (University of Queensland), Zi Huang (University of Queensland), Hongzhi Yin (University of Queensland)
  • Learning Multimodal Taxonomy via Variational Deep Graph Embedding and Clustering Huaiwen Zhang (Chinese Academy of Sciences and University of Chinese Academy of Sciences), Quan Fang (Chinese Academy of Sciences and University of Chinese Academy of Sciences), Shengsheng Qian (Chinese Academy of Sciences and University of Chinese Academy of Sciences), Changsheng Xu (Chinese Academy of Sciences and University of Chinese Academy of Sciences)
  • Watch, Think and Attend: End-to-End Video Classification via Dynamic Knowledge Evolution Modeling Junyu Gao (Chinese Academy of Sciences and University of Chinese Academy of Sciences), Tianzhu Zhang (Chinese Academy of Sciences and University of Chinese Academy of Sciences), Changsheng Xu (Chinese Academy of Sciences and University of Chinese Academy of Sciences)
  • Multi-Label Image Classification via Knowledge Distillation from Weakly-Supervised Detection Yongcheng Liu (Chinese Academy of Sciences and University of Chinese Academy of Sciences), Lu Sheng (Chinese University of Hong Kong), Jing Shao (SenseTime Research), Junjie Yan (SenseTime Research), Shiming Xiang (Chinese Academy of Sciences and University of Chinese Academy of Sciences), Chunhong Pan (Chinese Academy of Sciences)
  • Unregularized Auto-Encoder with Generative Adversarial Networks for Image Generation Jiayu Wang (University of Science and Technology of China), Wengang Zhou (University of Science and Technology of China), Jinhui Tang (Nanjing University of Science and Technology), Zhongqian Fu (University of Science and Technology of China), Qi Tian (Huawei Noah’s Ark Lab and University of Texas at San Antonio), Houqiang Li (University of Science and Technology of China)
  • When to Learn What: Deep Cognitive Subspace Clustering Yangbangyan Jiang (Institute of Information Engineering, Chinese Academy of Sciences and University of Chinese Academy of Sciences), Zhiyong Yang (Institute of Information Engineering, Chinese Academy of Sciences and University of Chinese Academy of Sciences), Qianqian Xu (Institute of Computing Technology, Chinese Academy of Sciences), Xiaochun Cao (Institute of Information Engineering, Chinese Academy of Sciences and University of Chinese Academy of Sciences), Qingming Huang (Institute of Computing Tech., CAS and University of Chinese Academy of Sciences and Key Lab of Big Data Mining and Knowledge Management, CAS)
  • Depth Structure Preserving Scene Image Generation Wendong Zhang (Shanghai Jiao Tong University), Feng Gao (Peking University), Bingbing Ni (Shanghai Jiao Tong University), Lingyu Duan (Peking University), Yichao Yan (Shanghai Jiao Tong University), Jingwei Xu (Shanghai Jiao Tong University), Xiaokang Yang (Shanghai Jiao Tong University)
  • CA3Net: Contextual-Attentional Attribute-Appearance Network for Person Re-Identification Jiawei Liu (University of Science and Technology of China), Zheng-Jun Zha (University of Science and Technology of China), Hongtao Xie (University of Science and Technology of China), Zhiwei Xiong (University of Science and Technology of China), Yongdong Zhang (University of Science and Technology of China)
  • RGCNN: Regularized Graph CNN for Point Cloud Segmentation Gusi Te (Peking University), Wei Hu (Peking University), Amin Zheng (MTlab, Meitu Inc.), Zongming Guo (Peking University)
  • Deep Priority Hashing Zhangjie Cao (Tsinghua University), Ziping Sun (Tsinghua University), Mingsheng Long (Tsinghua University), Jianmin Wang (Tsinghua University), Philip S. Yu (Tsinghua University)

13:30 – 15:00 Crystal Ballroom 1-3

Fast Forward 4

  • Learning Semantic Structure-Preserved Embeddings for Cross-Modal Retrieval Yiling Wu (Chinese Academy of Sciences), Shuhui Wang (Chinese Academy of Sciences), Qingming Huang (Chinese Academy of Sciences and University of Chinese Academy of Sciences)
  • Post Tuned Hashing: A New Approach to Indexing High-Dimensional Data Zhendong Mao (Chinese Academy of Sciences), Quan Wang (Chinese Academy of Sciences), Yongdong Zhang (Chinese Academy of Sciences), Bin Wang (Chinese Academy of Sciences)
  • Cross-Modal Moment Localization in Videos Meng Liu (Shandong University), Xiang Wang (National University of Singapore), Liqiang Nie (Shandong University), Qi Tian (Huawei Noah’s Ark Lab and University of Texas at San Antonio), Baoquan Chen (Peking University and Shandong University), Tat-Seng Chua (National University of Singapore)
  • Multi-Scale Correlation for Sequential Cross-Modal Hashing Learning Zhaoda Ye (Peking University), Yuxin Peng (Peking University)
  • Generative Adversarial Product Quantisation Litao Yu (Griffith University), Yongsheng Gao (Griffith University), Jun Zhou (Griffith University)
  • Aesthetic-Driven Image Enhancement by Adversarial Learning Yubin Deng (Chinese University of Hong Kong), Chen Change Loy (Nanyang Technological University), Xiaoou Tang (Chinese University of Hong Kong)
  • Attention-Based Multi-Patch Aggregation for Image Aesthetic Assessment Kekai Sheng (NLPR, Institute of Automation, Chinese Academy of Sciences and University of Chinese Academy of Sciences), Weiming Dong (NLPR, Institute of Automation, Chinese Academy of Sciences), Chongyang Ma (Snap Inc.), Xing Mei (Snap Inc.), Feiyue Huang (Tencent), Bao-Gang Hu (NLPR, Institute of Automation, Chinese Academy of Sciences)
  • An End-to-End Quadrilateral Regression Network for Comic Panel Extraction Zheqi He (Peking University), Yafeng Zhou (Peking University), Yongtao Wang (Peking University), Siwei Wang (Peking University), Xiaoqing Lu (Peking University), Zhi Tang (Peking University), Ling Cai (Alibaba AI Lab)
  • Monocular Camera Based Real-Time Dense Mapping Using Generative Adversarial Network Xin Yang (Huazhong University of Science and Technology), Jinyu Chen (Huazhong University of Science and Technology), Zhiwei Wang (Huazhong University of Science and Technology), Qiaozhe Zhang (Huazhong University of Science and Technology), Wenyu Liu (Huazhong University of Science and Technology), Chunyuan Liao (Huazhong University of Science and Technology), Kwang-Ting Cheng (Hong Kong University of Science and Technology)
  • JPEG Decompression in the Homomorphic Encryption Domain Xiaojing Ma (Huazhong University of Science and Technology), Changming Liu (Huazhong University of Science and Technology), Sixing Cao (Huazhong University of Science and Technology), Bin B. Zhu (Microsoft Research Asia)
  • MiniView Layout for Bandwidth-Efficient 360-Degree Video Mengbai Xiao (George Mason University), Shuoqian Wang (SUNY Binghamton), Chao Zhou (SUNY Binghamton), Li Liu (George Mason University), Zhenhua Li (Tsinghua University), Yao Liu (SUNY Binghamton), Songqing Chen (George Mason University)
  • Real-Time 3D Face-Eye Performance Capture of a Person Wearing VR Headset Guoxian Song (Nanyang Technological University), Jianfei Cai (Nanyang Technological University), Tat-Jen Cham (Nanyang Technological University), Jianmin Zheng (Nanyang Technological University), Juyong Zhang (Nanyang Technological University), Henry Fuchs (University of North Carolina at Chapel Hill)
  • Bridge the Gap Between VQA and Human Behavior on Omnidirectional Video: A Large-Scale Dataset and a Deep Learning Model Chen Li (Beihang University (BUAA)), Mai Xu (Beihang University (BUAA)), Xinzhe Du (Beihang University (BUAA)), Zulin Wang (Beihang University (BUAA))
  • Tracking-Assisted Weakly Supervised Online Visual Object Segmentation in Unconstrained Videos Zongpu Zhang (Shanghai Jiao Tong University), Yang Hua (Queen’s University Belfast), Tao Song (Shanghai Jiao Tong University), Zhengui Xue (Ulster University and Shanghai Jiao Tong University), Ruhui Ma (Shanghai Jiao Tong University), Neil Robertson (Queen’s University Belfast), Haibing Guan (Shanghai Jiao Tong University)
  • ThoughtViz: Visualizing Human Thoughts Using Generative Adversarial Network Praveen Tirupattur (University of Central Florida), Yogesh Singh Rawat (University of Central Florida), Concetto Spampinato (University of Catania), Mubarak Shah (University of Central Florida)
  • A Feature-Adaptive Semi-Supervised Framework for Co-Saliency Detection Xiaoju Zheng (Chinese Academy of Sciences and University of Science and Technology of China), Zheng-Jun Zha (University of Science and Technology of China), Liansheng Zhuang (University of Science and Technology of China)
  • iSPA-Net: Iterative Semantic Pose Alignment Network Jogendra Nath Kundu (Indian Institute of Science), Aditya Ganeshan (Indian Institute of Science), Rahul M. V. (Indian Institute of Science), Aditya Prakash (Indian Institute of Science), Venkatesh Babu R. (Indian Institute of Science)
  • Extractive Video Summarizer with Memory Augmented Neural Networks Litong Feng (SenseTime Research), Ziyin Li (SenseTime Research), Zhanghui Kuang (SenseTime Research), Wei Zhang (SenseTime Research)
  • Fully Point-Wise Convolutional Neural Network for Modeling Statistical Regularities in Natural Images Jing Zhang (Hangzhou Dianzi University), Yang Cao (University of Science and Technology of China), Yang Wang (University of Science and Technology of China), Chenglin Wen (Hangzhou Dianzi University), Chang Wen Chen (University at Buffalo, State University of New York)
  • Online Action Tube Detection via Resolving the Spatio-Temporal Context Pattern Jingjia Huang (Peking University), Nannan Li (Peking University Shenzhen Graduate School), Jiaxing Zhong (Peking University), Thomas H. Li (Gpower Semiconductor Inc.), Ge Li (Peking University)
  • Enhancing Visual Question Answering Using Dropout Zhiwei Fang (Institute of Automation, Chinese Academy of Sciences and University of Chinese Academy of Sciences), Jing Liu (Institute of Automation, Chinese Academy of Sciences and University of Chinese Academy of Sciences), Yanyuan Qiao (University of Chinese Academy of Sciences), Qu Tang (Institute of Automation, Chinese Academy of Sciences), Yong Li (Business Growth BU, JD.com), Hanqing Lu (Institute of Automation, Chinese Academy of Sciences and University of Chinese Academy of Sciences)
  • Face-Voice Matching using Cross-Modal Embeddings Shota Horiguchi (Hitachi, Ltd.), Naoyuki Kanda (Hitachi, Ltd.), Kenji Nagamatsu (Hitachi, Ltd.)
  • Deep Understanding of Cooking Procedure for Cross-Modal Recipe Retrieval Jing-Jing Chen (City University of Hong Kong), Chong-Wah Ngo (City University of Hong Kong), Fu-Li Feng (National University of Singapore), Tat-Seng Chua (National University of Singapore)
  • Decoupled Novel Object Captioner Yu Wu (University of Technology Sydney), Linchao Zhu (University of Technology Sydney), Lu Jiang (Google Inc.), Yi Yang (University of Technology Sydney and Chinese Academy of Sciences)
  • Temporal Cross-Media Retrieval with Soft-Smoothing David Semedo (Universidade NOVA de Lisboa), Joao Magalhaes (Universidade NOVA de Lisboa)
  • Photo Squarization by Deep Multi-Operator Retargeting Yu Song (Chinese Academy of Sciences and University of Chinese Academy of Sciences), Fan Tang (Chinese Academy of Sciences and University of Chinese Academy of Sciences), Weiming Dong (Chinese Academy of Sciences), Xiaopeng Zhang (Chinese Academy of Sciences), Oliver Deussen (VCC SIAT Shenzhen and University of Konstanz), Tong-Yee Lee (National Cheng-Kung University)
  • Non-Locally Enhanced Encoder-Decoder Network for Single Image De-Raining Guanbin Li (Sun Yat-sen University), Xiang He (Sun Yat-sen University), Wei Zhang (Sun Yat-sen University), Huiyou Chang (Sun Yat-sen University), Le Dong (University of Electronic Science and Technology of China), Liang Lin (Sun Yat-sen University)
  • An ADMM-Based Universal Framework for Adversarial Attacks on Deep Neural Networks Pu Zhao (Northeastern University), Sijia Liu (IBM Research AI), Yanzhi Wang (Northeastern University), Xue Lin (Northeastern University)
  • Local Convolutional Neural Networks for Person Re-Identification Jiwei Yang (University of Science and Technology of China), Xu Shen (Alibaba Group), Xinmei Tian (University of Science and Technology of China), Houqiang Li (University of Science and Technology of China), Jianqiang Huang (Alibaba Group), Xian-Sheng Hua (Alibaba Group)
  • Conditional Expression Synthesis with Face Parsing Transformation Zhihe Lu (Institute of Automation, Chinese Academy of Sciences), Tanhao Hu (Institute of Automation, Chinese Academy of Sciences), Lingxiao Song (Institute of Automation, Chinese Academy of Sciences and Boomhope Information and Technology Co., Ltd.), Zhaoxiang Zhang (Institute of Automation, Chinese Academy of Sciences), Ran He (Institute of Automation, Chinese Academy of Sciences)
  • Attentive Recurrent Neural Network for Weak-Supervised Multi-Label Image Classification Liang Li (Chinese Academy of Sciences), Shuhui Wang (Chinese Academy of Sciences), Shuqiang Jiang (Chinese Academy of Sciences and University of Chinese Academy of Sciences), Qingming Huang (Chinese Academy of Sciences and University of Chinese Academy of Sciences)
  • Deep Cross Modal Learning for Caricature Verification and Identification (CaVINet) Jatin Garg (Indian Institute of Technology Ropar), Skand Vishwanath Peri (Indian Institute of Technology Ropar), Himanshu Tolani (Indian Institute of Technology Ropar), Narayanan C. Krishnan (Indian Institute of Technology Ropar)
  • Few-Shot Adaptation for Multimedia Semantic Indexing Nakamasa Inoue (Tokyo Institute of Technology), Koichi Shinoda (Tokyo Institute of Technology)
  • Fashion Sensitive Clothing Recommendation Using Hierarchical Collocation Model Zhengzhong Zhou (Shanghai Jiao Tong University), Xiu Di (Shanghai Jiao Tong University), Wei Zhou (Shanghai Jiao Tong University), Liqing Zhang (Shanghai Jiao Tong University)
  • Multi-Scale Context Attention Network for Image Retrieval Yihang Lou (Peking University), Yan Bai (Peking University), Shiqi Wang (City University of Hong Kong), Ling-Yu Duan (Peking University)
  • Comprehensive Distance-Preserving Autoencoders for Cross-Modal Retrieval Yibing Zhan (Hangzhou Dianzi University), Jun Yu (Hangzhou Dianzi University), Zhou Yu (Hangzhou Dianzi University), Rong Zhang (University of Science and Technology of China), Dacheng Tao (University of Sydney), Qi Tian ( Huawei Noah’s Ark Lab and University of Texas at San Antonio)
  • Temporal Hierarchical Attention at Category- and Item-Level for Micro-Video Click-Through Prediction Xusong Chen (University of Science and Technology of China), Dong Liu (University of Science and Technology of China), Zheng-Jun Zha (University of Science and Technology of China), Wengang Zhou (University of Science and Technology of China), Zhiwei Xiong (University of Science and Technology of China), Yan Li (University of Science and Technology of China)
  • Historical Context-Based Style Classification of Painting Images via Label Distribution Learning Jufeng Yang (Nankai University), Liyi Chen (Nankai University), Le Zhang (Advanced Digital Sciences Center, Illinois at Singapore), Xiaoxiao Sun (Nankai University), Dongyu She (Nankai University), Shao-Ping Lu (Nankai University), Ming-Ming Cheng (Nankai University)
  • Direction-Aware Neural Style Transfer Hao Wu (Nanjing University), Zhengxing Sun (Nanjing University), Weihang Yuan (Nanjing University)
  • ChipGAN: A Generative Adversarial Network for Chinese Ink Wash Painting Style Transfer Bin He (Peking University), Feng Gao (Tsinghua University), Daiqian Ma (Peking University), Boxin Shi (Peking University), Ling-Yu Duan (Peking University)
  • CloudVR: Cloud Accelerated Interactive Mobile Virtual Reality Teemu Kämäräinen (Aalto University), Matti Siekkinen (Aalto University), Jukka Eerikäinen (Aalto University), Antti Ylä-Jääski (Aalto University)
  • Your Attention is Unique: Detecting 360-Degree Video Saliency in Head-Mounted Display for Head Movement Prediction Anh Nguyen (Georgia State University), Zhisheng Yan (Georgia State University), Klara Nahrstedt (University of Illinois at Urbana-Champaign)
  • Hybrid Point Cloud Attribute Compression Using Slice-Based Layered Structure and Block-Based Intra Prediction Yiting Shao (Peking University), Qi Zhang (Peking University), Ge Li (Peking University), Zhu Li (University of Missouri-Kansas City), Li Li (University of Missouri-Kansas City)
  • QARC: Video Quality Aware Rate Control for Real-Time Video Streaming based on Deep Reinforcement Learning Tianchi Huang (Guizhou University and Tsinghua University), Rui-Xiao Zhang (Tsinghua University), Chao Zhou (Beijing Kuaishou Technology Co., Ltd.), Lifeng Sun (Tsinghua University)
  • Optimizing Personalized Interaction Experience in Crowd-Interactive Livecast: A Cloud-Edge Approach Haitian Pang (Tsinghua University and Simon Fraser University), Cong Zhang (Simon Fraser University), Fangxin Wang (Simon Fraser University), Han Hu (Beijing Institute of Technology), Zhi Wang (Graduate School at Shenzhen, Tsinghua University), Jiangchuan Liu (Simon Fraser University), Lifeng Sun (Tsinghua University)

Thursday 25 October – Conference Day 4

8:30 – 9:00 Crystal Ballroom 1-3

Fast Forward 5

  • Online Inter-Camera Trajectory Association Exploiting Person Re-Identification and Camera Topology Na Jiang (Beihang University), SiChen Bai (Beihang University), Yue Xu (Beihang University), Chang Xing (Beihang University), Zhong Zhou (Beihang University), Wei Wu (Beihang University)
  • Learning Local Descriptors with Adversarial Enhancer from Volumetric Geometry Patches Jing Zhu (New York University), Yi Fang (New York University Abu Dhabi)
  • Context-Dependent Diffusion Network for Visual Relationship Detection Zhen Cui (Nanjing University of Science and Technology), Chunyan Xu (Nanjing University of Science and Technology), Wenming Zheng (Southeast University), Jian Yang (Nanjing University of Science
    and Technology)
  • Connectionist Temporal Fusion for Sign Language Translation Shuo Wang (Hefei University of Technology), Dan Guo (Hefei University of Technology), Wen-gang Zhou (University of Science and Technology of China), Zheng-Jun Zha (University of Science and Technology of China), Meng Wang (Hefei University of Technology)
  • Support Neighbor Loss for Person Re-Identification Kai Li (Northeastern University), Zhengming Ding (Indiana University-Purdue University), Kunpeng Li (Northeastern University), Yulun Zhang (Northeastern University), Yun Fu (Northeastern University)
  • Perceptual Temporal Incoherence Aware Stereo Video Retargeting Bing Li (University of Southern California), Chia-Wen Lin (National Tsing Hua University), Shan Liu (Tencent America LLC), Tiejun Huang (Peking University), Wen Gao (Peking University), C.-C. Jay Kuo (University of Southern California)
  • A Large-Scale RGB-D Database for Arbitrary-View Human Action Recognition Yanli Ji (University of Electronic Science and Technology of China), Feixiang Xu (University of Electronic Science and Technology of China), Yang Yang (University of Electronic Science and Technology of China), Fumin Shen (University of Electronic Science and Technology of China), Heng Tao Shen (University of Electronic Science and Technology of China), Wei-Shi Zheng (Sun Yat-sen University)
  • Spotting and Aggregating Salient Regions for Video Captioning Huiyun Wang (Tianjin University), Youjiang Xu (Tianjin University), Yahong Han (Tianjin University)
  • Adaptive Temporal Encoding Network for Video Instance-Level Human Parsing Qixian Zhou (Sun Yat-sen University), Xiaodan Liang (Carnegie Mellon University), Ke Gong (Sun Yat-sen University), Liang Lin (Sun Yat-sen University)
  • User-Guided Deep Anime Line Art Colorization with Conditional Adversarial Networks Yuanzheng Ci (Dalian University of Technology), Xinzhu Ma (Dalian University of Technology), Zhihui Wang (Dalian University of Technology), Haojie Li (Dalian University of Technology), Zhongxuan Luo (Dalian University of Technology)
  • BitStream: Efficient Computing Architecture for Real-Time Low-Power Inference of Binary Neural Networks on CPUs Tianli Zhao (Institute of Automation, Chinese Academy of Sciences), Xiangyu He (Institute of Automation, Chinese Academy of Sciences), Jian Cheng (Institute of Automation, Chinese Academy of Sciences), Jing Hu (Power Research Institute of State Gride, Jiangxi Electric Power Company)
  • Attentive Crowd Flow Machines Lingbo Liu (Sun Yat-sen University), Ruimao Zhang (Chinese University of Hong Kong), Jiefeng Peng (Sun Yat-sen University), Guanbin Li (Sun Yat-sen University), Bowen Du (Beihang University), Liang Lin (Sun Yat-sen University)
  • Video-Based Person Re-Identification via Self-Paced Learning and Deep Reinforcement Learning Framework Deqiang Ouyang (University of Electronic Science and Technology of China), Jie Shao (University of Electronic Science and Technology of China), Yonghui Zhang (University of Electronic Science and Technology of China), Yang Yang (University of Electronic Science and Technology of China), Heng Tao Shen (University of Electronic Science and Technology of China)
  • Interpretable Multimodal Retrieval for Fashion Products Lizi Liao (National University of Singapore), Xiangnan He (National University of Singapore), Bo Zhao (University of British Columbia), Chong-Wah Ngo (City University of Hong Kong), Tat-Seng Chua (National University of Singapore)
  • Generating Defensive Plays in Basketball Games Chieh-Yu Chen (National Chiao Tung University), Wenze Lai (National Chiao Tung University), Hsin-Ying Hsieh (National Chiao Tung University), Wen-Hao Zheng (National Chiao Tung University), Yu-Shuen Wang (National Chiao Tung University), Jung-Hong Chuang (National Chiao Tung University)
  • Dense Auto-Encoder Hashing for Robust Cross-Modality Retrieval Hong Liu (Xiamen University), Mingbao Lin (Xiamen University), Shengchuan Zhang (Xiamen University), Yongjian Wu (Tencent Youtu Lab, Tencent Technology (Shanghai) Co., Ltd.), Feiyue Huang (Tencent Youtu Lab, Tencent Technology (Shanghai) Co., Ltd.), Rongrong Ji (Xiamen University)
  • Dance with Melody: An LSTM-Autoencoder Approach to Music-Oriented Dance Synthesis Taoran Tang (Tsinghua University), Jia Jia (Tsinghua University), Hanyang Mao (Tsinghua University)
  • Musicality-Novelty Generative Adversarial Nets for Algorithmic Composition Gong Chen (Hong Kong Polytechnic University), Yan Liu (Hong Kong Polytechnic University), Sheng-hua Zhong (Shenzhen University), Xiang Zhang (Hong Kong Polytechnic University)
  • Improving QoE of ABR Streaming Sessions through QUIC Retransmissions Divyashri Bhat (University of Massachusetts, Amherst), Rajvardhan Deshmukh (University of Massachusetts, Amherst), Michael Zink (University of Massachusetts, Amherst)
  • From Data to Knowledge: Deep Learning Model Compression, Transmission and Communication Ziqian Chen (Peking University), Shiqi Wang ( City University of Hong Kong), Dapeng Oliver Wu (University of Florida), Tiejun Huang (Peking University), Ling-Yu Duan (Peking University)

13:30 – 14:00 Crystal Ballroom 1-3

Fast Forward 6

  • Examine before You Answer: Multi-Task Learning with Adaptive-Attentions for Multiple-Choice VQA Lianli Gao (University of Electronic Science and Technology of China), Pengpeng Zeng (University of Electronic Science and Technology of China), Jingkuan Song (University of Electronic Science and Technology of China), Xianglong Liu (Beihang University), Heng Tao Shen (University of Electronic Science and Technology of China)
  • Residual-Guide Network for Single Image Deraining Zhiwen Fan (Xiamen University), Huafeng Wu (Xiamen University), Xueyang Fu (Xiamen University), Yue Huang (Xiamen University), Xinghao Ding (Xiamen University)
  • From Volcano to Toyshop: Adaptive Discriminative Region Discovery for Scene Recognition Zhengyu Zhao (Radboud University), Martha Larson (Radboud University and TU Delft)
  • The Effect of Foveation on High Dynamic Range Video Perception Joshua Sowerby (University of Bristol), Yang Zhang (University of Bristol), Dimitris Agrafiotis (University of Bristol)
  • An Efficient Deep Quantized Compressed Sensing Coding Framework of Natural Images Wenxue Cui (Harbin Institute of Technology), Feng Jiang (Harbin Institute of Technology), Xinwei Gao (Harbin Institute of Technology), Shengping Zhang (Harbin Institute of Technology), Debin Zhao (Harbin Institute of Technology)
  • PoB: Toward Reasoning Patterns of Beauty in Image Data Diep Thi Ngoc Nguyen (University of Engineering and Technology, Vietnam National University), Hideki Nakayama (National Institute of Advanced Industrial Science and Technology and University of Tokyo), Naoaki Okazaki (National Institute of Advanced Industrial Science and Technology and Tokyo Institute of Technology), Tatsuya Sakaeda (National Institute of Advanced Industrial Science and Technology)
  • Partial Multi-View Subspace Clustering Nan Xu (Dalian University of Technology), Yanqing Guo (Dalian University of Technology), Xin Zheng (Dalian University of Technology), Qianyu Wang (Dalian University of Technology), Xiangyang Luo (State Key Laboratory of Mathematical Engineering and Advanced Computing)
  • Pseudo Transfer with Marginalized Corrupted Attribute for Zero-Shot Learning Teng Long (University of Electronic Science and Technology of China), Xing Xu (University of Electronic Science and Technology of China), Youyou Li (University of Electronic Science and Technology of China), Fumin Shen (University of Electronic Science and Technology of China), Jingkuan Song (University of Electronic Science and Technology of China), Heng Tao Shen (University of Electronic Science and Technology of China)
  • Semi-Supervised DFF: Decoupling Detection and Feature Flow for Video Object Detectors Guangxing Han (Tsinghua University), Xuan Zhang (Tsinghua University), Chongrong Li (Tsinghua University)
  • Unsupervised Learning of 3D Model Reconstruction from Hand-Drawn Sketches Lingjing Wang (New York University), Cheng Qian (New York University), Jifei Wang (New York University), Yi Fang (New York University)
  • Deep Adaptive Temporal Pooling for Activity Recognition Sibo Song (Singapore University of Technology and Design), Ngai-Man Cheung (Singapore University of Technology and Design), Vijay Chandrasekhar (Institute for Infocomm Research), Bappaditya Mandal (Keele University)
  • Person Re-Identification with Hierarchical Deep Learning Feature and Efficient XQDA Metric Mingyong Zeng (Army Engineering University of PLA and Jiangnan Institute of Computing Technology), Chang Tian (Army Engineering University of PLA), Zemin Wu (Army Engineering University of PLA)
  • Cumulative Nets for Edge Detection Jingkuan Song (University of Electronic Science and Technology of China), Zhilong Zhou (University of Electronic Science and Technology of China), Lianli Gao (University of Electronic Science and Technology of China), Xing Xu (University of Electronic Science and Technology of China), Heng Tao Shen (University of Electronic Science and Technology of China)
  • Webly Supervised Joint Embedding for Cross-Modal Image-Text Retrieval Niluthpol Chowdhury Mithun (University of California, Riverside), Rameswar Panda (University of California, Riverside), Evangelos E. Papalexakis (University of California, Riverside), Amit K. Roy-Chowdhury (University of California, Riverside)
  • Multi-Modal Preference Modeling for Product Search Yangyang Guo (Shandong University), Zhiyong Cheng (National University of Singapore), Liqiang Nie (Shandong University), Xin-Shun Xu (Shandong University), Mohan Kankanhalli (National University of Singapore)
  • Learning Joint Multimodal Representation with Adversarial Attention Networks Feiran Huang (Beihang University), Xiaoming Zhang (Beihang University), Zhoujun Li (Beihang University)
  • Dest-ResNet: A Deep Spatiotemporal Residual Network for Hotspot Traffic Speed Prediction Binbing Liao (Zhejiang University), Jingqing Zhang (Imperial College London), Ming Cai (Zhejiang University), Siliang Tang (Zhejiang University), Yifan Gao (Zhejiang University), Chao Wu (Zhejiang University), Shengwen Yang (Baidu Inc.), Wenwu Zhu (Tsinghua University), Yike Guo (Imperial College London), Fei Wu (Zhejiang University)
  • Learning and Fusing Multimodal Deep Features for Acoustic Scene Categorization Yifang Yin (National University of Singapore), Rajiv Ratn Shah (IIIT-Delhi), Roger Zimmermann (National University of Singapore)
  • Dynamic Sound Field Synthesis for Speech and Music Optimization Zhenyu Tang (University of North Carolina-Chapel Hill), Nicolas Morales (University of North Carolina-Chapel Hill), Dinesh Manocha (University of Maryland)
  • DASH for 3D Networked Virtual Environment Thomas Forgione (Université de Toulouse – IRIT), Axel Carlier (Université de Toulouse – IRIT), Géraldine Morin (Université de Toulouse – IRIT), Wei Tsang Ooi (National University of Singapore), Vincent Charvillat (Université de Toulouse – IRIT), Praveen Kumar Yadav (National University of Singapore)