Details of Poster Session


P1 Image/Video Enhancement I
Time  
Chair Licheng Liu (Hunan University)
ID Title Author
39 Deep Convolutional Sparse Coding Network for Pansharpening with Guidance of Side Information Shuang Xu (Xi'an Jiaotong University)*; Jiangshe Zhang (Xi'an Jiaotong University); Kai Sun (Xi'an Jiaotong University); Zixiang Zhao (Xi’an Jiaotong University); Lu Huang (Xi’an Jiaotong University); Junmin Liu (Xi'an Jiaotong University); Chunxia Zhang (Xi'an Jiaotong University)
131 Pyramid Orthogonal Attention Network Based on Dual Self-Similarity for Accurate MR Image Super-Resolution Xiaowan Hu (Tsinghua ShenZhen International Graduate School; )*; Haoqian Wang (Tsinghua Shenzhen International Graduate School, Tsinghua University); Yuanhao Cai (Tsinghua Univisity, Tsinghua Shenzhen International Graduate School); Xiaole Zhao (University of Electronic Science and Technology of China); Yulun Zhang (Northeastern University)
184 LEARNING A TREE-STRUCTURED CHANNEL-WISE REFINEMENT NETWORK FOR EFFICIENT IMAGE DERAINING Di Wang (Nanjing University of Science and Technology)*; Hao Tang (Nanjing University of Science and Technology); Jinshan Pan (Nanjing University of Science and Technology); Jinhui Tang (Nanjing University of Science and Technology)
254 Video Deraining via Temporal Aggregation-and-Guidance Long Ma (Dalian University of Technology); Risheng Liu (Dalian University of Technology); Xuefeng Zhang (Dalian University of Technology); Wei Zhong (Dalian University of Technology)*; Xin Fan (Dalian University of Technology)
256 STAR-Net: Spatial-Temporal Attention Residual Network for Video Deraining Wei Zhong (Dalian University of Technology); Xuefeng Zhang (Dalian University of Technology); Long Ma (Dalian University of Technology); Risheng Liu (Dalian University of Technology)*; Xin Fan (Dalian University of Technology); Zhongxuan Luo (DALIAN UNIVERSITY OF TECHNOLOGY)
260 Spatial-Temporal Integration Network with Self-Guidance for Robust Video Deraining Xiaokun Liu (Dalian University of Technology); Risheng Liu (Dalian University of Technology)*; Long Ma (Dalian University of Technology); Xin Fan (Dalian University of Technology); Zhongxuan Luo (DALIAN UNIVERSITY OF TECHNOLOGY)
P2 Object/Person detection, Tracking and Recognition I
Time  
Chair Nikolaos Passalis (Aristotle University of Thessaloniki)
ID Title Author
10 Rectifying  pseudo label by mutual disagreement learning for unsupervised domain adaptation person re-identification Xu Xu (Nanjing University of Aeronautics and Astronautics)*; Liyan Zhang (Nanjing University of Aeronautics and Astronautics)
84 DEEPWORD: A GCN-BASED APPROACH FOR OWNER-MEMBER RELATIONSHIP DETECTION IN AUTONOMOUS DRIVING zizhang wu (zongmu tech.com)*; man wang (zongmu tech.com); jason wang (zongmutech); wenkai zhang ( zongmu tech.com); Muqing Fang (Politecnico di Torino); tianhao xu (University of Braunschweig - Institute of Technology)
148 Modulating Localization and Classification for Harmonized Object Detection Taiheng Zhang (Zhejiang University); Qiaoyong Zhong (Hikvision Research Institute)*; Shiliang Pu (Hikvision Research Institute); Di Xie (Hikvision Research Institute)
221 Learning Factorized Cross-View Fusion for Multi-View Crowd Counting Liangfeng Zheng (Peking University); Yongzhi Li (Peking University); Yadong Mu (Peking University)*
328 Attention-guided Knowledge Distillation for Efficient Single-stage Detector Tong Wang (CASIA)*; yousong zhu (casia); Chaoyang Zhao (National Laboratory of Pattern Recognition, CASIA); Xu Zhao (Chinese Academy of Sciences); Jinqiao Wang (Institute of Automation, Chinese Academy of Sciences); Ming Tang (Institute of Automation, Chinese Academy of Sciences)
400 Graph Convolutional Hourglass Networks for Skeleton-based Action Recognition Yiran Zhu (University of Electronic Science and Technology of China); Xing Xu (University of Electronic Science and Technology of China)*; Yanli Ji (UESTC); Fumin Shen (UESTC); Heng Tao Shen (University of Electronic Science and Technology of China (UESTC)); Huimin Lu (Kyushu Institute of Technology)
P3 Emerging applications of artificial intelligence I
Time  
Chair Xuehe Wang (Nanyang Technological University)
ID Title Author
69 EXPLORING EXPLICIT AND IMPLICIT VISUAL RELATIONSHIPS FOR IMAGE CAPTIONING Zeliang Song (Institute of Information Engineering, Chinese Academy of Sciences & University of Chinese Academy of Sciences, School of Cyber Security ); Xiaofei Zhou (Institute of Information Engineering, Chinese Academy of Sciences & University of Chinese Academy of Sciences, School of Cyber Security)*
192 Unifying Dynamic Optimizer Search and Network Architecture Search Binbin Yang (Sun Yat-sen University)*; Xiaodan Liang (Sun Yat-sen University); Junhao Zhong (Sun Yat-sen University); Jiefeng Peng (Sun Yat-sen University); Guangrun Wang (University of Oxford); Liang Lin (Sun Yat-sen University)
249 Reference-Aided Part-Aligned Feature Disentangling for Video Person Re-Identification Guoqing Zhang (Nanjing University of Information Science & Technology)*; Yuhao Chen (Nanjing University of Information Science & Technology); Yang Dai ( Nanjing University of Information Science & Technology); Yuhui Zheng (Nanjing University of Information Science & Technology); Yi Wu (Wormpex AI Research)
255 Selective, Structural, Subtle: Trilinear Spatial-Awareness for Few-Shot Fine-Grained Visual Recognition Heng Wu (Beihang University); Yifan Zhao (Beihang University); Jia Li (Beihang University)*
304 Non-Local Attention Learning for Medical Image Classification Yang Wen (School of Computer Science and Engineering, University of Electronic Science and Technology of China); Leiting Chen (School of Computer Science and Engineering, University of Electronic Science and Technology of China); Haisheng Chen (University of Electronic Science and Technology of China); Ximan Tang (School of Computer Science and Engineering, University of Electronic Science and Technology of China); Yu Deng (King's College London); Yongbiao Chen (Shanghai Jiao Tong University); Chuan Zhou (School of Computer Science and Engineering, University of Electronic Science and Technology of China)*
349 Towards Efficient Medical Image Segmentation via Boundary-Guided Knowledge Distillation Yang Wen (School of Computer Science and Engineering, University of Electronic Science and Technology of China); Leiting Chen (School of Computer Science and Engineering, University of Electronic Science and Technology of China); Shuo Xi (School of Computer Science and Engineering, University of Electronic Science and Technology of China); Yu Deng (King's College London); Ximan Tang (School of Computer Science and Engineering, University of Electronic Science and Technology of China); Chuan Zhou (School of Computer Science and Engineering, University of Electronic Science and Technology of China)*
P4 Multimedia databases and data mining
Time  
Chair Austin Shuai (National Chiao Tung University)
ID Title Author
930 Multi-view Learning via Low-rank Tensor Optimization Lele Fu (Fuzhou University); Zhaoliang Chen (College of Mathematics and Computer Science, Fuzhou University, Fuzhou 350116, China); Sujia Huang (Jiangxi Normal University); Sheng Huang (Fuzhou University); Shiping Wang (Fuzhou University)*
93 Deep Unsupervised Hashing by Global and Local Consistency Xiao Luo (Peking University); Daqing Wu (Peking University); Chong Chen (Alibaba); Jinwen Ma (Peking University); Minghua Deng (Peking University)*
321 Attention-based Relation Reasoning Network for Video-Text Retrieval Ni Wang (University of Electronic Science and Technology of China ); Zheng Wang (UESTC); Xing Xu (University of Electronic Science and Technology of China)*; Fumin Shen (UESTC); Yang Yang (University of Electronic Science and Technology of China); Heng Tao Shen (University of Electronic Science and Technology of China (UESTC))
764 FAST BINARY EMBEDDING OF DEEP LEARNING Image FEATURES using Golay-Hadamard matrices Chanattra Ammatmanee (Brunel University); Lu Gan (Brunel University London)*; Hongqing Liu (CQUPT)
855 Disturbance Consistent Self-Ensembling For Semi-Supervised Hashing Shuai Cheng (Institute of Information Engineering, School of Cyber Security, University of Chinese Academy of Sciences); Yucan Zhou (Chinese Academy of Sciences)*; Dayan Wu (Institute of Information Engineering, Chinese Academy of Sciences); Haisu Zhang (NUDT); Bo Li ( Institute of Information Engineering, Chinese Academy of Sciences); Weiping Wang (Institute of Information Engineering, CAS, China)
1355 USER-PREFERENCE BASED KNOWLEDGE GRAPH FEATURE AND STRUCTURE LEARNING FOR RECOMMENDATION Hang Shu (Shanghai Advanced Research Institute, Chinese Academy of Sciences, Shanghai, China)*; Jun Huang (Shanghai Advanced Research Institute, Chinese Academy of Sciences)
P5 Special Session: Advancd Video Coding and Deep Active Learning
Time  
Chair Xin Zhao (Tencent)
ID Title Author
492 An Efficient and Open Source Encoder uavs3e for Video Compression Yangang Cai (Peking University Shenzhen Graduate School)*; Ronggang Wang (Peking University); Zhenyu Wang (Shenzhen Graduate School, Peking University); Bingjie Han (Shenzhen Graduate School, Peking University); Xufeng Li (Shenzhen Graduate School, Peking University)
866 Visual Analysis Motivated Rate-Distortion Model for Image Coding Zhimeng Huang (Peking University)*; Chuanmin Jia (Peking University); Shanshe Wang (Peking University); Siwei Ma (Peking University, China)
969 STUDY ON CODING TOOLS BEYOND AV1 Xin Zhao (Tencent America)*; Liang Zhao (Tencent); Madhu Krishnan (Tencent America); Yixin Du (Tencent America); Shan Liu (Tencent America);  Debargha Mukherjee (Google Inc); Yaowu Xu (Google Inc.); Adrian Grange (Google Inc)
1188 Dynamic Computational Resource Allocation for Fast Inter Frame Coding in Video Conferencing Applications Hang Yuan (Peking University; Peng Cheng Laboratory); Wei Gao (Peking University & Peng Cheng Laboratory)*; Junle Wang (Tencent)
78 VISIONNET: A COARSE-TO-FINE MOTION PREDICTION ALGORITHM BASED ON ACTIVE INTERACTION-AWARE DRIVABLE SPACE LEARNING Dongchun Ren (Meituan); Yanliang Zhu (Sankuai Online Corporation ); Mingyu Fan (Wenzhou University)*; Deheng Qian (Meituan); Huaxia Xia (Meituan); Zhuang Fu (Meituan)
840 Real-World Image Super-Resolution via Spatio-temporal Correlation Network Hongyang Zhou (University Of Science and Technology Beijing); Xiaobin Zhu (University Of Science and Technology Beijing)*; Zheng Han (University of Science and Technology Beijing); Xu-Cheng Yin (University of Science and Technology Beijing)
P6 Image/Video Enhancement II
Time  
Chair Cunjian Chen (Michigan State University)
ID Title Author
313 Multiple task-oriented encoders for unified image fusion Zhuoxiao Li (Dalian University of Technology); Jinyuan Liu (Dalian University of Technology); Risheng Liu (Dalian University of Technology); Xin Fan (Dalian University of Technology)*; Zhongxuan Luo (DALIAN UNIVERSITY OF TECHNOLOGY); Wen Gao (PKU)
323 Hardware-aware low-light image enhancement via one-shot neural architecture search with shrinkage sampling Yuansheng Yao (DLUT); Risheng Liu (Dalian University of Technology)*; Jiaao Zhang (Dalian University of Technology); Zhong Wei (Dalian University of Technology); Xin Fan (Dalian University of Technology); Zhongxuan Luo (DALIAN UNIVERSITY OF TECHNOLOGY)
378 SEARCHING FRAME-RECURRENT ATTENTIVE DEFORMABLE NETWORK FOR REAL-TIME VIDEO DERAINING Xinwei Xue (Dalian University of Technology)*; Xiangyu Meng (Dalian University of Technology); Long Ma (Dalian University of Technology); Yi Wang (Dalian University of Technology); Risheng Liu (Dalian University of Technology); Xin Fan (Dalian University of Technology)
424 Invertible color-to-grayscale Conversion By Using Clustering and Reversible Watermarking Qiaoyi Liang (Jinan University); Runwen Hu (Jinan University); Shijun Xiang (Jinan University)*
653 Restoration of HDR Images for SVE-based HDRI via a Novel DCNN Yilun Xu (Beihang University)*; Ziyang Liu (Beihang University); Xingming Wu (Beihang University); Weihai Chen (Beihang University); Zhengguo Li (A*STAR)
657 HEATMAP-AWARE PYRAMID FACE HALLUCINATION Chenyang Wang (Harbin Institute of Technology)*; Junjun Jiang (Harbin Institute of Technology); Xianming Liu (Harbin Institute of Technology)
P7 Object/Person detection, Tracking and Recognition II
Time  
Chair Raouf Hamzaoui (De Montfort University)
ID Title Author
414 ASOC: Adaptive Self-aware Object Co-localization Koteswar Rao Jerripothula (IIIT Delhi)*; Prerana Mukherjee (Jawaharlal Nehru University)
641 Retrospective Class Incremental Learning Qingyi Tao (Nanyang Technological University)*; Chen Change  Loy (Nanyang Technological University); Jianfei Cai (Monash University); Zongyuan Ge (Monash); Simon See (NVIDIA AI Tech Centre)
774 SALIENT OBJECT DETECTION VIA ATTENTION-AWARE CASCADED BOTTOM-UP FEATURE AGGREGATION Fengming Sun (Nanjing University of Science and Technology); Lufei Huang (Nanjing University of Science and Technology); Xia Yuan (Nanjing University of Science and Technology)*; ChunXia Zhao (Nanjing university of science and technology)
781 Feature Aggregation Network with Tri-hybrid Loss for Instance Segmentation Zeping Zhou (University of Shanghai for Science and Technology); Yongxiong Wang (University of Shanghai for Science and Technology)*; Jin Peng (University of Shanghai for Science and Technology)
818 Robust Video Text Detection through Parametric Shape Regression, Propagation and Fusion Long Chen (Nanjing University); Jiahao Shi (Nanjing University); Feng Su (Nanjing University)*
819 Static Image Action Recognition with Hallucinated Fine-grained Motion Information Shengyuan Huang (Shanghai Jiao Tong University)*; Xing Zhao (Shanghai Jiao Tong University); Li Niu (Shanghai Jiao Tong University); Liqing Zhang (Shanghai Jiao Tong University)
P8 Emerging multimedia applications of deep learning
Time  
Chair Jong-Seok LEE (Yonsei University)
ID Title Author
7 MULTI-PRETEXT ATTENTION NETWORK FOR FEW-SHOT LEARNING WITH SELF-SUPERVISION Hainan Li (Beihang University); Renshuai Tao (Beihang University); Jun Li (Capital Normal University); Haotong Qin (Beihang University); Yifu Ding (Beihang University); Shuo Wang (Beihang University); Xianglong Liu (Beihang University)*
31 More-Similar-Less-Important: Filter Pruning via KMeans Clustering Zili Liu (China University of Mining and Technology, Beijing)*; Peisong  Wang (Institute of Automation, Chinese Academy of Sciences); Zaixing Li (China University of Mining and Technology, Beijing)
83 Interpret the Predictions of Deep Networks via Re-Label Distillation Yingying Hua (Chinese Academy of Sciences); Shiming Ge (Chinese Academy of Sciences)*; Daichi Zhang (Chinese Academy of Sciences)
152 Teacher-supervised Generative Adversarial Networks Yan Gan (Chongqing University); Tao Xiang (Chongqing University)*; Hangcheng Liu (Chongqing University); Mao Ye (University of Electronic Science and Technology of China); Dan Liu (University of Shanghai for Science and Technology)
270 Non-Adversarial Novelty Detection with Generative Latent Nearest Neighbors Chengwei Chen (East China Normal University); Zhizhong Zhang (East China Normal University); Yuan Xie (East China Normal University)*; Haichuan Song (East China Normal University); Lizhuang Ma (East China Normal University)
706 Towards Effective Adversarial Attack Against 3D Point Cloud Classification Chengcheng Ma (Institute of Automation, Chinese Academy of Sciences); Weiliang Meng (Institute of Automation, Chinese Academy of Sciences)*; Baoyuan Wu (The Chinese University of Hong Kong, Shenzhen; Shenzhen Research Institute of Big Data); Shibiao Xu (Institute of Automation, Chinese Academy of Sciences); Xiaopeng Zhang (Institute of Automation, Chinese Academy of Sciences)
P9 Multimedia for society and health
Time  
Chair Carl James Debono (University of Malta)
ID Title Author
617 SEEING HEALTH WITH EYES: FEATURE COMBINATION FOR IMAGE-BASED HUMAN BMI ESTIMATION Junjia Huang (Sun Yat-Sen University); Chenming Shang (School of Intelligent Systems Engineering, Sun Yat-sen University); Aolin Xiong (Sun Yat-Sen University); Yuxian Pang (School of Intelligent Systems Engineering, Sun Yat-sen University ); Zhi Jin (Sun Yat-sen University)*
1366 LOWER BODY REHABILITATION DATASET AND MODEL OPTIMIZATION Chenxi Wang (University of Massachusetts Lowell)*; Ying Li (University of Massachusetts Lowell); Zinan Xiong (University of Massachusetts Lowell); Yan Luo ( The University of Massachusetts Lowel); Yu Cao (University of Massachusetts Lowell)
32 Constrained Contrastive Representation: Classification on Chest X-rays with Limited Data Weiqi Zhang (Academy for Engineering and Technology, Fudan University); Hongbo Wang (Academy for Engineering and Technology, Fudan University)*; Zhiping Lai (Fudan University); Chao Hou (Academy for Engineering and Technology, Fudan University)
317 A Keypoint Transformer to Discover Spine Structure for Cobb Angle Estimation Yue Guo (Institute of Automation, Chinese Academy of Sciences)*; Yanmei Li (Beijing College of Finance and Commerce); Xiaowei Zhou (Institute of Automation, Chinese Academy of Sciences); Wenhao He (Institute of Automation, Chinese Academy of Sciences)
659 A ZERO-SHOT METHOD FOR 3D MEDICAL IMAGE SEGMENTATION Shiqiang Ma (College of Intelligence and Computing, Tianjin University)*; Xuejian Li (College of Intelligence and Computing, Tianjin University); Jijun Tang (Tianjin University); Fei Guo (Tianjin University)
1043 QAU-Net: Quartet Attention U-Net for Liver and Liver-tumor Segmentation Luminzi Hong (Shaanxi University of Science and Technology); Risheng Wang (Shaanxi University of Science and Technology); Tao Lei (Shaanxi University of Science and Technology)*; Xiaogang Du (Shaanxi University of Science and Technology); Yong Wan (the First Affiliated Hospital of Xi'an Jiaotong University)
P10 Special Session: Advanced Representation Learning and Depth-Related Processing
Time  
Chair Hui Yuan (Shandong University)
ID Title Author
95 ANIME STYLE TRANSFER WITH SPATIALLY-ADAPTIVE NORMALIZATION Jinrong Cui (South China Agricultural University)*
138 TOWARDS RICH-DETAIL 3D FACE RECONSTRUCTION AND DENSE ALIGNMENT VIA MULTI-SCALE DETAIL AUGMENTATION Jianjun Zhang (Ningxia University)*; Suping Wu  (Ningxia University); Lei Li (Ningxia  University); Kui Lin (Ningxia University); Xing Zheng (Ningxia University); hu cao (Ningxia University)
183 Dual Prototype Relaxation for Generalized Zero Shot Learning Jie Zhang (Nanjing University of Science and Technology); Haofeng Zhang (Nanjing University of Science and Technology)*; BingZhang Hu (Newcastle University)
841 Variation-net: Interpretable Variation-inspired Deep Network for Pansharpening Kun Li (Wuhan University); Wei Zhang (Wuhan University); Xin Tian (Wuhan University)*; Jiayi Ma (Wuhan University); Huabing Zhou (Wuhan Institute of Technology); Zhongyuan Wang (Wuhan University)
615 BTS-NET: BI-DIRECTIONAL TRANSFER-AND-SELECTION NETWORK FOR RGB-D SALIENT OBJECT DETECTION Wenbo Zhang (Sichuan University); Yao Jiang (Sichuan University); Keren Fu (Sichuan University)*; Qijun Zhao (Sichuan University)
989 Distortion-Tolerant Monocular Depth Estimation On Omnidirectional Images Using Dual-Cubemap Zhijie Shen (Beijing Jiaotong University); Chunyu Lin (Beijing Jiaotong University)*; Lang Nie (Beijing Jiaotong University); Kang Liao (Beijing Jiaotong University); Yao Zhao (Beijing Jiaotong University)
P11 Image/Video Enhancement III
Time  
Chair Zhiyong Wang (The University of Sydney)
ID Title Author
751 Unsupervised Remoting Sensing Super-Resolution Via Migration Image Prior Jiaming Wang (Wuhan University )*; Zhenfeng Shao (Wuhan University); Tao Lu ( Wuhan Institute of Technology); Xiao Huang (University of Arkansas); Ruiqian Zhang (Wuhan University); Yu Wang (Wuhan Institute of technology)
758 Research on super-resolution enhancement algorithm based on skip residual dense network Mu Shaoshuo (communication university of zhejiang); Zhang Yanhua (communication university of zhejiang); Qian Xiaolan (communication university of zhejiang); Jiang Yanbing (communication university of zhejiang)*
808 SDAN: Squared Deformable Alignment Network for Learning Misaligned Optical Zoom Kangfu Mei (The Chinese University of Hong Kong, Shenzhen)*; Shenglong Ye (The Chinese University of Hong Kong, Shenzhen); Rui Huang (The Chinese University of Hong Kong, Shenzhen)
816 A novel attention enhanced residual-in-residual dense network for text image super-resolution Minglong Xue (National Key Lab for Novel Software Technology, Nanjing University, Nanjing, China)*; Zhiheng Huang (National Key Lab for Novel Software Technology, Nanjing University); Ruo-Ze Liu (Nanjing University); Tong Lu (Nanjing University)
933 Graph Attention Neural Network for Image Restoration Chong Mou (Peking University Shenzhen Graduate School); Jian Zhang (Peking University Shenzhen Graduate School)*
938 IMPROVING CONVOLUTIONAL NETWORKS WITH BOOSTING ATTENTION CONVOLUTIONS Chao li ( Shenzhen University)*; Yongsheng Liang (Harbin Institute of Technology Shenzhen Graduate School); Huoxiang Yang (Shenzhen University); Fanyang Meng (Peng Cheng Laboratory); Wei Liu (Shenzhen Institute of Information Technology); Handong Wang (Harbin Institute of Technology Shenzhen Graduate School)
P12 Multimedia analysis and understanding I
Time  
Chair Wei Qi Yan (Auckland University of Technology)
ID Title Author
1299 Efficient Fine-Grained Visual-Text Search Using Adversarially-Learned Hash Codes Yongzhi Li (Peking University); Yadong Mu (Peking University)*; Nan Zhuang (Peking University); Xianglong Liu (Beihang University)
1329 Depth-Guided AdaIN and Shift Attention Network for Vision-and-Language Navigation Qiang Sun (Fudan University); Yifeng Zhuang (Fudan University); Zhengqing Chen (Fudan University); Yanwei Fu (Fudan University)*; Xiangyang Xue (Fudan University)
1502 Learning Outfit Compatibility with Graph Attention Network and Visual-Semantic Embedding Jianfeng Wang (Sun Yat-sen University); Xiaochun Cheng (Middlesex University)*; Ruomei Wang (Sun Yat-sen University); Shaohui Liu (Harbin Institute of Technology)
1042 Key Facial Components Guided Micro-expression Recognition based on First & Second-order Motion Yu-ting Su (Tianjin University); Jiaqi Zhang (Tianjin University); Jing Liu (Tianjin University)*; Guangtao Zhai (Shanghai Jiao Tong University)
1380 FFNET-M: FEATURE FUSION NETWORK WITH MASKS FOR MULTIMODAL FACIAL EXPRESSION RECOGNITION Mingzhe Sui (University of Science and Technology of China); Zhaoqing Zhu (University of Science and Technology of China); Feng Zhao (University of Science and Technology of China)*; Feng Wu (University of Science and Technology of China)
1578 Dual-waveform emotion recognition model for conversations Jiayi Zhang (Beijing University of Posts and Telecommunication)*; Zihe Liu (Beijing University of Posts and Telecommunications); Peihang Liu (Beijing University of Posts and Telecommunications); Bin Wu (Beijing University of Posts and Telecommunications)
P13 Emerging applications of artificial intelligence II
Time  
Chair Chong-Yang Zhang (Shanghai Jiao Tong University)
ID Title Author
699 CRANet: Cascade Residual Attention Network for Crowd Counting Zhongyuan Wu (Chongqing University); Jun Sang (Chongqing University)*; Ying Shi (Chongqing University); Qi Liu (Chongqing University); Nong Sang (Huazhong University of Science and Technology); Xinyue Liu (Chongqing University)
922 FUSING TEMPORALLY DISTRIBUTED MULTI-MODAL SEMANTIC CLUES FOR VIDEO QUESTION ANSWERING Fuwei Zhang (Sun Yat-sen University); Ruomei Wang (Sun Yat-sen University); Songhua Xu (Xi'an Jiaotong University)*; Fan Zhou (Sun Yat-sen university)
981 Driving Video Fixation Prediction Model via Spatio-Temporal Networks and Attention Gates Tao Deng (Southwest Jiaotong University)*; Fei Yan (Southwest Jiaotong University); Hongmei Yan ()
1424 Incorporating Multimodal Cues for Advertorial Discovery Lu Zhang (University of Technology Sydney)*; Jian Zhang (UTS); Jialie Shen (Queen's Belfast University); JingSong Xu (University of Technology Sydney ); Zhibin Li (University of Technology Sydney ); Litao Yu (UTS)
1464 Dynamic Cross Fusion Network for Building-Based Damage Assessment Huaxin Xiao (NUDT)*; Yang Peng (National University of Defense Technology); Hanlin Tan (National University of Defense Technology); Ping Li (Hangzhou Dianzi University)
457 Toward Personalized Human Activity Recognition Model with Auto-Supervised Learning Framework Ala Mhalla Mhalla (Blaise Pascal University); Ala Mhalla (Université Clermont Auvergne ( UCA ))*
P14 Multimedia security, privacy and forensics I
Time  
Chair Cunjian Chen (Michigan State University)
ID Title Author
554 DeepFake videos detection using self-supervised decoupling network Jian Zhang (School of Computer Science and Engineering, Sun Yat-sen University)*; Jiangqun Ni Sun Yat-sen Univ. (); HAO XIE (Sun Yat-sen University)
747 Object-based Video Forgery Detection via Dual-Stream Networks Xiao Jin (Nankai University)*; he zhen (nankai university); Jing Xu (Nankai University); Yongwei Wang (University of British Columbia); Yu-ting Su (Tianjin University)
917 DLFMNet: End-to-End Detection and Localization of Face Manipulation using Multi-domain Features Peng Chen (1. Institute of Information Engineering,Chinese Academy of Sciences. 2. School of Cyber Security, University of Chinese Academy of Sciences); Jin Liu (1. Institute of Information Engineering,Chinese Academy of Sciences. 2. School of Cyber Security, University of Chinese Academy of Sciences); Tao Liang (1. Institute of Information Engineering,Chinese Academy of Sciences. 2. School of Cyber Security, University of Chinese Academy of Sciences); Cai Yu (1. Institute of Information Engineering,Chinese Academy of Sciences. 2. School of Cyber Security, University of Chinese Academy of Sciences); Shuqiao Zou (1. Institute of Information Engineering,Chinese Academy of Sciences. 2. School of Cyber Security, University of Chinese Academy of Sciences); Jiao Dai (Institute of Information Engineering,Chinese Academy of Sciences)*; Jizhong Han (Institute of Information Engineering,Chinese Academy of Sciences)
951 Zero Knowledge Adversarial Defense via Iterative Translation Cycle Fan Jia (Tianjin University); Yucheng Shi (Tianjin University); Yahong Han (Tianjin University)*
1086 Detection of Deep Video Frame Interpolation via Learning Dual-stream Fusion CNN in the Compression domain xiangling ding (Hunan University of Science and Technology); Pan YIfeng (Hunan University of Science and Technology); Gu Qing (Hunan University of Science and Technology)*; you ji chen (chenjiyou); Gaobo Yang (Hunan University of Science and Technology); Xiong Yimao (Hunan University of Science and Technology)
1302 RPATTACK: REFINED PATCH ATTACK ON GENERAL OBJECT DETECTORS Hao Huang (Peking University); Yongtao Wang (Peking University)*; Zhaoyu Chen (Fudan University); Zhi Tang (Peking University); Wenqiang Zhang (Fudan University); Kai-Kuang Ma (Nanyang Technological University, Singapore)
P15 Speial Session: Multimedia Processing
Time  
Chair Yueqi Duan (Stanford University)
ID Title Author
613 DENSE FUSION NETWORK WITH MULTIMODAL RESIDUAL FOR SENTIMENT CLASSIFICATION Huan Deng (Guangdong University of Technology)*; peipei kang (Guangdong University of Technology); Zhenguo Yang (Guangdong University of Technology); Tianyong Hao (South China Normal University); Qing Li (The Hong Kong Polytechnic University); Wenyin Liu (Guangdong University of Technology)
90 Learning Multiple Semantic Knowledge for Cross-domain Unsupervised Vehicle Re-identification Huibing Wang (Dalian Maritime University)*; Jinjia Peng (Dalian Maritime University); Guangqi Jiang (Dalian Maritime University); Xianping Fu (Dalian Maritime University)
1203 Auxiliary Bi-Level Graph Representation for Cross-Modal Image-Text Retrieval Xian Zhong (Wuhan University of Technology); Zhengwei Yang (Wuhan University of Technology); Mang YE (Wuhan University)*; Wenxin Huang (Hubei University); Jingling Yuan (Wuhan University of Technology); Chia-Wen Lin (National Tsing Hua University)
1413 Are GAN generated images easy to detect?  A critical analysis of the state-of-the-art Diego Gragnaniello (University Federico II of Naples); Davide Cozzolino (University Federico II of Naples); Francesco Marra (University Federico II of Naples); GIovanni Poggi (University Federico II of Naples); Luisa Verdoliva (University Federico II of Naples)*
380 Lightweight Image Super-Resolution with Multi-scale Feature Interaction Network Zhengxue Wang (Nanjing University of Posts and Telecommunications); Guangwei Gao (NII)*; Juncheng Li (East China Normal University); Yi Yu (NII); Huimin Lu (Kyushu Institute of Technology)
504 Self-supervised Mutual Learning for Video Representation Learning Jinpeng Wang (Sun Yat-sen University); Yutong Li (Sun Yat-sen University); Jianguo Hu (Sun Yat-sen University)*; Xuebin Yang (Sun Yat-sen University); Yanyu Ding (Dongguan University Of Technology)
P16 Multimedia analysis and processing
Time  
Chair Nikos Nikolaidis (Aristotle University of Thessaloniki)
ID Title Author
479 Visually Maintained Image Disturbance Against DeepFake Face Swapping Junhao Dong (Sun Yat-sen University); Xiaohua Xie (Sun Yat-sen University)*
582 Boosting few-shot classification with view-learnable contrastive learning Xu Luo (University of Electronic Science and Technology of China); Yuxuan Chen (University of Electronic Science and Technology of China); liangjian Wen (University of Electronic Science and Technology of China); Lili Pan (University of Electronic Science and Technology of China); Zenglin Xu (Harbin Institute of Technology, Shenzhen)*
1393 Few-Shot Semantic Segmenation via Prototype Augmentation with Image-level Annotations Shuo Lei (Virginia Tech)*; Xuchao Zhang (Virginia Tech); Jianfeng He (Virginia Tech); Fanglan Chen (Virginia Tech); Chang-Tien Lu (Virginia Tech, USA)
708 Enhancing Viewing Experience of Generated Visual Storylines for Promotional Videos Chang Liu (Nanyang Technological University)*; Han Yu (Nanyang Technological University (NTU)); Zhiqi Shen (NTU); Ian Dixon (Nanyang Technological University); Yingxue Yu (Nanyang Technological University); Zhanning Gao (Alibaba Group); Pan Wang (Alibaba Group); Peiran Ren (Alibaba Group); Xuansong Xie (Alibaba); Lizhen Cui (ShanDong University); Chunyan Miao (NTU)
15 SHOW, RETHINK, AND TELL: IMAGE CAPTION GENERATION WITH HIERARCHICAL TOPIC CUES Feng Chen (National University of Defense Technology)*; Songxian Xie (National University of Defense Technology); Xinyi Li (National University of Defense Technology); Jintao Tang (National University of Defense Technology); Kunyuan Pang (National University of Defense technology); shasha li (National University of Defence Technology); Ting Wang (National University of Defense Technology)
415 Pyramid Feature Attention Network for Monocular Depth Prediction Yifang Xu (NanJing University)*; Chenglei Peng (Nanjing University); Ming Li (NanJing University); Yang Li (NanJing University); Sidan Du (Nanjing University)
P17 Image/Video Enhancement IV
Time  
Chair Raouf Hamzaoui (De Montfort University)
ID Title Author
949 Spatial-Temporal Correlation Learning for Real-Time Video Deinterlacing Yuqing Liu (Dalian University of Technology); xinfeng zhang (University of Chinese Academy of Sciences); Shanshe Wang (Peking University); Siwei Ma (Peking University, China)*; Wen Gao (PKU)
1028 Rethinking Noise Modeling in Extreme Low-light Environments Jing Wang (Sony R&D Center China)*; Yitong Yu (Central University of Finance and Economics); Songtao Wu (Sony R&D Center China); Chang Lei (Columbia University); Kuanhong Xu (Sony R&D Center China)
1078 UNDEREXPOSED IMAGE ENHANCEMENT VIA UNSUPERVISED FEATURE ATTENTION NETWORK fengji ma (Beihang University)*; haitao Li (Beihang University)
1126 Self-Attention Recurrent Summarization Network with Reinforcement Learning for Video Summarization Task Aniwat Phaphuangwittayakul (East China University of Science and Technology); Yi Guo (ecust)*; Fangli Ying (East China University of Science and Technology); Wentian Xu (East China University of Science and Technology); Zheng Zheng (East China University of Science and Technology)
1264 Image inpainting using edge structure aware hierarchical guidance Yashi Su (south china university of technology); Lihong Ma (south china university of technology); Jing Tian (national university of singapore)*
1284 L2 NORM IS ALL YOUR NEED: INFRARED-VISIBLE IMAGE FUSION VIA GUIDED TRANSFORMATION MINIMIZATION Huibin Yan (Shenzhen University); Shuoyao Wang (Shenzhen University)*
P18 Object/Person detection, Tracking and Recognition III
Time  
Chair Nikolaos Passalis (Aristotle University of Thessaloniki)
ID Title Author
820 DUAL CONTRASTIVE UNIVERSAL ADAPTATION NETWORK Ziyun Cai (Nanjing University of Posts and Telecommunications)*; jie song (Nanjing University of Posts and Telecommunications); Tengfei Zhang (Nanjing University of Posts and Telecommunications); Jing Xiao-Yuan (School of Computer, Wuhan University); Ling Shao (Inception Institute of Artificial Intelligence)
865 Knowledge Transfer Based Fine-Grained Visual Classification Siqing Zhang (Beijing University of Posts and Telecommunications); Ruoyi Du (Beijing University of Posts and Telecommunications); Dongliang Chang (Beijing University of Posts and Telecommunications); Zhanyu Ma (Beijing University of Posts and Telecommunications)*; Jun Guo (Beijing University of Posts and Telecommunications)
935 Inharmonious Region Localization Jing Liang (Shanghai Jiao Tong University); Li Niu (Shanghai Jiao Tong University)*; Liqing Zhang (Shanghai Jiao Tong University)
939 A Change-aware Approach for Relative Motion Segmentation Zhuojun Zou (Institute of Automation, Chinese Academy of Sciences; School of Artificial Intelligence, University of Chinese Academy of Sciences)*; Zhaoteng Meng (Institute of Automation,Chinese Academy of Sciences; University of Chinese Academy of Sciences); lin shu (Institute of Automation, Chinese Academy of Sciences); jie hao (Institute of Automation,Chinese Academy of Sciences)
987 A METHOD OF STABLE LONG-TERM SINGLE OBJECT TRACKING Zitong Yi (BUPT)*; Zhihang Tong (BUPT); Yanyun  Zhao (Beijing Univiersity of Posts and Telecommunications); Zhicheng Zhao (bupt); Fei Su (Beijing University of Posts and Telecommunications)
1219 Multi-camera Logical Topology Inference via Conditional Probability Graph Convolution Network keyang Cheng (Jiangsu University); Qing Liu (Jiangsu University)*; Rabia Tahir (Jiangsu University); Lubamba  E Kasangu Eric (Jiangsu University ); Ligang He (The University of Warwick)
P19 Multimedia analysis and understanding II
Time  
Chair Chong-Yang Zhang (Shanghai Jiao Tong University)
ID Title Author
1316 REAL-TIME OBJECT DETECTION BY FEATURE MAP FORECAST FOR LIVE STREAMING VIDEO Masato Fujitake (The Graduate University for Advanced Studies, SOKENDAI)*; Akihiro Sugimoto (NII)
1446 SVRAT: A SKELETON-BASED INTELLIGENT MONITORING SYSTEM FOR VIOLENCE RECOGNITION AND ABUSER TRACKING Haiqiang Liu (Jilin University)*; Meibao Yao (Jilin University); Linlin Wang (Jilin University)
1048 Graph-in-graph contrastive learning for semi-supervised adaptation Liang Li (Tianjin University); Aming Wu (Tianjin University); Yahong Han (Tianjin University)*
1087 FINED: FAST INFERENCE NETWORK FOR EDGE DETECTION Jan Kristanto Wibisono (National Chiao Tung University)*; Hsueh-Ming Hang (National Chiao Tung University)
1170 Global-to-Local Dynamic Feature Aggregation for Unsupervised Person Re-identification Wei Li (Fudan University); Jiayuan Fan (Fudan University)*; Yanwei Fu (Fudan University)
1341 RELATIVE POSITION REPRESENTATION OVER INTERACTION SPACE FOR NATURAL LANGUAGE INFERENCE Huiyan Wu (Shanghai Advanced Research Institute, Chinese Academy of Sciences, Shanghai, China)*; Jun Huang (Shanghai Advanced Research Institute, Chinese Academy of Sciences)
P20 Immersive media 
Time  
Chair Carl James Debono (University of Malta)
ID Title Author
62 Rotation Transformation Network: Learning View-Invariant Point Cloud for Classification and Segmentation Shuang Deng (NLPR-IA-CAS)*; Bo Liu (NLPR-IA-CAS); Qiulei Dong (NLPR-IA-CAS); Zhanyi Hu (National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences)
172 HIGH-RESOLUTION MULTI-VIEW STEREO WITH DYNAMIC DEPTH EDGE FLOW Kui Lin (Ningxia University)*; Lei Li (Ningxia  University); Jianjun Zhang (Ningxia University); Xing Zheng (Ningxia University); Suping Wu  (Ningxia University)
1363 OlaNet: Self-supervised 360° Depth Estimation with Effective Distortion-Aware View Synthesis and L1 Smooth Regularization Ziye Lai (Fuzhou University); Dan Chen (Fuzhou University); Kaixiong Su (Fuzhou University)*
988 THE IMPACT OF BLACK EDGE ARTIFACT ON USER EXPERIENCE FOR THE INTERACTIVE CLOUD VR SERVICES Jiarun Song (Xidian University)*; Jianquan Zhou (Xidian University); Xionghui Mao (Xidian University); FuZheng Yang (Xidian University)
1313 GRAPH ATTENTION-BASED DEEP NEURAL NETWORK FOR 3D POINT CLOUD PROCESSING Xun Li (Hefei University of Technology); Feng Xue (Hefei University of Technology); Chao Chen (Hefei University of Technology); Xiaohui Yuan (University of North Texas); Qiang Lu (Hefei University of Technology)*
P21 Multimedia security, privacy and forensics II
Time  
Chair Liang He (Tsinghua University)
ID Title Author
734 REVERSIBLE PRIVACY-PRESERVING RECOGNITION Zhengxin You (Fudan University); Sheng Li (Fudan University); Zhenxing Qian (School of Computer Science, Fudan University)*; Xinpeng Zhang (School of Computer Science, Fudan University)
958 IMPROVED LIGHTCNN WITH ATTENTION MODULES FOR ASV SPOOFING DETECTION Xinyue Ma (Tsinghua University)*; Tianyu Liang (Tsinghua University); Shanshan Zhang (Tencent Research); Shen Huang (Tencent Research); Liang HE (Tsinghua University)
972 Undetectable Adversarial Examples based on Microscopical Regularization Nan Zhong (Fudan University); Zhenxing Qian (School of Computer Science, Fudan University); Xinpeng Zhang (School of Computer Science, Fudan University)*
1358 A Multi-factor Combinations Enhanced Reversible Privacy Protection System for Facial Images Yi-Lun Pan (National Taiwan University )*; Jun-Cheng Chen (Academia Sinica); Ja-Ling Wu (NTU)
842 A Semantic-enhanced Method Based on Deep SVDD for Pixel-wise Anomaly Detection Chuanfei Hu (University of Shanghai for Science and Technology)*; Kai Chen (University of Shanghai for Science and Technology); Hang Shao (University of Shanghai for Science and Technology)
1609 Robust Cross-Scene Foreground Segmentation in Surveillance Video Dong Liang (Nanjing University of Aeronautics and Astronautics)*; Zongqi Wei (Nanjing University of Aeronautics and Astronautics); Han Sun (NUAA); Huiyu Zhou (University of Leicester)
P22 Multimedia Applications I
Time  
Chair Wenhan Yang (Peking University)
ID Title Author
472 A Generative Model for Partial Label Learning Yan Yan (Northwestern Polytechnical University)*; Shining Li (Northwestern Polytechnical University)
1494 Asymmetric Loss for Positive-unlabeled Learning Cong Wang (East China Normal University); Jian Pu (Fudan University)*; Zhi Xu (East China Normal University); Junping Zhang (Fudan University)
700 ADAPTIVE FLEXIBLE 3D HISTOGRAM WATERMARKING Chen Hui (Harbin Institute of Technology); Shaohui Liu (Harbin Institute of Technology)*; Wenxue Cui (Harbin Institute of Technology); Jinghua Zeng (Harbin Institute of Technology); Feng Jiang (Harbin Institute of Technology, Harbin); Debin Zhao (Harbin Institute of Technology)
344 OVERSAMPLING BY A CONSTRAINT-BASED CAUSAL NETWORK IN MEDICAL IMBALANCED DATA CLASSIFICATION Hao Luo (Chongqing University ); Jun Liao (Chongqing University); Xuewen Yan (Chongqing University); Li Liu (Chongqing University)*
1430 Depth Super-Resolution by Texture-Depth Transformer Chao Yao (University of Science and Technology, Beijing); Shuaiyong Zhang (Beijing Jiaotong University); Mengyao Yang (China Aerospace Academy of Systems Science and Engineering); Meiqin Liu (Beijing Jiaotong University)*; Junpeng Qi (China Aerospace Academy of Systems Science and Engineering)
P23 Image/video synthesis and creation
Time  
Chair Chau-Wai Wong (North Carolina State University)
ID Title Author
537 SAFIN: ARBITRARY STYLE TRANSFER WITH SELF-ATTENTIVE FACTORIZED INSTANCE NORMALIZATION Aaditya Singh (Indian Institute of Technology Kanpur); Shreeshail Suhas Hingane (Indian Institute of Technology Kanpur)*; Xinyu  Gong  (University of Texas at Austin); Zhangyang Wang (University of Texas at Austin)
830 Label-free Regional Consistency for Image-to-Image Translation Shaohua Guo (Shanghai Jiao Tong University)*; Qianyu Zhou (Shanghai Jiao Tong University); Zhou Ye (CLS Fintech); Qiqi Gu (Shanghai Jiao Tong University ); Junshu  Tang (Shanghai Jiao Tong University); Zhengyang Feng (Shanghai Jiao Tong University); Lizhuang Ma (Shanghai Jiao Tong University)
864 Reinforcement Learning Based Automatic Personal Mashup Generation Panwen Hu (The Chinese University of Hong Kong,Shenzhen)*; Liu Jiazhen (The Chinese University of Hong Kong, Shenzhen); Tianyu Cao (The Chinese University of Hong Kong, Shenzhen); Rui Huang (The Chinese University of Hong Kong, Shenzhen)
1144 DEEP SUPERVISED IMAGE RETARGETING Yijing Mei (Tianjin University); Xiaojie Guo (Tianjin University); Di Sun (Tianjin University of Science and Technology); Gang Pan (Tianjin University)*; Jiawan Zhang (Tianjin University)
1243 Watermark Faker: Towards Forgery of Digital Image Watermarking Ruowei Wang (Sichuan university)*; Chenguo Lin (Sichuan University); Qijun Zhao (Sichuan University); Feiyu Zhu (Sichuan University)
1551 High-quality Face Sketch Synthesis via Geometric Normalization and Regularization Xiang Li (Hangzhou Dianzi University); Fei Gao (Hangzhou Dianzi University)*; Fei Huang (Hangzhou Dianzi University)
P24 Cross-modal and multi-modal media analysis I
Time  
Chair Jun Wan (NLPR, CASIA)
ID Title Author
182 Efficient Online Label Consistent Hashing for Large-Scale Cross-Modal Retrieval Jinhan Yi (Huaqiao University)*; Xin Liu (Huaqiao University); Yiu-ming CHEUNG (Hong Kong Baptist University); Xing Xu (University of Electronic Science and Technology of China); Wentao Fan (Huaqiao University); Yi He (Huaqiao University)
197 Adversarial Disentanglement and Correlation Network for RGB-Infrared Person Re-identification Bingyu Hu (University of Science and Technology of China)*; Jiawei Liu (University of Science and Technology of China); Zheng-Jun Zha (University of Science and Technology of China)
285 LAVS: A Lightweight Audio-visual Saliency Prediction Model dandan zhu (Shanghai Jiao Tong University)*; Defang Zhao (Tongji University); Xiongkuo Min (Shanghai Jiao Tong University); Tian Han (Stevens Institute of Technology); Qiangqiang Zhou (Jiangxi Normal University); Shaobo Yu (East China Normal University); yongqing chen ( Hainan Air Traffic Management Sub-Bureau); Guangtao Zhai (Shanghai Jiao Tong University); Xiaokang Yang (Shanghai Jiao Tong University of China)
458 Distance Restricted Transformer Encoder for Multi-label Classification Xiaomei Wang (Fudan University); Yaqian Li (OPPO Research Institute)*; Tong Luo (OPPO Research Institute); Yandong Guo (OPPO Research Institute); Yanwei Fu (Fudan University); Xiangyang Xue (Fudan University)
494 Learning Controlled Semantic Embedding for Cross-Modal Retrieval Yong Yang (Guangdong University of Technology); Min Meng (Guangdong University of Technology)*; Jun Yu (HDU); Jigang Wu ( Guangdong University of Technology)
570 A Language Prior Based Focal Loss for Visual Question Answering Mingrui Lao (Leiden University); Yanming Guo (National University of Defense Technology)*; Yu Liu (Dalian University of Technology); Michael S Lew (Leiden University)
P25 Multimedia activity analysis and understanding
Time  
Chair Tsung-Wei Huang (Dolby Labs)
ID Title Author
139 Complex Action Segmentation in Compressed Videos Hongfeng Han (Renmin University of China); Guoxing Yang (Renmin University of China); Yuqi Huo (Renmin University of China); Zhiwu Lu (Renmin University of China)*; Ji-Rong Wen (Renmin University of China)
478 Temporal Label Aggregation for Unintentional Action Localization Nuoxing Zhou (Tsinghua University); Guangyi Chen (Tsinghua University); Jinglin Xu (Tsinghua University); WEI-SHI ZHENG (Sun Yat-sen University, China); Jiwen Lu (Tsinghua University)*
1211 CONTEXT DRIVEN NETWORK WITH BAYES FOR WEAKLY SUPERVISED TEMPORAL ACTION  LOCALIZATION Jiaruo Yu (Chongqing University)*; Yongxin Ge (Chongqing University); ziqiang li (Chongqing university); Zhongming Chen (Chongqing University); xiaolei qin (Chongqing University)
1239 HIERARCHICAL TRANSFORMER: UNSUPERVISED REPRESENTATION LEARNING FOR SKELETON-BASED HUMAN ACTION RECOGNITION Yi-Bin Cheng (Sun Yat-sen university)*; Xipeng Chen (Sun Yat-sen University); Junhong Chen (Sun Yat-sen University); Pengxu Wei (Sun Yat-sen University); Dongyu Zhang (Sun Yat-sen University); Liang Lin (Sun Yat-sen University)
1487 Action Category and Phase Consistency Regularization for High-quality Temporal Action Proposal Generation Yushu Liu (Harbin Institute of Technology, Weihai)*; Weigang Zhang (Harbin Institute of Technology, Weihai); Guorong Li (University of Chinese Academy of Sciences); Qingming Huang (University of Chinese Academy of Sciences)
1500 Spatial-Temporal Human-Object Interaction Detection Xu Sun (Nanjing University); Yunqing He (Nanjing University); Tongwei Ren (Nanjing University)*; Gangshan Wu (Nanjing University)
P26 Emerging multimedia applications and technologies
Time  
Chair Austin Shuai (National Chiao Tung University)
ID Title Author
1127 MSFC: DEEP FEATURE COMPRESSION IN MULTI-TASK NETWORK Zhicong Zhang (Huawei & Harbin Institute of Technology); Mengyang Wang (Huawei & Harbin Institute of Technology); Mengyao Ma (Huawei); Jiahui Li (Huawei); Xiaopeng Fan (Harbin Institute of Technology)*
1250 Towards GANs' Approximation Ability Xuejiao Liu (Qian Xuesen Laboratory of Space Technology); Yao Xu (Qian Xuesen Laboratory of Space Technology); Xueshuang Xiang (Qian Xuesen Laboratory of Space Technology)*
1485 FedNS: Improving Federated Learning for collaborative image classification on mobile clients Yaoxin Zhuo (Arizona State University)*; baoxin Li (Arizona State University)
1555 Universal Adversarial Training with Class-Wise Perturbations Philipp Benz (KAIST)*; Chaoning Zhang (KAIST); Adil Karjauv (KAIST); In So Kweon (KAIST)
1573 Heterogeneous Federated Learning through Multi-branch Network Ching-Hao Wang (NCTU); Kang-Yang Huang (National Chiao Tung University)*; Jun-Cheng Chen (Academia Sinica); Hong-Han Shuai (National Chiao Tung University); Wen-Huang Cheng (National Chiao Tung University)
1159 MotionSnap: A Motion Sensor-Based Approach for Automatic Capture and Editing of Photos and Videos on Smartphones Adil Karjauv (KAIST); Sanzhar  Bakhtiyarov (KAIST); Chaoning Zhang (KAIST)*; Jean-Charles Bazin (KAIST); In So Kweon (KAIST)
P27 Multimedia Applications II
Time  
Chair Xinggong Zhang (Peking University)
ID Title Author
175 SHORT VIDEO STREAMING WITH DATA WASTAGE AWARENESS Guanghui Zhang (The Hong Kong Polytechnic University (PolyU)); Ke Liu (Chinese Academy of Sciences); Haibo Hu (Hong Kong Polytechnic University)*; Jing Guo (Bank of Communications)
1202 PSTR: Per-title encoding using Spatio-Temporal Resolutions Hadi Amirpour (Alpen-Adria-Universität Klagenfurt)*; Christian Timmerer (Alpen-Adria-Universität Klagenfurt); Mohammad Ghanbari (University of Essex)
872 LEARNING CONNECTED ATTENTIONS FOR CONVOLUTIONAL NEURAL NETWORKS Xu Ma (University of North Texas)*; Jingda Guo (University of North Texas); Sihai Tang (University of North Texas); Zhinan Qiao (University of North Texas); Qi Chen (University of North Texas); Qing Yang (University of North Texas); Song Fu (University of North Texas); Paparao Palacharla (Fujitsu Network Communications); Nannan Wang (Fujitsu Network Communications); Xi Wang (Fujitsu Network Communications)
1026 Learned Image Coding for Machines: A Content-Adaptive Approach Nam H Le (Tampere University)*; Honglei Zhang (Nokia Technologies); Francesco Cricri (Nokia Technologies); Ramin Ghaznavi Youvalari (Nokia Technologies); Hamed Rezazadegan Tavakoli (Nokia Technologies); Esa Rahtu (Tampere University)
1095 Toward Effective Automated Content Analysis via Crowdsourcing Jiele Wu (BIT); Chau-Wai Wong (NC State University)*; Xinyan Zhao (UNC-CH); Xianpeng Liu (NC State University)
P28 Special Session: Deep Learning for Multimedia Applications with Limited Supervision
Time  
Chair Mang Ye (Wuhan University)
ID Title Author
164 Both Comparison and Induction are Indispensable for Cross-Domain Few-shot Learning Wang Yuan (East China Normal University); TianXue Ma (East China Normal University); Haichuan Song (East China Normal University); Yuan Xie (East China Normal University); Zhizhong Zhang (East China Normal University); Lizhuang Ma (East China Normal University)*
166 CROSS-MODALITY GRAPH NEURAL NETWORK FOR FEW-SHOT LEARNING ShuBao Liu (East China Normal University)*; Yuan Xie (East China Normal University); Wang Yuan (East China Normal University); Lizhuang Ma (East China Normal University)
185 Improving weakly supervised object localization by uncertainty estimation of pseudo supervision Xi Chen (Sun Yat-sen University); Andy J Ma (Sun Yat-sen University)*; Nanxi Guo (Sun Yat-sen University); Jiajia Chen (Sun Yat-sen University)
203 Weakly-Supervised Image Semantic Segmentation Using Graph Convolutional Networks Shun-Yi Pan ( National Chiao Tung University); Cheng-You Lu (National Yang Ming Chiao Tung University); Shih-Po Lee (National Chiao Tung University); Wen-Hsiao Peng (National Chiao Tung University)*
216 Attention-Guided Semantic Hashing for Unsupervised Cross-Modal Retrieval Xiao Shen (Nanjing University of Science and Technology); Haofeng Zhang (Nanjing University of Science and Technology)*; Lunbo Li ( Nanjing University of Science and Technology); Li Liu (the inception institute of artificial  intelligence)
233 Semi-DerainGAN: A New Semi-supervised Single Image Deraining Network Yanyan Wei (Hefei University of Technology); Zhao Zhang (Hefei University of Technology)*; Yang Wang (Hefei University of Technology); Haijun Zhang (Harbin Institute of Technology (Shenzhen)); Mingbo Zhao (Donghua University); Mingliang Xu (Zhengzhou University); Meng Wang (Hefei University of Technology)
P29 Multimedia representation learning
Time  
Chair Hongxing Wang (Chongqing University)
ID Title Author
12 Intra-Class Uncertainty Loss Function for Classification He Zhu ( Brainnetome Center and NLPR; School of Future Technology, UCAS; University of Chinese Academy of Sciences; Institute of Automation, Chinese Academy of Sciences)*; Shan Yu (Brainnetome Center and NLPR;University of Chinese Academy of Sciences;CAS Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences;)
198 PROGRESSIVE DISTRIBUTION ALIGNMENT BASED ON LABEL CORRECTION FOR UNSUPERVISED DOMAIN ADAPTATION Yong Li (Shenzhen University); desheng Li (Shenzhen University)*; Yuwu Lu (Shenzhen University); can gao (Shenzhen University); wenjing Wang (Shenzhen University); Jianglin Lu (Shenzhen University)
240 LPCC-Net: RGB Guided Local Point Cloud Completion for Outdoor 3D Object Detection Yufei Wei (Shanghai Em-Data Technology Co., Ltd. ); Yao Xiao (Shanghai Em-Data Technology Co., Ltd.); Yibo Guo (Shanghai Em-Data Technology Co., Ltd.); Shichao Liu (Shanghai EM-data Technology Co., Ltd.); Lin Xu (Shanghai Em-Data Technology Co., Ltd.)*
505 VISUAL AND SEMANTIC FEATURE COORDINATED BI-LSTM MODEL FOR UNSUPERVISED VIDEO SUMMARIZATION Zhiqiang Hong (Central China Normal University); Rui Zhong (Central China Normal University)*
634 Semi-Supervised Few-Shot Learning with Pseudo Label Refinement Pan Li (Queen Mary University of London)*; Guile Wu (Queen Mary University of London); Shaogang Gong (Queen Mary University of London); Xu Lan (Queen Mary University of London)
788 MGARL: Multiple Graph Adversarial Regularized Learning Ziyan Zhang (Anhui University); Bo Jiang (Anhui University)*; Bin Luo (Anhui University)
P30 Speech/audio synthesis and coding
Time  
Chair Kong Aik Lee (Institute for Infocomm Research, A*STAR)
ID Title Author
565 MULTI-SCALE GATED ATTENTION FOR WEAKLY LABELLED SOUND EVENT DETECTION HOU ZHENWEI (CQU)*; Yang Liping (CQU)
1483 Cross-Language Transfer Learning and Domain Adaptation for End-to-End Automatic Speech Recognition Jian Luo (Ping An Technology (Shenzhen) Co., Ltd.)*; Jianzong Wang (Ping An Technology (Shenzhen) Co., Ltd); Ning Cheng (Ping An Technology (Shenzhen) Co., Ltd); Edward Xiao (Ping An Technology (Shenzhen) Co., Ltd); Jing Xiao (Ping An Insurance (Group) Company of China); Georg Kucsko (Kensho); Patrick O'Neill (Kensho); Jagadeesh Balam (NVIDIA); Slyne Deng (NVIDIA); Adriana Flores (NVIDIA); Boris Ginsburg (NVIDIA); Jocelyn Huang (NVIDIA); Oleksii Kuchaiev (NVIDIA); Vitaly Lavrukhin (NVIDIA); Jason Li (NVIDIA)
1601 SPEECH SYNTHESIS OF CHINESE BRAILLE WITH LIMITED TRAINING DATA Jianguo Mao (Institute of Computing Technology, Chinese Academy of Sciences)*; Jingwen Zhu (Institute of Computing Technology, Chinese Academy of Sciences); Xiangdong Wang (Institute of Computing Technology, Chinese Academy of Sciences); Hong Liu (Institute of Computing Technology, Chinese Academy of Sciences); Yueliang Qian (Institute of Computing Technology, Chinese Academy of Sciences)
636 A Result based Portable Framework for Spoken Language Understanding Lizhi Cheng (Shanghai Jiaotong University )*; Wenmian Yang (National University of Singapore); Weijia Jia (Institute of AI and Future Networks, Beijing Normal University (Zhuhai); BNU-HKBU United International College, Zhuhai, PR China; Shanghai Jiao Tong University)
957 Spiker-Converter: A Semi-supervised Framework for Low-resource Speech Recognition with Stable Adversarial Training Cheng Yi (University of Chinese Academy of Sciences)*; Bo Xu (Institute of Automation, Chinese Academy of Sciences)
P31 Image/video acquisition, compression, and procesing
Time  
Chair Wenhan Yang (Peking University)
ID Title Author
1512 Unsupervised HDR Image Reconstruction Based on Over/Under-Exposed LDR Image Pair Hao Wang (Rochester Institute of Technology); Zhang Tao (Tianjin University); Guoyu Lu (Rochester Institute of Technology)*
875 Machine Learning-based Rate Distortion Modeling for VVC/H.266 Intra-Frame Miaohui Wang (Shenzhen University); Jialin Zhang (Shenzhen University)*; Lirong Huang (Shenzhen University); Jian Xiong (Univeristy of Posts and Telecommunications)
1066 SEMI-SUPERVISED LEARNING BY EXPLOITING UNLABELED DATA CORRELATIONS IN A DUAL-BRANCH NETWORK Jie Ling (Sun Yat-sen University); Meng Yang (Sun Yat-sen University)*
1507 Rate-Distortion Optimized Hierarchical Deep Feature Compression Ademola Ikusan (University of Cincinnati)*; Rui Dai (University of Cincinnati)
258 Consistent Representation Learning across Modalities for Zero-Shot Image Recognition Yu Wang (Tongji University)*; S-J Zhao (HaiBa Technology)
355 Geometric Transformation-based Network Ensemble  for Open-set Recognition Pramuditha Perera (Amazon); Vishal Patel (Johns Hopkins University)*
P32 Cross-modal and multi-modal media analysis II
Time  
Chair Raouf Hamzaoui (De Montfort University)
ID Title Author
580 Detecting Highlighted Video Clips via Emotion-enhanced Audio-Visual Cues Linkang Hu (University of Science and Technology of China)*; Weidong He (University of Science and Technology of China); Le Zhang (University of Science and Technology of China); Tong Xu (University of Science and Technology of China); Hui  Xiong (the State University of New Jersey); Enhong Chen (University of Science and Technology of China)
783 DEEP FEATURE SELECTION-AND-FUSION FOR RGB-D SEMANTIC SEGMENTATION Yuejiao Su (Northwestern Polytechnical University); Yuan Yuan ( Northwestern Polytechnical University); Zhiyu Jiang (Northwestern Polytechnical University)*
834 CI-GAN: Co-clustering by Information Maximizing Generative Adversarial Networks Jaejun Lee (University of Waterloo)*; Chul Lee (Amazon); Tomasz Palczewski (Samsung Research America)
854 What Matters: Attentive and Relational Feature Aggregation Network for Video-Text Retrieval Xiaoshuai Hao (Institute of information technology, Chinese Academy of Sciences); Yucan Zhou (Chinese Academy of Sciences)*; Dayan Wu (Institute of Information Engineering, Chinese Academy of Sciences); Wanqian Zhang (Institute of Information Engineering, Chinese Academy of Sciences); Bo Li ( Institute of Information Engineering, Chinese Academy of Sciences); Weiping Wang (Institute of Information Engineering, CAS, China); Dan Meng (Institute of Information Engineering, CAS)
1220 Cognition-driven Real-time Personality Detection via Language-guided Contrastive Visual Attention Xiaoya Gao (Soochow University); Jingjing Wang ( Soochow University)*; Shoushan Li (Soochow University); Zhou Guodong (Soochow University)
1280 Multi-Knowledge Fusion Network for Generalized Zero-Shot Learning Hongxin Xiang (Yunnan University); Cheng Xie (Yunnan University); Ting Zeng (Yunnan University); yun yang (yunnan university)*
P33 Multimedia semantic segmentation
Time  
Chair Nikos Nikolaidis (Aristotle University of Thessaloniki)
ID Title Author
238 GSVNet: Guided Spatially-Varying Convolution for Fast Semantic Segmentation on Video Shih-Po Lee (National Chiao Tung University); Si-Cun Chen (National Chiao Tung University); Wen-Hsiao Peng (National Chiao Tung University)*
292 Cross-Modal Guidance for Hyperfluorescence Segmentation in Fundus Fluorescein Angiography Chuan Zhou (School of Computer Science and Engineering, University of Electronic Science and Technology of China); Tian Zhang (School of Computer Science and Engineering, University of Electronic Science and Technology of China); Yang Wen (School of Computer Science and Engineering, University of Electronic Science and Technology of China); Leiting Chen (School of Computer Science and Engineering, University of Electronic Science and Technology of China)*; Lei Zhang (School of Computer Science and Engineering, University of Electronic Science and Technology of China); Junjing Chen (School of Computer Science and Engineering, University of Electronic Science and Technology of China)
572 DOBNet: Dynamic Object Boundary-refinement Network for Real-time Instance Segmentation Boxiang Zhang (Jilin University); Yuanyuan Guan (Jilin University); Hongru Liu (Jilin University); Wenhui Li (Jilin University)*; Ying Wang (Jilin University)
610 Confident Semantic Ranking Loss for Part Parsing Xin Tan (Shanghai Jiao Tong University)*; Jiachen Xu (Shanghai Jiao Tong University); Zhou Ye (CLS Fintech); Jinkun Hao (East China University of Science and Technology); Lizhuang Ma (Shanghai Jiao Tong University)
1014 Input-Output Balanced Framework for Long-tailed LiDAR Semantic Segmentation Peishan Cong (ShanghaiTech); Xinge Zhu (The Chinese University of Hong Kong); Yuexin Ma (ShanghaiTech University)*
1319 ARNet: Active-Reference Network for Few-shot Image Semantic Segmentation Guangchen Shi (Hohai University); Wu Yirui (Hohai University)*; Shivakumara Palaiahnakote (University of Malaya); Umapada Pal  (Indian Statistical Institute, Kolkata); Tong Lu (Nanjing University)
P34 Multimedia interaction & Multimedia quality assessment
Time  
Chair Arijit Biswas (Dolby Labs)
ID Title Author
1530 A JENSEN-SHANNON DIVERGENCE DRIVEN METRIC OF VISUAL SCANNING EFFICIENCY INDICATES PERFORMANCE OF VIRTUAL DRIVING Zezhong Lv (College of Intelligence and Computing, Tianjin University); Qing Xu (College of Intelligence and Computing, Tianjin University)*; Klaus Schoeffmann (Klagenfurt University); Simon Parkinson (University of Huddersfield)
1151 Multimodal Disentangled Representation for Recommendation Xin Wang (Tsinghua University)*; Hong Chen (Tsinghua University); Wenwu Zhu (Tsinghua University)
1149 Multi-view Clustering Based on Self-Weighted High-order Similarity Fusion Hong Peng (South China University of Technology); Hongmin Cai (South China University of Technology)*
234 Spatial Attention-based Non-reference Perceptual Quality Prediction Network for Omnidirectional Images Li Yang (Beihang university)*; Mai Xu (BUAA); Xin Deng (Beihang university); Bo Feng (Columbia University )
396 Neurophysiological Assessment of Image Quality from EEG Using Persistent Homology of Brain Network Chang Liu ( Communication University of Zhejiang); Xiaoyu Ma (Communication University of Zhejiang ); Jiaojiao Wang (Communication University of Zhejiang ); Jiefang Zhang (Communication University of Zhejiang ); Honggang Zhang (Zhejiang University); Songyun Xie (Northwestern Polytechnical University); Dingguo Yu (Communication University of Zhejiang)*
122 Blind Quality Assessment of Night-Time Images via Weak Illumination Analysis Miaohui Wang (Shenzhen University)*; Yijing Huang (Shenzhen University); Jialin Zhang (Shenzhen University)