Keynote Talk: Mar Gonzalez Franco

Session Chair: Zhu Li, University of Missouri, Kansas City, USA.

Wed, Jul 11, 09-10:00 AM

Room: Plaza Terrace

Coffee Break

SS4: Special Session: Multimedia-based Health Computing (Oral)

Session Chair: Dr. Xuequan Lu, Deakin University, Australia

Wed, Jul 12, 10:30 – 12:00

Room: Plaza Terrace

• Hierarchical Attention Learning for Multimodal Classification 

• Xin Zou (China University of Geosciences)
• Chang Tang (China University of Geosciences)
• Wei Zhang (Shandong Provincial Key Laboratory of Computer Networks, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences))
• Kun Sun (China University of Geosciences(Wuhan))
• Liangxiao Jiang (China University of Geoscience)

• An End-to-end Food Portion Estimation Framework Based on Shape Reconstruction from Monocular Image 

• Zeman Shao (Purdue University)
• Gautham Vinod (Purdue University)
• Jiangpeng He (Purdue University)
• Fengqing Zhu (Purdue University, USA)

• Unsupervised Domain Adaptation For Neuron Membrane Segmentation Based On Structural Features 

• Yuxiang An (The University of Sydney)
• Dongnan Liu (University of Sydney)
• Weidong Cai (University of Sydney)

• Latent Feature Regularization based Adversarial Network for Brain Tumor Anomaly Detection 

• Nan Wang (East China Normal University)
• Chengwei Chen (East China Normal University)
• Shaohui Lin (East China Normal University )
• Lizhuang Ma (East China Normal University)

• Development of Deep Learning Algorithms for Automated Scoliosis and Abnormal Posture Screening Using 2D Back Image 

• Zhenda XU (Hong Kong Polytechnic University)
• Hu Jiahao (Northwestern Polytechnical University)
• Qihua Zhou (The Hong Kong Polytechnic University)
• Song Guo (The Hong Kong Polytechnic University)
• Aiqian Gan (Univeristy of Sydney)

• LACL: Lesion-Aware Contrastive Learning Framework for Medical Image Classification 

• yu tang (Renming University of China)
• Gang Yang (Renmin University of China)
• Dayong Ding (Vistel Inc.)
• Jianchun Zhao (Vistel Inc.)
• Jun Wu (Northwestern Polytechnical University)

Session Chair Signature                                         Date/Time:

O15 - Storage, Transmission & Communication (Oral)

Session Chair: Jangwoo Son, Fraunhofer HHI

Wed, Jul 12, 10:30 – 12:00  

Room: P1

• Collaborative Edge Caching: a Meta Reinforcement Learning Approach with Edge Sampling 

• Yinan Mao (Tsinghua University)
• Bowei He (City University of Hong Kong)
• Shiji Zhou (Tsinghua University)
• Chen Ma (City University of Hong Kong)
• Zhi Wang (Tsinghua University)

• PACC: Perception Aware Congestion Control for Real-time Communication 

• Feng Peng (Shanghai Jiao Tong University)
• Bingcong Lu (Shanghai Jiao Tong University)
• Li Song (Shanghai Jiao Tong University)
• Rong Xie (Shanghai Jiao Tong University)

• Label-Semantic-Enhanced Online Hashing for Efficient Cross-modal Retrieval 

• xueting Jiang (Huaqiao University)
• Xin Liu (Huaqiao University)
• Yiu-ming CHEUNG (Hong Kong Baptist University)
• Xing Xu (University of Electronic Science and Technology of China)
• Shukai Zheng (Zhejiang Lab)
• Taihao Li (zhejianglab)

• QoE Maximization for Aerial Video Streaming with Multiple Cellular Connected UAVs 

• Cheng Zhan (Southwest University)
• huan yan (Southwest University)
• Han Hu (Beijing Institute of Technology, China)

• Multi-stream Adaptive Offloading of Joint Compressed Video Streams, Feature Streams, and Semantic Streams in Edge Computing Systems 

• Dieli Hu (the Institute of Computing Technology, Chinese Academy of Sciences)
• Wen Ji (Institute of Computing Technology, Chinese Academy of Sciences)
• Zhi Wang (Tsinghua University)

• L4S congestion Control algorithm for interactive low latency applications over 5G 

• Jangwoo Son (Fraunhofer HHI)
• Yago Sanchez de la Fuente (Fraunhofer HHI)
• Thomas Schierl (Fraunhofer HHI)
• Cornelius Hellge (Fraunhofer HHI)
• Christian Hampe (Deutsche Telekom)
• Dominik Schnieders (Deutsche Telekom)

Session Chair Signature                                         Date/Time:  

O16 - Action Detection & Localization (Oral)

Session Chair: Dr Amit Gupta VueMotion AI/DView AI, Australia 

Wed, Jul 12, 10:30 – 12:00  

Room: P2

• Weakly-supervised Temporal Action Localization with Adaptive Clustering and Refining Network 

• Hao Ren (Fudan University)
• Wu Ran (Fudan University)
• Xingson Liu (Fudan University)
• Haoran Ren (Fudan University)
• Hong Lu (Fudan University)
• Rui Zhang (Fudan University)
• Cheng Jin (Fudan University)

• Do we really need temporal convolutions in action segmentation? 

• Dazhao Du (Institute of Software Chinese Academy of Sciences)
• Bing Su (Renmin University of China)
• Yu Li (International Digital Economy Academy)
• Zhongang Qi (Tencent)
• Lingyu Si (Institute of Software Chinese Academy of Sciences)
• Ying Shan (Tencent)

• ELAN: Enhancing Temporal Action Detection with Location Awareness 

• Guo Chen (Nanjing University)
• Yin-Dong Zheng (Nanjing University, China)
• Zhe Chen (Nanjing University)
• Jiahao Wang (Nanjing University)
• Tong Lu (Nanjing University)

• MRSN: Multi-Relation Support Network for Video Action Detection 

• Yin-Dong Zheng (Nanjing University, China)
• Guo Chen (Nanjing University)
• Minglei Yuan (Nanjing University)
• Tong Lu (Nanjing University)

• Unleashing the Potential of Adjacent Snippets for Weakly-supervised Temporal Action Localization 

• Qinying Liu (University of Science and Technology of China)
• Zilei Wang (University of Science and Technology of China)
• Chen Ruoxi (University of Science and Technology of China)
• Zhilin Li (University of Science and Technology of China)

• Compositional Learning in Transformer-Based Human-Object Interaction Detection 

• Zikun Zhuang (Tongji University)
• Ruihao Qian (Tongji University)
• Chi Xie (Tongji University)
• Shuang Liang (Tongji University)

Session Chair Signature                                         Date/Time:

O17 - Contrastive Learning (Oral)

Session Chair: Prof. Manoranjan Paul, Charles Stuart University, Australia

Wed, Jul 12, 10:30 – 12:00

Room: P3

• Self-supervised Cross-stage Regional Contrastive Learning for Object Detection 

• Junkai Yan (Sun Yat-sen University)
• Lingxiao YANG (Sun-Yat Sen University)
• Yipeng Gao (Sun Yat-sen University, China)
• WEI-SHI ZHENG (Sun Yat-sen University, China)

• Hierarchical and Contrastive Representation Learning for Knowledge-aware Recommendation 

• Bingchao Wu (Institute of Software, Chinese Academy of Science)
• Yangyuxuan Kang (Institute of Software Chinese Academy of Sciences)
• Daoguang Zan (Cooperative Innovation Center, Institute of Software, Chinese Academy of Sciences & University of Chinese Academy of Sciences)
• Bei Guan (Chinese Academy of Sciences)
• Yongji Wang (Cooperative Innovation Center, Institute of Software, Chinese Academy of Sciences & University of Chinese Academy of Sciences)

• Colo-SCRL: Self-Supervised Contrastive Representation Learning for Colonoscopic Video Retrieval 

• Qingzhong Chen (Shanghai Jiao Tong University)
• Suncheng Xiang (Shanghai Jiao Tong University)
• Crystal Cai (Shanghai Jiao Tong University)
• Zefang Yu (Shanghai Jiao Tong University)
• Shilun Cai (Fudan University)
• Dahong Qian (Shanghai Jiao Tong Univerisity)

• Establishing a stronger baseline for lightweight contrastive models 

• Wenye Lin (Tsinghua Shenzhen International Graduate School, Tsinghua University)
• Yifeng Ding (Tsinghua University)
• Zhixiong Cao (Tsinghua Shenzhen International Graduate School, Tsinghua University)
• Hai-Tao Zheng (Tsinghua University)

• Graph Information Interaction on Feature and Structure via Cross-modal Contrastive Learning 

• Jinyong Wen (Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences)

• Discriminative and Contrastive Consistency for Semi-supervised Domain Adaptive Image Classification 

• yidan fan (Tianjin university)
• Wenhuan Lu (Tianjin University)
• Yahong Han (Tianjin University)

Session Chair Signature                                         Date/Time:

O18 - Sound Processing (Oral)

Session Chair: Dr. Bingkun Bao, Nanjing University of Posts and Telecommunications

Wed, Jul 12, 10:30 – 12:00

Room: P4

• COVERHUNTER: COVER SONG IDENTIFY WITH REFINED ATTENTION AND ALIGNMENTS 

• Feng Liu (Huya)
• Xintong Han (Huya Inc)
• Deyi Tuo (Huya.Inc)
• Yinan Xu (Huya Inc.)

• Exploring Pre-Trained Neural Audio Representations for Audio Topic Segmentation 

• Iacopo Ghinassi (Queen Mary University of London)
• Matthew Purver
• Huy Phan (Amazon Alexa)
• Chris Newell (BBC Research and Development)

• A HIGH-QUALITY MELODY-AWARE PEKING OPERA SYNTHESIZER USING DATA AUGMENTATION 

• xun zhou (Xiamen University)
• xiaodong shi (xiamen university)

• LC-Beating: An Online System for Beat and Downbeat Tracking using Latency-Controlled Mechanism 

• Xinlu Liu (Fudan University)
• Jiale Qian (Fudan University)
• Qiqi He (Fudan Univ.)
• Yi Yu (NII)
• Wei Li (Fudan University)

• Improving Domain Generalization for Sound Classification with Sparse Frequency-Regularized Transformer 

• Honglin Mu (Research Center for Social Computing and Information Retrieval, Harbin Institute of Technology)
• Wentian Xia (Research Center for Social Computing and Information Retrieval, Harbin Institute of Technology)
• Wanxiang Che (Research Center for Social Computing and Information Retrieval, Harbin Institute of Technology)

• MFAE: Masked frame-level features autoencoder with hybrid-supervision for low-resource music transcription 

• Yulun Wu (Fudan University)
• Jiahao Zhao (Fudan University)
• Yi Yu (NII)
• Wei Li (Fudan University)

Session Chair Signature                                         Date/Time:

O19 - 3D & Depth I (Oral)

Session Chair: Dr. Max Mühlhäuser, Technische Universität Darmstadt

Wed, Jul 12, 10:30 – 12:00

Room: P5

• SELF-SUPERVISED IMPLICIT 3D RECONSTRUCTION VIA RGB-D SCANS 

• Hongji Yang (Nankai University)
• Jiao Liu (Nankai University )
• Shao-Ping Lu (Nankai University)
• Bo Ren (Nankai University)

• OBJECT-AWARE CALIBRATED DEPTH-GUIDED TRANSFORMER FOR RGB-D CO-SALIENT OBJECT DETECTION 

• Yang Wu (nuist)
• Kaihua Zhang (Inspur，NUIST)
• lingyan liang (inspur)
• Yaqian Zhao (Inspur)

• A Two-stage Hybrid CNN-Transformer Network for RGB Guided Indoor Depth Completion 

• Yufan Deng (Beihang University)
• Xin Deng (Beihang university)
• Mai Xu (BUAA)

• FEATURE DECOUPLING AND UNCERTAINTY ESTIMATION FOR 3D OBJECT DETECTION 

• Peiyuan Zhi (Tsinghua University)
• Ya-Li Li (Tsinghua University)
• Kaiyue Zhou (Wayne State University)
• Shengjin Wang (Tsinghua University)

• Scene Graph Generation using Depth-based Multimodal Network 

• Lianggangxu Chen (East China Normal University)
• Jiale Lu (East China Normal University)
• Changbo Wang (East China Normal University)
• Gaoqi He (East China Normal University)

• Multi-View Token Clustering and Fusion for 3D Object Recognition and Retrieval 

• Linlong Fan (University of Electronic Science and Technology of China)
• Yanqi Ge (University of Electronic Science and Technology of China)
• Wen Li (University of Electronic Science and Technology of China)
• Lixin Duan (University of Electronic Science and Technology of China)

Session Chair Signature                                         Date/Time:

O20 - Transformer I (Oral)

Session Chair: Dr. Zhan Ma, Nanjing University

Wed, Jul 12, 10:30 – 12:00

Room: M9

• Local Consensus Transformer for Correspondence Learning 

• Gang Wang (Shanghai University of Finance and Economics)
• Yufei Chen (Tongji University)

• Preserving Locality in Vision Transformers for Class Incremental Learning 

• Bowen Zheng (Nanjing University)
• Da-Wei Zhou (Nanjing University)
• Han-Jia Ye (Nanjing University)
• De-Chuan Zhan (Nanjing University)

• MTNet: Learning modality-aware representation with transformer for RGBT tracking 

• Ruichao Hou (Nanjing University)
• Boyue Xu (Nanjing University)
• Tongwei Ren (Nanjing University)
• Gangshan Wu (Nanjing University)

• Adaptive Split-Fusion Transformer 

• Zixuan Su (Fudan University)
• Jingjing Chen (Fudan University)
• Lei Pang (City University of Hong Kong)
• Chong-Wah Ngo (Singapore Management University)
• Yu-Gang Jiang (Fudan University)

• GSFormer: Geometric-Spatial Transformer on Point Cloud Completion 

• Jun Long (Fudan University)
• Zhaoyu Chen (Fudan University)
• Hong Lu (Fudan University)
• Wenqiang Zhang (Fudan University)

• SDGFormer: An Efficient Convolution Network Structurally Similar to Transformer 

• chaohao wen (Southwest Jiaotong University)

Session Chair Signature                                         Date/Time:

P7 - Security, Privacy & Forensics I (Poster)

Session Chair: Prof. Brian C. Lovell, University of Queensland, Australia

Wed, Jul 12, 10:30 – 12:00

Room: Plaza Foyer

• General GAN-Generated Image Detection by Data Augmentation in Fingerprint Domain 

• Huaming Wang (Jinan University)
• Jianwei Fei (Nanjing University of Information Science and Technology)
• Yunshu Dai (Nanjing University of Information Science and Technology)
• leng lingyun (Jinan University)
• Zhihua Xia (Jinan University)

• Image Protection for Robust Cropping Localization and Recovery 

• Qichao Ying (School of Computer Science, Fudan University)
• Hang Zhou (Simon Fraser University)
• Xiaoxiao Hu (School of Computer Science, Fudan University)
• Zhenxing Qian (School of Computer Science, Fudan University)
• Sheng Li (Fudan University)
• Xinpeng Zhang (School of Computer Science, Fudan University)

• Towards Diverse Liveness Feature Representation and Domain Expansion for Cross-Domain Face Anti-Spoofing 

• Pei-Kai Huang (National Tsing Hua University)
• Jun-Xiong Chong (National Tsing Hua University)
• Hui-Yu Ni (National Tsing Hua University)
• Tzu-Hsien Chen (National Tsing Hua University)
• Chiou-Ting Hsu (National Tsing Hua University)

• Joint Statistical and Causal Feature Modulated Face Anti-Spoofing 

• Xin Dong (Ningxia University)
• Tao Wang (Ningxia University)
• Zhendong Li (Ningxia University)
• Hao Liu (Ningxia University)

• Watermarks for Generative Adversarial Network Based on Steganographic Invisible Backdoor 

• Yuwei Zeng (Fudan University)
• Jingxuan Tan (Fudan University)
• Zhengxin You (Fudan University)
• Zhenxing Qian (School of Computer Science, Fudan University)
• Xinpeng Zhang (School of Computer Science, Fudan University)

• Promoting adversarial transferability with enhanced loss flatness 

• Yan Fang (Wuhan University)
• Zhongyuan Wang (Wuhan University)
• jikang cheng (Wuhan university)
• Ruoxi Wang (Jianghan University)
• Chao Liang (Wuhan University)

• Face Poison: Obstructing DeepFakes by Disrupting Face Detection 

• Yuezun Li (Ocean University of China)
• Jiaran Zhou (Ocean University of China)
• Siwei Lyu (University at Buffalo)

• ABTD‐Net: Autonomous Baggage Threat Detection networks for X‐ray images. 

• Wen Liu (Institute of Information Engineering, Chinese Academy of Sciences)
• degang Sun (Institute of Information Engineering，Chinese Academy of Sciences)
• Yan Wang (Institute of Information Engineering,Chinese Academy of Sciences)
• haitian yang (Institute of Information Engineering,Chinese Academy of Sciences)

• An Explainable Multi-view Semantic Fusion Model for Multimodal Fake News Detection 

• zhi zeng (Huazhong Agricultural University)
• mingmin wu (Huazhong Agricultural University)
• Li Xiang (College of Informatics of Huazhong Agriculture University)
• Guodong Li (Xinjiang Technical Institute of Physics and Chemistry, Chinese Academy of Sciences)
• Ying Sha (College of Informatics, Huazhong Agricultural University, Wuhan, China.)

• Improving CoatNet for spatial and JPEG domain steganalysis 

• Hao Li (The State Key Laboratory of Mathematical Engineering and Advanced Computing)
• Xiangyang Luo (State Key Laboratory of Mathematical Engineering and Advanced Computing)
• Yi Zhang (State Key Laboratory of Mathematical)

Session Chair Signature                                         Date/Time:

P8 - Super Resolution & Inpainting II (Poster)

Session Chair:  A/Prof. Zhu Li, University of Missouri, Kansas City, USA.

Wed, Jul 12, 10:30 – 12:00

Room: Plaza Foyer

• Image Super-Resolution with Implicit Texture Pattern Modulation 

• Shuai Hao (Dalian University of Technology)
• Jialin Yang (Dalian University of Technology )
• Xu Jia (Dalian University of Technology)
• You He (Naval Aviation University)
• Huchuan Lu (Dalian University of Technology)

• TOWARDS EFFICIENT LARGE MASK INPAINTING VIA KNOWLEDGE TRANSFER 

• Feihong Qin (Nanjing University of Aeronautics and Astronautics)
• Liyan Zhang (Nanjing University of Aeronautics and Astronautics)

• GRNN:Recurrent Neural Network based on Ghost Features for Video Super-Resolution 

• GUO YUTONG (East China University of Science and Technology)

• Structure First Detail Next: Image Inpainting with Pyramid Generator 

• Shuyi Qu (Northwest University)
• Zhenxing Niu (Alibaba Group)
• Jianke Zhu (Zhejiang University)
• Kaizhu Huang (Duke Kunshan University)

• LEARNING A MULTILEVEL COOPERATIVE VIEW RECONSTRUCTION NETWORK FOR LIGHT FIELD ANGULAR SUPER-RESOLUTION 

• Deyang Liu ( Jiangxi University of Finance and Economics)
• MAO YIFAN (AQNU)
• Xiaofei Zhou (Hangzhou Dianzi University)
• Ping An (Shanghai University)
• Yuming Fang (Jiangxi University of Finance and Economics)

• NLCUnet: Single-image super-resolution network with hairline details 

• Yuan-Gen Wang (Guangzhou University)
• fengchuang xing (guangzhou university)

• Progressive Generative Adversarial Network for High-Resolution Image Inpainting 

• Muzi Cui (Jinan University)
• Chaozhuo Li (Microsoft Research Asia)
• Zhiying Li (Jinan University)
• Yingze Xie (Beijing Foreign Studies University)
• Xing Xie (Microsoft Research Asia)
• Feiran Huang (Jinan University)

Session Chair Signature                                         Date/Time:

Lunch Break (12:00 – 13:30)

SS5: Special Session: Quality Enhancement And Assessment For Low-Quality Multimedia Data Understanding (Oral)

Session Chair: Dr. Frederic Dufuax,CNRS, France

Wed, Jul 12, 13:30 – 15:00

Room: Plaza Terrace

• An Order-Complexity Model for Aesthetic Quality Assessment of Symbolic Homophony Music Scores 

• Xin Jin (Beijing Electronic Science and Technology Institute)
• Wu Zhou (Beijing Electronic Science and Technology Institute)
• Jinyu Wang (Beijing Electronic Science and Technology Institute)
• Duo Xu (Tianjin Conservatory of Music，Qingdao Academy of intelligent Industries )
• Yiqing Rong (Beijing Electronic Science and Technology Institute)
• Shuai Cui (University of California, Davis)

• Collaborative Auto-encoding for Blind Image Quality Assessment 

• Fei Zhou (Shenzhen University)
• Zehong Zhou (Shenzhen University)
• Guoping Qiu (University of Nottingham)

• NO REFERENCE IMAGE QUALITY ASSESSMENT VIA QUALITY DIFFERENCE LEARNING 

• Jiaming Xie (Guangdong University of Technology)
• Yu Luo (Guangdong University of Technology)
• Jie Ling (Guangdong University of Technology)
• guanghui Yue (Shenzhen university)

• Low-Light Image Enhancement by Learning Contrastive Representations in Spatial and Frequency Domains 

• Yi Huang (School of Information Engineering,Southwest University of Science and Technology)
• Xiaoguang Tu (Civil Aviation Flight University of China)

• Noise adaptive speech intelligibility enhancement based on improved StarGAN 

• Lanxin Zhao (Jianghan University)
• Dengshi Li (Jianghan University )
• Jing Xiao (Wuhan University)
• Chenyi Zhu (Jianghan University)

• Image Template Matching via Dense and Consistent Contrastive Learning 

• Bo Li (Northwestern Polytechnical University)
• Lin Wu (Swansea University)
• Deyin Liu (Anhui University)
• Hongyang Chen (Zhejiang Lab)
• Xianghua Xie (Swansea University)

Session Chair Signature                                         Date/Time:

O21 - UAV & Underwater Media Processing (Oral)

Session Chair: Dr. Ioannis Pitas, Aristotle University of Thessaloniki

Wed, Jul 12, 13:30 – 15:00

Room: P1

• Deep Reinforcement Learning with semi-expert distillation for autonomous UAV cinematography 

• Ioannis Mademlis ( Aristotle University of Thessaloniki)
• Andreas Sochopoulos (Aristotle University of Thessaloniki)
• Ioannis Pitas (Aristotle University of Thessaloniki)

• Learning Disentangled Representation with Mutual Information Maximization for Real-Time UAV Tracking 

• Xucheng Wang (Guilin University of Technology)
• xiangyang yang (Guilin university of technology)
• hengzhou ye (Guilin university of technology)
• Shuiwang Li (Guilin University of Technology)

• Transmission and Color-guided Network for Underwater Image Enhancement 

• Pan Mu (Zhejiang University of Technology)
• JING FANG (ZJUT)
• Cong Bai (Zhejiang University of Technology)

• Invertible Underwater Image Enhancement Network 

• Fei Li (China Agricultural University)
• Zhenbo Li (China Agricultural University)
• Xinxin zhang (China Agricultural University)
• Meng Ding (The State University of New York at Buffalo)
• Zikun Liu (Samsung Research China – Beijing (SRC-B))

• Towards Discriminative Representations with Contrastive Instances for Real-Time UAV Tracking 

• Dan Zeng (Southern University of Science and Technology)
• Mingliang Zou (Guilin University Of Technology)
• Xucheng Wang (Guilin University of Technology)
• Shuiwang Li (Guilin University of Technology)

• Underwater Image Enhancement with an Adaptive Self Supervised Network 

• Rizwan Khan (ZJNU)
• Atif Mehmood (KTH)

Session Chair Signature                                         Date/Time:

O22 - Sentiment, Expression & Emotion (Oral)

Session Chair: A/Prof. Zhu Li, University of Missouri, Kansas City, USA.

Wed, Jul 12, 13:30 – 15:00

Room: P2

• Privacy-Protected Facial Expression Recognition Augmented by High-Resolution Facial Images 

• Cong Liang (University of Science and Technology of China)
• Shangfei Wang (University of Science and Technology of China)
• Xiaoping Chen (University of Science and Technology of China)

• Multimodal Sentiment Analysis with Preferential Fusion and Distance-aware Contrastive Learning 

• Feipeng Ma (University of Science and Technology of China)
• Yueyi Zhang (University of Science and Technology of China)
• Xiaoyan Sun (University of Science and Technology of China)

• A Multi-view Co-learning Method for Multimodal Sentiment Analysis 

• Wenxiu Geng (Shandong University)
• Yulong Bian (Shandong University)
• Xiangxian Li (Shandong University)

• Multimodal Aspect-Based Sentiment Classification with Knowledge-Injected Transformer 

• Zenan Xu (Sun Yat-sen University)
• Qinliang Su (SUN YAT-SEN UNIVERSITY)
• Junxi Xiao (Sun Yat-sen University)

• STA-GCN:Spatial Temporal Adaptive Graph Convolutional Network for Gait Emotion Recognition 

• chuang chen (Anhui University)
• Xiao Sun (Institute of Artificial Intelligence, Hefei Comprehensive National Science Center (Anhui Artificial Intelligence Laboratory))

• Adaptive graph attention network with temporal fusion for micro-expressions recognition 

• Yiming Zhang (University of Science and Technology of China)
• Sirui Zhao (University of Science and Technology of China)
• Hao Wang (University of Science and Technology of China)
• Yifan Xu (University of Science and Technology of China)
• Xinglong Mao (USTC)
• Tong Xu (University of Science and Technology of China)
• Enhong Chen (University of Science and Technology of China)

Session Chair Signature                                         Date/Time:

O23 - Transformer II (Oral)

Session Chair: Dr. Zhi Li, East China Normal University

Wed, Jul 12, 13:30 – 15:00

Room: P3

• DEEP HOMOGRAPHY ESTIMATION WITH FEATURE CORRELATION TRANSFORMER 

• Haoyu Zhou (Wuhan University)
• Li Ying (Wuhan University)
• Chu He (Wuhan University)
• Xi Chen (Wuhan university)

• ADATS: Adaptive RoI-Align based Transformer for End-to-End Text Spotting 

• Zepeng Huang (Shenzhen University)
• Qi Wan (Shenzhen University)
• Junliang Chen (Shenzhen University)
• Xiaodong Zhao (Shenzhen University)
• Kai Ye (Shenzhen University)
• Linlin Shen (Shenzhen University)

• Trajectory Alignment based Multi-Scaled Temporal Attention for Efficient Video Transformer 

• Zao Zhang (The University of Sydney)
• Dong Yuan (The University of Sydney)
• Yu Zhang (University of Sydney)
• Wei Bao (The University of Sydney)

• Swin-ASNet: An Adaptive RGB-selection Network with Swin Transformer for Retinal Vessel Segmentation 

• Qunchao Jin (East China Normal University)
• Hongyu Hou (East China Normal University)
• Guixu Zhang (East China Normal University)
• Haoan Wang (East China Normal University)
• Zhi Li (East China Normal University)

• OAFormer: Occlusion Aware Transformer for Camouflaged Object Detection 

• xin Yang (FuJian University of Technology)
• hengliang Zhu (FuJian University of Technology)

• Know Who You Are: Learning Target-Aware Transformer for Object Tracking 

• Zhuojun Zou (Institute of Automation, Chinese Academy of Sciences; School of Artificial Intelligence, University of Chinese Academy of Sciences)
• Xuexin Liu (School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, 100083)
• Yuanpei Zhang (Institute of Automation, Chinese Academy of Sciences; School of Artificial Intelligence, University of Chinese Academy of Sciences)
• lin shu (Institute of Automation, Chinese Academy of Sciences)
• jie hao (Institute of Automation，Chinese Academy of Sciences)

Session Chair Signature                                         Date/Time:

O24 - Model Simplification (Oral)

Session Chair: Dr. Bin Jiang, Hunan University

Wed, Jul 12, 13:30 – 15:00

Room: P4

• A Novel Channel Pruning Approach Based on Local Attention and Global Ranking for CNN Model Compression 

• Wei Lu (Tianjin University)
• Jiang Yang (Tianjin University)
• Peiguang Jing (Tianjin University)
• Jinghui Chu (Tianjin University)
• Fugui Fan (Tianjin University)

• Splittable Pattern-specific Weight Pruning For Deep Neural Networks 

• Yiding Liu (Beijing University of Posts and Telecommunications)
• Tao Niu (Beijing University of Posts and Telecommunications)

• Dynamic Dense-Sparse Representations for Real-Time Question Answering 

• Minyu Sun (Hunan University)
• Bin Jiang (Hunan University)
• Chao Yang (Hunan University)

• DynaSlim: Dynamic Slimming for Vision Transformers 

• Da Shi (SJTU)
• Jingsheng Gao (Shanghai Jiao Tong University)
• Ting Liu (Shanghai Jiao Tong University)
• Yuzhuo Fu (sjtu)

• Post-training Quantization for Vision Transformer in Transformed Domain 

• Kai Feng (University of Chinese Academy of Sciences)
• Zhuo Chen (Nanyang Technological University)
• Long Xu (National Astronomical Observatories)
• Weisi Lin (Nanyang Technological University, Singapore)

• Residual based hierarchical feature compression for multi-task machine vision 

• Chaoran Chen (Beihang University)
• Mai Xu (BUAA)
• Shengxi Li (Beihang University)
• Tie Liu (BUAA)
• Minglang Qiao (BUAA)
• Zhuoyi Lv (vivo)

Session Chair Signature                                         Date/Time:

O25 - Cross-Modality & Cross-Domain (Oral)

Session Chair: Dr. Wen Wang, Zhejiang Lab

Wed, Jul 12, 13:30 – 15:00

Room: P5

• Cross-domain Federated Object Detection 

• Shangchao Su (Fudan University)
• Bin Li (Fudan University)
• Zhang Chengzhi (Fudan University)
• Mingzhao Yang (Fudan University)
• Xiangyang Xue (Fudan University)

• Cross-Modality Fourier Feature for Medical Image Synthesis 

• mei ma (NingxiaUniversity)
• Ling Lin (NingXia University)
• Heng Wang (Ningxia University)
• Zhendong Li (Ningxia University)
• Hao Liu (Ningxia University)

• Point-Syn2Real: Semi-Supervised Synthetic-to-Real Cross-Domain Learning for Object Classification in 3D Point Clouds 

• Ziwei Wang (CSIRO)
• Reza Arablouei (CSIRO)
• Jiajun Liu (CSIRO)
• Paulo Borges (CSIRO)

• Temporal-enhanced Cross-modality Fusion Network for Video Sentence Grounding 

• Zezhong Lv (Renmin University of China)
• Bing Su (Renmin University of China)

• A Cross-direction Task Decoupling Network for Small Logo Detection 

• Sujuan Hou (Shandong Normal University)
• Xingzhuo Li (Shandong Normal University)
• Weiqing Min (Institute of Computing Technology, Chinese Academy of Sciences)
• Jiacheng Li (Shandong Normal University)
• Jing Wang (Shandong Normal University)
• Yuanjie Zheng (Shandong Normal University)
• Shuqiang Jiang (ICT, China Academy of Science)

• CHAN: Cross-Modal Hybrid Attention Network for Temporal Language Grounding in Videos 

• Wen Wang (Zhejiang Lab)
• Ling Zhong (Zhejiang Lab)
• Guang Gao (Zhejiang Lab)
• Minhong Wan (Zhejiang Lab)
• Jason Gu (Dalhousie University)

Session Chair Signature                                         Date/Time:

O26 - Multimodal (Oral)

Session Chair: Prof. Patrick Le Callet, University of Nantes, France

Wed, Jul 12, 13:30 – 15:00

Room: M9

• DMRL-Net: Differentiable Multi-View Representation Learning Network 

• Zihan Fang (Fuzhou University)
• Shide Du (Fuzhou University)
• Yaqing Chen (Fuzhou University)
• Shiping Wang (Fuzhou University)

• Conditional Video-Text Reconstruction Network with Cauchy Mask for Weakly Supervised Temporal Sentence Grounding 

• Jueqi Wei (Fudan University)
• Yuanwu Xu (Fudan University)
• Mohan Chen (Fudan University)
• Yuejie Zhang (Fudan University)
• Rui Feng (Fudan University)
• Shang Gao (Deakin University)

• FlowText: Synthesizing Realistic Scene Text Video with Optical Flow Estimation 

• Yuzhong Zhao (University of Chinese Academy of Sciences)
• Weijia Wu (Zhejiang Unversity)
• Weiqiang Wang (University of Chinese Academy of Sciences)
• Zhuang Li (Kuaishou)
• Jiahong Li (Kuaishou)

• Atomic-action-based Contrastive Network For Weakly Supervised Temporal Language Grounding 

• Hongzhou Wu (National University of Defense Technology)
• Xiang Zhang (National University of Defense Technology)
• Yifan Lv (Science and Technology on Integrated Information System Laboratory, Institute of Software Chinese Academy of Sciences)
• Xingyu Shen (National University of Defense Technology)
• Xuechen Zhao (National University of Defense Technology)
• Mengzhu Wang (NUDT)
• Zhigang Luo (National University of Defense Technology)

• MANDARI: MULTI-MODAL TEMPORAL KNOWLEDGE GRAPH-AWARE SUB-GRAPH EMBEDDING FOR NEXT-POI RECOMMENDATION 

• Xiaoqian Liu (Beijing University of Posts and Telecommunications)
• Yuan Cao (Beijing University of Posts and Telecommunications)
• Fan Zhang (Beijing University of Posts and Telecommunications)
• Xiongnan Jin (Zhejiang Lab)
• Jinpeng Chen (Beijing University of Posts and Telecommunications)

• MOVIE BOX OFFICE PREDICTION WITH SELF-SUPERVISED AND VISUALLY GROUNDED PRETRAINING 

• Qin Chao (Nanyang Technological University)
• Eunsoo Kim (Nanyang Technological University)
• Boyang Li (Nanyang Technological University)

Session Chair Signature                                         Date/Time:

P9 - Data & Labelling for Machine Learning II (Poster)

Session Chair: Dr. Hyomin Choi, InterDigital

Wed, Jul 12, 13:30 – 15:00

Room: Plaza Foyer

• Need a dog for seeing eye? A Walk Viewpoint Dataset for Freespace Detection in Unstructured Environments 

• Wenbin Zou (Shenzhen University)
• guoguang hua (shenzhen university)
• Shishun Tian (Shenzhen University)

• INCLR: INTENSIFYING THE CONSISTENCY OF PSEUDO LABEL REFINEMENT FOR UNSUPERVISED DOMAIN ADAPTATION PERSON RE-IDENTIFICATION 

• linfan zha (anhui university)
• Yanming Chen (Anhui University)
• Peng Zhou (Anhui University)
• Yiwen Zhang (Anhui University)

• NOISY-TO-CLEAN LABEL LEARNING FOR MEDICAL IMAGE SEGMENTATION 

• Zihao Bu (Jiangsu University)
• chengjian qiu (Jiangsu university)
• Kai Han (Jiangsu university)
• Zhe Liu (Jiangsu University)

• Learning Discrimination from Contaminated Data: Multi-Instance Learning for Unsupervised Anomaly Detection 

• Wenhao Hu (Zhejiang University)
• Yingying Liu (Zhejiang University)
• Jiazhen Xu (Zhejiang University)
• Xuanyu Chen (Zhejiang University)
• Gaoang Wang (Zhejiang University)

• Rethinking Video Error Concealment: A Benchmark Dataset 

• Bin Zheng (Shenzhen University)
• Miaohui Wang (Shenzhen University)

• Visual Place Recognition Datasets for Indoor Spaces 

• Zemian Guo (ShenZhen University)
• Yingying Zhu (Shenzhen University)

• AutoKary2022: A Large-Scale Densely Annotated Dateset for Chromosome Instance Segmentation 

• chen qiuzhu (HCU)
• Minghui Wu (Zhejiang University City College)
• Suncheng Xiang (Shanghai Jiao Tong University)
• Jun Wang (Zhejiang University)

Session Chair Signature                                         Date/Time:

P10 - Visual Information Processing II (Poster)

Session Chair: Dr. Honglei Zhang, Nokia Technologies

Wed, Jul 12, 13:30 – 15:00

Room: Plaza Foyer

• DESIGNING OPTICS AND ALGORITHM FOR ULTRA-THIN, HIGH-SPEED LENSLESS CAMERAS 

• Salman Siddique Khan (IIT Madras)
• Vivek Boominathan (Rice University)
• Ashok Veeraraghavan (Rice University)
• Kaushik Mitra (IIT Madras)

• DUAL-DOMAIN FEATURE LEARNING AND MEMORY-ENHANCED UNFOLDING NETWORK FOR SPECTRAL COMPRESSIVE IMAGING 

• Yangke Ying (Beijing University of Technology)
• Jin Wang (Beijing University of Technology)
• Yunhui Shi (Beijing University of Technology)
• Baocai Yin (Beijing University of Technology)

• Image Compressed Sensing Using Multi-Scale Characteristic Residual Learning 

• xinxin xiang (Qilu University of Technology)
• Fenghua Tong (Qilu University of Technology)
• Dawei Zhao (Shandong Academy of Sciences)

• LKD-Net: Large Kernel Convolution Network for Single Image Dehazing 

• Pinjun Luo (Southwest University)
• Guoqiang Xiao (College of Computer and Information Science, Southwest University, Chongqing, China)
• Xinbo Gao (Chongqing University of Posts and Telecommunications)
• Song Wu (Southwest University)

• Video noise removal using progressive decomposition with conditional invertibility 

• Huang Haoran (South China University of Technology)
• Yuhui Quan (South China University of Technology)
• Yan Huang (South China University of Technology)
• Jinlong Hu ( South China University of Technology)
• Zhenghua Lei (South China University of Technology)

• DOCMAE: DOCUMENT IMAGE RECTIFICATION VIA SELF-SUPERVISED REPRESENTATION LEARNING 

• Yi Zhang (University of Queensland)
• Hao Feng (University of Science and Technology of China)
• Wengang Zhou (University of Science and Technology of China)
• Houqiang Li (University of Science and Technology of China)
• Cong Liu (iFLYTEK Research)
• Feng Wu (University of Science and Technology of China)

• Information-density Masking Strategy for Mask Image Modelling 

• He Zhu ( Brainnetome Center and NLPR; School of Future Technology, UCAS; University of Chinese Academy of Sciences; Institute of Automation, Chinese Academy of Sciences)
• yang chen ( Brainnetome Center, National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences;University of Chinese Academy of Sciences;)
• Guyue Hu (Nanyang Technological University)
• 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;)

• Histogram-guided Video Colorization Structure with Spatial-Temporal Connection 

• Zheyuan Liu (Zhejiang University of Technology)
• Pan Mu (Zhejiang University of Technology)
• Cong Bai (Zhejiang University of Technology)
• Hanning Xu (Zhejiang Univ1ersity of Technology)

• Mask-Guided Stamp Erasure for Real Document Image 

• Xinye Yang (Institute of Information Engineering, Chinese Academy of Sciences; School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China)
• Dongbao Yang (Institute of Information Engineering, Chinese Academy of Sciences; School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China)
• Yu Zhou (Institute of Information Engineering, CAS; Also with University of Chinese Academy of Sciences)
• Youhui Guo (Institute of Information Engineering, Chinese Academy of Sciences)
• Weiping Wang (Institute of Information Engineering, CAS, China)

• Attention-Aware Anime Line Drawing Colorization 

• Yu Cao (The Hong Kong Polytechnic University)
• Hao Tian (The Hong Kong Polytechnic University)
• Tracy Mok (The Hong Kong Polytechnic University)

• Edge-aware Neural Implicit Surface Reconstruction 

• Xinghui Li (Tsinghua University)
• Yikang Ding (Tsinghua University)
• Jia Guo (None)
• Xiansong Lai (Tsinghua University)
• Shihao Ren (Tsinghua University)
• Wensen Feng (the Shenzhen Graduate School, Tsinghua University, Shenzhen 518071, China)
• Long Zeng (Tsinghua University)

• Handwriting Curve Interpolation Using Gradient Graph Laplacian Regularizer 

• Yinhe Lin (Fuzhou University)
• Fei Chen (Fuzhou University)
• Hang Cheng (Fuzhou University)
• Meiqing Wang (Fuzhou University)

Session Chair Signature                                         Date/Time:

Coffee Break

SS6: Special Session: Optimized Media Delivery (Oral)

Session Chair: Dr. Shiqi Wang, City University of Hong Kong

Wed, Jul 12, 15:30 – 17:00

Room: Plaza Terrace

• COMPARISON OF HDR QUALITY METRICS IN PER-CLIP λ OPTIMISATION WITH AV1 

• Vibhoothi Vibhoothi (Trinity College Dublin)
• Francois Pitie (Trinity College Dublin)
• Angeliki Katsenou (Trinity College Dublin)
• Yeping Su (YouTube/Google)
• Balu Adsumilli (YouTube/Google)
• Anil Kokaram (Trinity College Dublin, Ireland)

• A real-time blind quality-of-experience assessment metric for HTTP adaptive streaming 

• Chunyi Li (Shanghai Jiao Tong University)
• Roger Zimmermann (NUS)

• Towards guidelines for subjective Haptic quality assessment: a case study on quality assessment of compressed haptic signals 

• Andreas Pastor (University of Nantes)
• Patrick Le Callet ("Universite de Nantes, France")

• Just Noticeable Difference-aware Per-Scene Bitrate-laddering for Adaptive Video Streaming 

• Vignesh V Menon (Alpen-Adria-Universitat Klagenfurt)
• jingwen zhu (Nantes university)
• Prajit Rajendran (CEA LIST)
• Hadi Amirpour (University of Klagenfurt)
• Patrick Le Callet ("Universite de Nantes, France")
• Christian Timmerer (Alpen-Adria-Universität Klagenfurt)

• Optimizing Video Streaming for Sustainability and Quality: The Role of Preset Selection in Per-Title Encoding  

• Hadi Amirpour (Alpen-Adria-Universität Klagenfurt)
• Vignesh V Menon (Alpen-Adria-Universitat Klagenfurt)
• Samira Afzal (Alpen-Adria-Universitat Klagenfurt)
• Radu Prodan (University of Klagenfurt)
• Christian Timmerer (Alpen-Adria-Universität Klagenfurt)

• Anableps: Adapting Bitrate for Real-Time Communication Using VBR-encoded Video 

• Zicheng Zhang (Nanjing University)
• Hao Chen (Nanjing University)
• Xun Cao (Nanjing University)
• Zhan Ma (Nanjing University)

Session Chair Signature                                         Date/Time:

O27 - Speech Processing (Oral)

Session Chair: Dr. Zhiyong Wu, Tsinghua University

Wed, Jul 12, 15:30 – 17:00

Room: P1

• Adversarial Speaker Disentanglement Using Unannotated External Data for Self-supervised Representation Based Voice Conversion 

• Xintao Zhao (Tsinghua University)
• Shuai Wang (Tencent)
• young chao (tencent)
• Zhiyong Wu (Tsinghua University)
• Helen Meng (The Chinese University of Hong Kong)

• A DISENTANGLED RECURRENT VARIATIONAL AUTOENCODER FOR SPEECH ENHANCEMENT 

• Hegen Yan (Ningbo University)
• Zhihua Lu (Ningbo University)

• SnakeGAN: A Universal Vocoder Leveraging DDSP Prior Knowledge and Periodic Inductive Bias 

• Sipan Li (Tsinghua University)
• Songxiang Liu (Tencent)
• Luwen Zhang (Tsinghua University)
• Xiang Li (Tsinghua University)
• Zhiyong Wu (Tsinghua University)
• Yanyao Bian (Tencent AI Lab)
• Chao Weng (Tencent AI Lab)
• Helen Meng (The Chinese University of Hong Kong)

• CRA-DiffuSE: Improved cross-domain speech enhancement based on diffusion model with T-F domain pre-denoising 

• Zhibin Qiu (Xinjiang University)
• Yachao Guo (Xinjiang University)
• Mengfan Fu (XinJiang University)
• Hao Huang (Xinjiang University)
• Ying Hu (Xinjiang University)
• Liang HE (Tsinghua University)
• Fuchun Sun (Tsinghua University)

• A JOINT NETWORK BASED ON INTERACTIVE ATTENTION FOR SPEECH EMOTION RECOGNITION 

• Ying Hu (Xinjiang University)
• shijing hou (Xinjiang university)
• Liang HE (Tsinghua University)

• SPEECH TOPIC CLASSIFICATION BASED ON PRE-TRAINED AND GRAPH NETWORKS 

• fangjing niu (Xinjiang University )
• Tengfei Cao (Xinjiang University)
• Ying Hu (Xinjiang University)
• Liang HE (Tsinghua University)

Session Chair Signature                                         Date/Time:

O28 - Face Computing (Oral)

Session Chair: Prof. Brian C. Lovell, University of Queensland

Wed, Jul 12, 15:30 – 17:00

Room: P2

• Unsupervised 3D Face Reconstruction with Reprogramming Skip Connections 

• Cheukming Dung (Sun Yat-sen University)
• Huajun Zhou (Sun Yat-sen University)
• Jian-Huang Lai (Sun Yat-sen University)

• EvenFace: Deep Face Recognition with Uniform Distribution of Identities 

• Pengfei Hu (Tsinghua University)
• Yingfan Tao (Tsinghua University)
• Qiqi Bao (Tsinghua university)
• Guijin Wang (Tsinghua University)
• Wenming Yang (Tsinghua University)

• LARGE POSE FRIENDLY FACE REENACTMENT USING SUBTLE MOTIONS 

• Xiaomeng Fu (1. Institute of Information Engineering, Chinese Academy of Sciences. 2. School of Cyber Security, University of Chinese Academy of Sciences)
• Xi Wang (Institute of Information Engineering, 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)
• Jiao Dai (Institute of Information Engineering,Chinese Academy of Sciences)
• Jizhong Han (Institute of Information Engineering,Chinese Academy of Sciences)

• MSAbox: A spatially stable face detector 

• Wei Xu (Beijing University of Posts and Telecommunications)
• kangkang wang (Baidu)
• Ziliang Chen (Baidu Inc.)
• Bin He (baidu)
• Bi Li (Baidu Inc.)
• Haocheng Feng (Baidu Inc.)
• gang zhang (Baidu Inc.)
• jingtuo liu (baidu)
• Junyu Han (Baidu Inc.)
• Errui Ding (Baidu Inc.)

• DR-Net: Multi-View Face Synthesis by Dual Representation 

• Xianliang Huang (Fudan University)
• YINING LANG (Alibaba)
• Ying Guo (Meituan)
• Yuan He (Alibaba Group )
• hui xue (Alibaba)
• Li Zhao (Hangzhou Yugu Technology)
• Shuigeng Zhou (Fudan University)

• MA-NeRF: Motion-Assisted Neural Radiance Fields for Face Synthesis from Sparse Images 

• Weichen Zhang (tsinghua university)
• Xiang Zhou (Tsinghua Univeristy)
• Yukang CAO (the University of Hong Kong)
• Wensen Feng (the Shenzhen Graduate School, Tsinghua University, Shenzhen 518071, China)
• Chun Yuan (Graduate School at ShenZhen,Tsinghua University)

Session Chair Signature                                         Date/Time:

O29 - Robustness (Oral)

Session Chair: Dr. Shuoyao Wang, Shenzhen University

Wed, Jul 12, 15:30 – 17:00

Room: P3

• Enhancing Robustness of Deep Networks Against Noisy Labels Based on A Two-Phase Formulation of Their Learning Behavior 

• Yaoru Luo (National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences)
• Ge Yang (National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences)

• Robust and Efficient Memory Network for Video Object Segmentation 

• Yadang Chen (NUIST)
• Dingwei Zhang (NUIST)
• Zhi-Xin Yang (University of Macau)
• Enhua Wu (CAS)

• Weight-based Regularization for Improving Robustness in Image Classification 

• Hao Yang (National University of Defense Technology)
• Min Wang (National University of Defense Technology )
• Zhengfei Yu (National University of Defense Technology)
• Yun Zhou (National University of Defense Technology)

• Robust Structured Sparse Subspace Clustering with Neighborhood Preserving Projection 

• Wenyi Feng (east China university of science and technology)
• Wei Guo (East China University of Science and Technology)
• Ting Xiao (East China University of Science and Technology)
• Zhe Wang ( East China University of Science and Technology )

• Improving robustness of learning-based adaptive video streaming in wildly fluctuating networks 

• Jiawei Lin (Shenzhen University)
• Shuoyao Wang (Shenzhen University)

• Robust Person Re-Identification with Wireless Signals 

• Dong Xi (University of Science and Technology of China)
• Wengang Zhou (University of Science and Technology of China)
• Houqiang Li (University of Science and Technology of China)

Session Chair Signature                                         Date/Time:

O30 - Data & Labelling for Machine Learning I (Oral)

Session Chair: Dr. Jie Zhang, University Of Bath

Wed, Jul 12, 15:30 – 17:00

Room: P4

• GradSalMix: Gradient Saliency-based Mix for Image Data Augmentation 

• Tao Hong (Peking University)
• Ya Wang (Tencent Inc.)
• xingwu sun (Tencent Inc.)
• Fengzong Lian (Tencent)
• zhanhui kang (tencent)
• Jinwen Ma (Peking University)

• Get a Head Start: Targeted Labeling at Source with Limited Annotation Overhead for Semi-Supervised Learning 

• Hui Zhu (Institute of Computing Technology, Chinese Academy of Sciences)
• Yongchun Lu (Mashang Consumer Finance Co., Ltd.)
• Qin Ma (China Agricultural University)
• Xunyi Zhou (Mashang Consumer Finance Co., Ltd.)
• Fen Xia (Mashing Consumer Finance Co., Ltd.)
• Guoqing Zhao (Mashang Consumer Finance Co., Ltd)
• Ning Jiang (Mashang Consumer Finance Co., Ltd.)
• Xiaofang Zhao (Institute of Computing Technology, Chinese Academy of Sciences; Institute of Intelligent Computing Technology, Suzhou, CAS)

• Partial multi-label learning: exploration of binary ground-truth labels 

• Yan Hu (Guangdong University of Technology)
• Xiaozhao Fang
• peipei kang (Guangdong University of Technology)

• Customizing Synthetic Data for Data-Free Student Learning 

• Shiya Luo (Zhejiang University)
• Defang Chen (Zhejiang University)
• Can Wang (Zhejiang University)

• A Geometrical Characterization on Feature Density of Image Datasets 

• Zhen Liang (National University of Defense Technology)
• Changyuan Zhao (State Key Laboratory of Computer Science Institute of Software, Chinese Academy of Sciences)
• Wanwei Liu (National University of Defense Technology)
• Bai Xue (Institute of Software CAS)
• Wenjing Yang (National University of Defense Technology)

• Federated Domain Adaptation via Pseudo-label Refinement 

• Gang Li (Zhejiang University)
• Qifei Zhang (Zhejiang University)
• peizheng wang (Zhejiang University)
• Jie Zhang (Zhejiang University)
• Chao Wu (Zhejiang University)

Session Chair Signature                                         Date/Time:

O31 - Learning Techniques I (Oral)

Session Chair: Dr. Reji Mathew, The University of New South Wales, Australia

Wed, Jul 12, 15:30 – 17:00

Room: P5

• Learning continuous piecewise non-linear activation functions for deep neural networks 

• Xinchen Gao (University of Electronic Science and Technology of China)
• Yawei Li (ETH Zurich)
• Wen Li (University of Electronic Science and Technology of China)
• Lixin Duan (University of Electronic Science and Technology of China)
• Luc Van Gool (ETH Zurich)
• Luca Benini (ETHZ, University of Bologna )
• Michele Magno (ETH Zurich)

• Discriminative Spatiotemporal Alignment for Self-Supervised Video Correspondence Learning 

• Qiaoqiao Wei (Tsinghua University)
• Hui Zhang (Tsinghua University)
• Jun-Hai Yong (Tsinghua University)

• Unsupervised Fashion Style Learning by Solving Fashion Jigsaw Puzzles 

• Jia Chen (Wuhan Textile University)
• Haidongqing Yuan (Wuhan Textile University)
• Fei Fang (Wuhan Textile University)
• Tao Peng (Wuhan Textile University)
• xinrong Hu (Wuhan Textile University)

• Anchor-Free Action Proposal Network with Uncertainty Estimation 

• Selen Pehlivan (Aalto University)
• Jorma Laaksonen (Aalto University)

• SCALE-AWARE TASK MESSAGE TRANSFERRING FOR MULTI-TASK LEARNING 

• Shalayiding Sirejiding (Shanghai Jiao Tong University)
• Yue Ding (Shanghai Jiao Tong University)
• Yuxiang Lu (Shanghai Jiao Tong University)
• Hongtao Lu (Shanghai Jiaotong University)

• Improving the Homophily of Heterophilic Graphs for Semi-Supervised Node Classification 

• Yuhu Wang (Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences)
• SHIMING XIANG (Chinese Academy of Sciences, China)
• Chunhong Pan (Institute of Automation, Chinese Academy of Sciences)

Session Chair Signature                                         Date/Time:

P11 - Transformer III (Poster)

Session Chair: Dr. Kun Hu, University of Sydney

Wed, Jul 12, 15:30 – 17:00

Room: Plaza Foyer

• SiTPose: A Siamese Convolutional Transformer for Relative Camera Pose Estimation 

• Kai Leng (Harbin Institute of Technology(ShenZhen))
• Cong Yang (Soochow University)
• Wei Sui (Horizon Robotics)
• Jie Liu (Harbin Institute of Technology)
• Zhijun Li (Harbin Institute of Technology)

• TextFormer: Component-aware Text Segmentation with Transformer 

• Xiaocong Wang (Fudan University)
• Haiyang Yu (Fudan University)
• Bin Li (Fudan University)
• Xiangyang Xue (Fudan University)

• SCFORMER: INTEGRATING HYBRID FEATURES IN VISION TRANSFORMERS 

• Hui Lu (Utrecht University)
• Ronald Poppe (Utrecht University)
• Albert Ali Salah (Utrecht University)

• IMAGE DERAINING TRANSFORMER WITH SPARSITY AND FREQUENCY GUIDANCE 

• Tianyu Song (Dalian Polytechnic University)
• Pengpeng Li (Dalian Polytechnic University)
• Guiyue Jin (Dalian Polytechnic University)
• Jiyu Jin (Dalian Polytechnic University)
• Shumin Fan (Dalian Polytechnic University)
• Xiang Chen (Nanjing University of Science and Technology)

• ShiftFormer: Spatial-Temporal Shift Operation in Video Transformer 

• Beiying Yang (Institute of Automation, Chinese Academy of Sciences)
• Guibo Zhu (Institute of Automation, Chinese Academy of Sciences )
• Guojing Ge (NLPR, Institute of Automation, CAS)
• Jinqiao Wang (Institute of Automation, Chinese Academy of Sciences)
• Jinzhao Luo (ucas)

• ABMNet: Coupling Transformer with CNN based on Adams-Bashforth-Moulton Method for Infrared small target detection 

• Tianxiang Chen (University of Science and Technology of China)
• Zhentao Tan (Alibaba DAMO Academy)
• Qi Chu (University of Science and Technology of China)
• Bin Liu (University of Science and Technology of China)
• Nenghai Yu (University of Science and Technology of China)

• ART: an Efficient Transformer with Atrous Residual Learning for Medical Images 

• Yufan Wang (Northeastern University)
• Linlong He (Northeastern University)
• He Ma (Northeastern University)

• MedFCT: A Frequency Domain Joint CNN-Transformer Network for Semi-supervised Medical Image Segmentation 

• Shiao Xie (Zhejiang University)
• Huimin Huang (Zhejiang University)
• Ziwei Niu (Zhejiang University)
• Yen-Wei Chen (Ritsumeikan University)
• Lanfen Lin (Zhejiang University)

• Cross-cycle Transformer-based stitching method for low-resolution borehole images 

• Jia Chen (Wuhan Textile University)
• ZhenPeng Fu (WuHan textile university)
• Fei Fang (Wuhan Textile University)
• xinrong Hu (Wuhan Textile University)
• Tao Peng (Wuhan Textile University)

• Improving Vision Transformers with Nested Multi-head Attentions 

• Jiquan Peng (Yanshan University)
• Chaozhuo Li (Microsoft Research Asia)
• Yuting Lin (Yanshan University)
• xiaohan fang (Yanshan University)

Session Chair Signature                                         Date/Time:

P12 - Knowledge Distillation II (Poster)

Session Chair: Dr. Aous Naman, The University of New South Wales, Australia

Wed, Jul 12, 15:30 – 17:00

Room: Plaza Foyer

• KnowledgeIE: Unifying Online-Offline Distillation based on Knowledge Inheritance and Evolution 

• Yiqing Shen ( Johns Hopkins University)

• Collaborative Spatial-Temporal Distillation for Efficient Video Deraining 

• Yuzhang Hu (Peking University)
• Minghao Liu (Peking University)
• Wenhan Yang (City University of Hong Kong)
• Jiaying Liu (Peking University)
• Zongming Guo (Peking University)

• Adaptive Multi-Teacher Knowledge Distillation with Meta-Learning 

• Hailin Zhang (Zhejiang University)
• Defang Chen (Zhejiang University)
• Can Wang (Zhejiang University)

• Towards General and Fast Video Derain via Knowledge Distillation 

• cai defang (Zhejiang University of Technology)
• Pan Mu (Zhejiang University of Technology)
• Sixian Chan (Zhejiang University of Technology)
• Zhanpeng Shao (Hunan Normal University)
• Cong Bai (Zhejiang University of Technology)

P13 - Media Retrieval II (Poster)

Session Chair: Dr. Xinzheng Niu, University of Electronic Science and Technology

Wed, Jul 12, 15:30 – 17:00

Room: Plaza Foyer

• DEEP METRIC MULTI-VIEW HASHING FOR MULTIMEDIA RETRIEVAL 

• Jian Zhu (Zhejiang Lab)
• Zhangmin Huang (Zhejiang Lab)
• Yu Cui (zhejianglab)
• Lingfang Zeng (Zhejiang Lab)

• MIM: LIGHTWEIGHT MULTI-MODAL INTERACTION MODEL FOR JOINT VIDEO MOMENT RETRIEVAL AND HIGHLIGHT DETECTION 

• Jinyu Li (Sun Yat-sen University)
• Fuwei Zhang (Sun Yat-sen University)
• Shujin Lin (Sun Yat-sen University)
• Fan Zhou (Sun Yat-sen university)
• Ruomei Wang (Sun Yat-sen University)

• Image-text Retrieval via Preserving Main Semantics of Vision 

• Xu Zhang (University of Electronic Science and Technology of China)
• Xinzheng Niu (University of Electronic Science and Technology )
• Philippe Fournier-Viger (Shenzhen University)

• Progressive Event Alignment Network for Partial Relevant Video Retrieval 

• Xun Jiang (UESTC)
• Zhiguo Chen (UESTC)
• Xing Xu (University of Electronic Science and Technology of China)
• Fumin Shen (UESTC)
• Zuo Cao (MEITUAN)
• Xunliang Cai (MEITUAN.COM)

Session Chair Signature                                         Date/Time:

D2 - Demonstrations

Session Chair: Dr Reji Mathew, University of New South Wales

Time: Wed 12 July, 13:30 to 15:00 pm /15:30 to 17:00

Room: Booth Area

• SMARTSCORE: FROM OMR TO AUTO PAGE TURNING 

• Wei Xu (Huazhong University of Science and Technology)

• FaceClone: Interactive Facial Shape and Motion Cloning System using Multi-View images 

• Kyungjune Lee ( Yonsei University)
• Jeonghaeng Lee (Yonsei University)
• Hyucksang Lee (Yonsei University)
• Mingyu Jang (Yonsei)
• Seongmin Lee (Yonsei University)
• Sanghoon Lee (Yonsei University, Korea)

• DiffAds: An Interactive Platform for Personalized Visual Advertisement Generation 

• Ling Lo (National Yang Ming Chiao Tung University)
• Hong-Han Shuai (National Yang Ming Chiao Tung University)
• Wen-Huang Cheng (National Taiwan University)

Session Chair Signature                                         Date/Time: