FP-V1.V4: Machine Learning for Image & Video Analysis
Fri, 7 Oct, 21:00 - 22:00 China Standard Time (UTC +8)
Fri, 7 Oct, 15:00 - 16:00 Central European Time (UTC +2)
Fri, 7 Oct, 13:00 - 14:00 UTC
Fri, 7 Oct, 09:00 - 10:00 Eastern Time (UTC -4)
Virtual Poster
Location: Gather.Town 4
Session Co-Chairs: Jean-Christophe Pesquet, CentraleSupélec and Andrea Cavallaro, Queen Mary University of London and Rebecca Willett, University of Chicago
Track: Applications of Machine Learning

FP-V1.V4.1: WEIGHTED SUPERVISED CONTRASTIVE LEARNING AND DOMAIN MIXTURE FOR GENERALIZED PERSON RE-IDENTIFICATION
Kaixiang Chen, Tiantian Gong, Liyan Zhang, Nanjing University of Aeronautics and Astronautics, China

FP-V1.V4.2: CyEDA: CYCLE-OBJECT EDGE CONSISTENCY DOMAIN ADAPTATION
Jing Chong Beh, Jie Long Kew, Chee Seng Chan, Universiti Malaya, Malaysia; Kam Woh Ng, University of Surrey, United Kingdom of Great Britain and Northern Ireland; Che-Tsung Lin, Christopher Zach, Chalmers University of Technology, Sweden; Shang-Hong Lai, National Tsing Hua University / Microsoft AI R&D Center, Taiwan

FP-V1.V4.3: GUIDED SAMPLING BASED FEATURE AGGREGATION FOR VIDEO OBJECT DETECTION
Jun Liang, Haosheng Chen, Yan Yan, Yang Lu, Hanzi Wang, Xiamen University, China

FP-V1.V4.4: A NOVEL CONTRASTIVE LEARNING FRAMEWORK FOR SELF-SUPERVISED ANOMALY DETECTION
Jingze Li, Zhichao Lian, Min Li, Nanjing University of Science and Technology, China

FP-V1.V4.5: Clustering by Directly Disentangling Latent Space
Fei Ding, Yin Yang, Feng Luo, Clemson University, United States of America

FP-V1.V4.6: INDOOR TARGET-DRIVEN VISUAL NAVIGATION BASED ON SPATIAL SEMANTIC INFORMATION
Jiaojie Yan, Qieshi Zhang, Jun Cheng, Shenzhen Institutes of Advanced Technology，Chinese Academy of Sciences, China; Ziliang Ren, School of Science and Technology, Dongguan University of Technology, China; Tian Li, Guangdong University of Technology, China; Zhuo Yang, Guangdong Mechanical and Electrical Polytechnic, China

FP-V1.V4.7: CONTINUAL LEARNING IN VISION TRANSFORMER
Mana Takeda, Keiji Yanai, The University of Electro-Communications, Tokyo, Japan

FP-V1.V4.8: MAANU-NET: MULTI-LEVEL ATTENTION AND ATROUS PYRAMID NESTED U-NET FOR WRECKED OBJECTS SEGMENTATION IN FORWARD-LOOKING SONAR IMAGES
Yingshuo Liang, Xingyu Zhu, Jianlei Zhang, Nankai University, China

FP-V1.V4.9: Learning from Designers: Fashion Compatibility Analysis via Dataset Distillation
Yulan Chen, Zhiyong Wu, Zheyan Shen, Jia Jia, Tsinghua University, China

FP-V1.V4.10: DYNAMIC SELECTION NETWORK FOR RGB-D SALIENT OBJECT DETECTION
Jinlin Zhou, Zhiming Luo, Shaozi Li, Xiamen University, China

FP-V1.V4.11: A PERSON RE-IDENTIFICATION BASELINE BASED ON ATTENTION BLOCK NEURAL ARCHITECTURE SEARCH
Jia Sun, Yanfeng Li, Houjin Chen, Yahui Peng, Beijing Jiaotong University, China

FP-V1.V4.12: FAST VEHICLE DETECTION AND TRACKING ON FISHEYE TRAFFIC MONITORING VIDEO USING CNN AND BOUNDING BOX PROPAGATION
Sandy Ardianto, Hsueh-Ming Hang, Wen-Huang Cheng, National Yang Ming Chiao Tung University, Taiwan

FP-V1.V4.13: DYNAMIC TEMPLATE UPDATE FOR VISUAL OBJECT TRACKING
Kibum Yun, Kyujin Shim, Kangwook Ko, Changick Kim, Korea Advanced Institute of Science and Technology (KAIST), Korea, Republic of

FP-V1.V4.14: DETECTING A CHILD’S STIMMING BEHAVIOURS FOR AUTISM SPECTRUM DISORDER DIAGNOSIS USING RGBPOSE-SLOWFAST NETWORK
Jeba Berlin S, Deepak Pandian, DineshBabu Jayagopi, International Institute of Information Technology, India; Shyam Sundar Rajagopalan, St. John's National Academy of Health Sciences, India

FP-V1.V4.15: Multiclass-SGCN: Sparse Graph-based Trajectory Prediction with Agent Class Embedding
Ruochen Li, Stamos Katsigiannis, Hubert P. H. Shum, Durham University, United Kingdom of Great Britain and Northern Ireland