TP1.L303: Image and Video Representation I
Tue, 10 Oct, 14:30 - 16:00 Malaysia Time (UTC +8)
Location: Room 303
Session Type: Lecture
Session Chair: Marek Domanski, Poznań University of Technology
Track: Image and Video Analysis, Synthesis, and Retrieval
Click the to view the manuscript on IEEE Xplore Open Preview
Tue, 10 Oct, 14:30 - 14:48 Malaysia Time (UTC +8)
 

TP1.L303.1: VIDEO SUMMARIZATION THROUGH FINE-GRAINED HIERARCHICAL MODELING WITH MULTI-DIMENSIONAL FEATURES

Mengnan Liang, Ju Liu, Xiaoxi Liu, Shandong University, China; Lingchen Gu, Shandong Normal University, China
Tue, 10 Oct, 14:48 - 15:06 Malaysia Time (UTC +8)
 

TP1.L303.2: IMPROVE UNSUPERVISED DEEP HASHING VIA MASKED CONTRASTIVE LEARNING

Chuang Zhao, Hefei Ling, Shijie Lu, Yuxuan Shi, Ping Li, Qiang Cao, Huazhong University of Science and Technology, China
Tue, 10 Oct, 15:06 - 15:24 Malaysia Time (UTC +8)
 

TP1.L303.3: GRAPHRPE: RELATIVE POSITION ENCODING GRAPH TRANSFORMER FOR 3D HUMAN POSE ESTIMATION

Junjie Zou, Southeast University, China; Ming Shao, University of Massachusetts Dartmout, United States of America; Siyu Xia, Southeast University, China
Tue, 10 Oct, 15:24 - 15:42 Malaysia Time (UTC +8)
 

TP1.L303.4: COMPACT SELECTIVE TRANSFORMER BASED ON INFORMATION ENTROPY FOR FACIAL EXPRESSION RECOGNITION IN THE WILD

Liyuan Guo, Lianghai Jin, Guangzhi Ma, Xiangyang Xu, Huazhong University of Science and Technology, China
Tue, 10 Oct, 15:42 - 16:00 Malaysia Time (UTC +8)
 

TP1.L303.5: USGG: UNION MESSAGE BASED SCENE GRAPH GENERATION

Shiqi Sun, Tsinghua University, China; Danlan Huang, Beijing University of Posts and Telecommunications, China; Zhijin Qin, Xiaoming Tao, Tsinghua University, China; Chengkang Pan, Guangyi Liu, China Mobile Research Institute, China