IVMSP-42.6
MODELING HUMAN MEMORY IN MULTI-OBJECT TRACKING WITH TRANSFORMERS
Yizhuo Li, Cewu Lu, Shanghai Jiao Tong University, China
Session:
Video Communication
Track:
Image, Video, and Multidimensional Signal Processing
Location:
Gather Area I
Presentation Time:
Fri, 13 May, 22:00 - 22:45 China Time (UTC +8)
Fri, 13 May, 14:00 - 14:45 UTC
Fri, 13 May, 14:00 - 14:45 UTC
Session Chair:
Paul Chan, Institute for Infocomm Research, A*STAR
Session IVMSP-42
IVMSP-42.1: DILATED CONVOLUTIONAL NEURAL NETWORK-BASED DEEP REFERENCE PICTURE GENERATION FOR VIDEO COMPRESSION
Haoyue Tian, Pan Gao, Nanjing University of Aeronautics and Astronautics, China; Ran Wei, Science and Technology on Electro-optic Control Laboratory, China; Manoranjan Paul, Charles Sturt University, Australia
IVMSP-42.2: RATE CONTROL FOR LEARNED VIDEO COMPRESSION
Yanghao Li, Xinyao Chen, Jisheng Li, Jiangtao Wen, Tsinghua University, China; Yuxing Han, Research Institute of Tsinghua University in Shenzhen, China; Shan Liu, Xiaozhong Xu, Tencent Media Lab, China
IVMSP-42.3: GLOBAL OPTIMIZATION SOLUTION FOR DYNAMIC ADAPTIVE 360-DEGREE STREAMING
Xuekai Wei, Weijia Jia, Beijing Normal University, China; Mingliang Zhou, Chongqing University, China
IVMSP-42.4: COLLABORATIVE OBJECT DETECTORS ADAPTIVE TO BANDWIDTH AND COMPUTATION
Juliano S. Assine, José C. S. Santos Filho, Eduardo Valle, Unicamp, Brazil
IVMSP-42.5: MA-NET: MULTI-SCALE ATTENTION-AWARE NETWORK FOR OPTICAL FLOW ESTIMATION
Mu Li, Baojiang Zhong, Soochow University, China; Kai-Kuang Ma, Nanyang Technological University, Singapore
IVMSP-42.6: MODELING HUMAN MEMORY IN MULTI-OBJECT TRACKING WITH TRANSFORMERS
Yizhuo Li, Cewu Lu, Shanghai Jiao Tong University, China