Constructing holistic spatio-temporal scene graph for video semantic role labeling

• Main Authors: ZHAO, Yu, FEI, Hao, CAO, Yixin, LI, Bobo, ZHANG, Meishan, WEI, Jianguo, ZHANG, Min, CHUA, Tat-Seng
• 格式: text
• 語言: English
• 出版: Institutional Knowledge at Singapore Management University 2023
• 主題: video understanding; semantics role labeling; event extraction; scene graph; Graphics and Human Computer Interfaces; Numerical Analysis and Scientific Computing
• 在線閱讀: https://ink.library.smu.edu.sg/sis_research/8290; https://ink.library.smu.edu.sg/context/sis_research/article/9293/viewcontent/2308.05081.pdf
• 機構: Singapore Management University

As one of the core video semantic understanding tasks, Video Semantic Role Labeling (VidSRL) aims to detect the salient events from given videos, by recognizing the predict-argument event structures and the interrelationships between events. While recent endeavors have put forth methods for VidSRL,...