Action-centric relation transformer network for video question answering

• Main Authors: ZHANG, Jipeng, SHAO, Jie, CAO, Rui, GAO, Lianli, XU, Xing, SHEN, Heng Tao
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2022
• Subjects: Knowledge discovery; multi-modal reasoning; Proposals; relation reasoning; Task analysis; temporal action detection; Video question answering; video representation; Visualization; Cognition; Encoding; Feature extraction; Broadcast and Video Studies; Databases and Information Systems; Numerical Analysis and Scientific Computing
• Online Access: https://ink.library.smu.edu.sg/sis_research/6020; https://ink.library.smu.edu.sg/context/sis_research/article/7023/viewcontent/Action_Centric_Relation_Video_Question_Answering_av.pdf
• Institution: Singapore Management University

Video question answering (VideoQA) has emerged as a popular research topic in recent years. Enormous efforts have been devoted to developing more effective fusion strategies and better intra-modal feature preparation. To explore these issues further, we identify two key problems. (1) Current works t...