Video graph transformer for video question answering

• Main Authors: XIAO, Junbin, ZHOU, Pan, CHUA, Tat-Seng, YAN, Shuicheng
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2022
• Subjects: Dynamic visual graph; Transformer; VideoQA; Graphics and Human Computer Interfaces
• Online Access: https://ink.library.smu.edu.sg/sis_research/8994; https://ink.library.smu.edu.sg/context/sis_research/article/9997/viewcontent/2022_ECCV_VQA.pdf
• Institution: Singapore Management University

This paper proposes a Video Graph Transformer (VGT) model for Video Quetion Answering (VideoQA). VGT’s uniqueness are two-fold: 1) it designs a dynamic graph transformer module which encodes video by explicitly capturing the visual objects, their relations, and dynamics for complex spatio-temporal r...