TRRNet : tiered relation reasoning for compositional visual question answering

• Main Authors: Yang, Xiaofeng, Lin, Guosheng, Lv, Fengmao, Liu, Fayao
• Other Authors: School of Computer Science and Engineering
• Format: Conference or Workshop Item
• Language: English
• Published: 2020
• Subjects: Engineering::Computer science and engineering; Visual Question Answering; Visual Reasoning
• Online Access: https://hdl.handle.net/10356/144262
• Institution: Nanyang Technological University

Compositional visual question answering requires reasoning over both semantic and geometry object relations. We propose a novel tiered reasoning method that dynamically selects object level candidates based on language representations and generates robust pairwise relations within the selected candi...