Discovering Spatio-Temporal Rationales for Video Question Answering.
Yicong LiJunbin XiaoChun FengXiang WangTat-Seng ChuaPublished in: ICCV (2023)
Keyphrases
- question answering
- spatio temporal
- human actions
- information retrieval
- question classification
- natural language processing
- multimedia
- natural language questions
- natural language
- information extraction
- video content
- cross language
- video sequences
- named entities
- qa clef
- syntactic information
- question answering systems
- passage retrieval
- video data
- open domain question answering
- image sequences
- video frames
- semantic roles
- relation extraction
- video search
- video database
- answer extraction
- textual entailment recognition
- action recognition