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