Invariant Grounding for Video Question Answering.
Yicong LiXiang WangJunbin XiaoWei JiTat-Seng ChuaPublished in: CoRR (2022)
Keyphrases
- question answering
- question classification
- video sequences
- natural language processing
- video data
- cross language
- information retrieval
- syntactic information
- passage retrieval
- video content
- open domain question answering
- video frames
- multimedia
- information extraction
- question answering systems
- sentence retrieval
- natural language
- relation extraction
- named entities
- semantic roles
- qa clef
- multi modal
- natural language questions
- artificial intelligence
- image retrieval
- video search
- information retrieval systems
- qa systems
- key frames
- answer validation
- question answer pairs
- textual entailment recognition