Divide and Conquer: Question-Guided Spatio-Temporal Contextual Attention for Video Question Answering.
Jianwen JiangZiqiang ChenHaojie LinXibin ZhaoYue GaoPublished in: AAAI (2020)
Keyphrases
- question answering
- spatio temporal
- question classification
- question answering systems
- qa clef
- natural language questions
- answer extraction
- qa systems
- answer validation
- candidate answers
- human actions
- open domain question answering
- answering questions
- information extraction
- natural language processing
- information retrieval
- video data
- multimedia
- video sequences
- natural language
- cross language
- video content
- video frames
- video retrieval
- question answer pairs
- named entities
- action recognition
- image sequences
- contextual information
- correct answers
- syntactic information
- key frames
- semantic roles
- sentence retrieval
- cross lingual
- search computing
- feature weighting
- search engine
- speech transcripts
- textual entailment recognition
- machine learning