Video Question Answering via Hierarchical Spatio-Temporal Attention Networks.
Zhou ZhaoQifan YangDeng CaiXiaofei HeYueting ZhuangPublished in: IJCAI (2017)
Keyphrases
- question answering
- spatio temporal
- information retrieval
- human actions
- information extraction
- video sequences
- natural language processing
- video data
- multimedia
- named entities
- qa clef
- question classification
- cross language
- question answering systems
- natural language questions
- relation extraction
- natural language
- sentence retrieval
- passage retrieval
- video frames
- video database
- syntactic information
- candidate answers
- video content
- video retrieval
- answer validation
- open domain question answering
- machine learning
- semantic roles
- word sense disambiguation
- image sequences