Dynamic Spatio-Temporal Modular Network for Video Question Answering.
Zi QianXin WangXuguang DuanHong ChenWenwu ZhuPublished in: ACM Multimedia (2022)
Keyphrases
- question answering
- spatio temporal
- dynamic textures
- information retrieval
- natural language processing
- question classification
- named entities
- information extraction
- human actions
- cross language
- qa clef
- passage retrieval
- video sequences
- natural language
- natural language questions
- question answering systems
- candidate answers
- syntactic information
- sentence retrieval
- answer validation
- relation extraction
- image sequences
- video search
- qa systems
- visual data
- video content
- video data
- machine learning