Cross-Attentional Spatio-Temporal Semantic Graph Networks for Video Question Answering.
Yun LiuXiaoming ZhangFeiran HuangBo ZhangZhoujun LiPublished in: IEEE Trans. Image Process. (2022)
Keyphrases
- question answering
- spatio temporal
- human actions
- information extraction
- named entities
- natural language processing
- video sequences
- multimedia
- natural language questions
- cross language
- information retrieval
- question classification
- video data
- qa clef
- syntactic information
- question answering systems
- video database
- open domain question answering
- relation extraction
- passage retrieval
- video retrieval
- video content
- video frames
- video search
- qa systems
- natural language
- answer validation
- image sequences
- ranked list
- sentence retrieval