Long-Term Video Question Answering via Multimodal Hierarchical Memory Attentive Networks.
Ting YuJun YuZhou YuQingming HuangQi TianPublished in: IEEE Trans. Circuits Syst. Video Technol. (2021)
Keyphrases
- question answering
- information retrieval
- multimedia
- information extraction
- named entities
- video sequences
- passage retrieval
- natural language processing
- video data
- cross language
- question classification
- question answering systems
- natural language
- video content
- sentence retrieval
- multi modal
- video frames
- relation extraction
- qa clef
- open domain question answering
- answer validation
- qa systems
- syntactic information
- semantic roles
- video retrieval
- audio visual
- natural language questions
- artificial intelligence
- data mining