Multi-Turn Video Question Answering via Hierarchical Attention Context Reinforced Networks.
Zhou ZhaoZhu ZhangXinghua JiangDeng CaiPublished in: IEEE Trans. Image Process. (2019)
Keyphrases
- question answering
- question classification
- information extraction
- natural language processing
- information retrieval
- passage retrieval
- cross language
- multimedia
- natural language questions
- qa clef
- video data
- contextual information
- named entities
- relation extraction
- open domain question answering
- question answering systems
- context aware
- answering questions
- artificial intelligence
- video content
- video frames
- syntactic information
- natural language
- data mining
- semantic relations
- visual features
- candidate answers
- multi modal