From FiLM to Video: Multi-turn Question Answering with Multi-modal Context.
Dat Tien NguyenShikhar SharmaHannes SchulzLayla El AsriPublished in: CoRR (2018)
Keyphrases
- multi modal
- question answering
- video search
- semantic concepts
- information retrieval
- named entities
- information extraction
- syntactic information
- natural language processing
- high dimensional
- qa clef
- video data
- passage retrieval
- question classification
- question answering systems
- answer validation
- multiple modalities
- natural language
- video frames
- natural language questions
- video analysis
- image annotation
- audio visual
- semantic roles
- context aware
- question answer pairs
- cross language
- contextual information
- video sequences
- multimedia
- video shots
- video retrieval
- machine learning