Open-Ended Video Question Answering via Multi-Modal Conditional Adversarial Networks.
Zhou ZhaoShuwen XiaoZehan SongChujie LuJun XiaoYueting ZhuangPublished in: IEEE Trans. Image Process. (2020)
Keyphrases
- multi modal
- question answering
- open ended
- video search
- semantic concepts
- information retrieval
- multimedia
- audio visual
- multiple modalities
- natural language
- natural language questions
- natural language processing
- video data
- video content
- passage retrieval
- cross language
- video streams
- syntactic information
- question answering systems
- qa clef
- information extraction
- video sequences
- question classification
- learning outcomes
- video analysis
- video retrieval
- image annotation
- video frames
- answering questions
- high dimensional
- qa systems
- video shots
- answer extraction
- candidate answers
- video database
- low level
- learning environment