Movie Question Answering: Remembering the Textual Cues for Layered Visual Contents.
Bo WangYoujiang XuYahong HanRichang HongPublished in: CoRR (2018)
Keyphrases
- question answering
- visual content
- visual features
- video retrieval
- visual information
- image content
- low level
- image collections
- image retrieval
- multimedia content
- natural language processing
- visual words
- information extraction
- spatial relationships
- image representation
- information retrieval
- qa clef
- key frames
- video search
- natural language
- natural language questions
- multimedia data
- high level
- passage retrieval
- multimedia databases
- action recognition
- databases
- multimedia
- artificial intelligence
- machine learning
- image annotation
- image classification
- co occurrence
- video sequences
- answer extraction