Motion-Appearance Co-Memory Networks for Video Question Answering.
Jiyang GaoRunzhou GeKan ChenRam NevatiaPublished in: CVPR (2018)
Keyphrases
- question answering
- object motion
- dynamic textures
- space time
- key frames
- video data
- question classification
- natural language
- image sequences
- information extraction
- information retrieval
- video sequences
- multimedia
- natural language processing
- cross language
- named entities
- visual data
- passage retrieval
- qa clef
- video content
- natural language questions
- open domain question answering
- syntactic information
- human motion
- candidate answers
- sentence retrieval
- semantic roles
- qa systems
- relation extraction
- video retrieval
- answer validation
- knowledge base