Learning Question-Guided Video Representation for Multi-Turn Video Question Answering.
Guan-Lin ChaoAbhinav RastogiSemih YavuzDilek Hakkani-TürJindong ChenIan R. LanePublished in: SIGdial (2019)
Keyphrases
- question answering
- video representation
- video streams
- question classification
- space time
- natural language processing
- spatio temporal
- video content
- question answering systems
- natural language
- natural language questions
- answer extraction
- answer validation
- qa clef
- co occurrence
- video processing
- video analysis
- temporal information
- image representation
- information extraction
- moving objects
- machine learning