Understanding Video Scenes through Text: Insights from Text-based Video Question Answering.
Soumya JahagirdarMinesh MathewDimosthenis KaratzasC. V. JawaharPublished in: CoRR (2023)
Keyphrases
- question answering
- video scene
- video data
- scene analysis
- news video
- video analysis
- information retrieval
- video sequences
- syntactic information
- video shots
- dynamic scenes
- video frames
- information extraction
- named entities
- natural language processing
- moving objects
- multimedia
- video clips
- text mining
- passage retrieval
- video streams
- foreground objects
- question answering systems
- video content
- space time
- natural language
- multiple features
- event detection
- audio visual
- video search
- keywords
- computer vision
- video database
- video retrieval
- machine learning
- text documents
- search engine
- question answer pairs