The Role of the Input in Natural Language Video Description.
Silvia CascianelliGabriele CostanteAlessandro DevoThomas A. CiarfugliaPaolo ValigiMario Luca FravoliniPublished in: CoRR (2021)
Keyphrases
- natural language
- video sequences
- video data
- video content
- natural language descriptions
- real time
- multimedia
- video frames
- semantic representation
- video streams
- real time video
- natural language processing
- input data
- language processing
- digital video
- video database
- content description
- video analysis
- natural language interface
- machine translation
- space time
- multimedia data
- semantic interpretation
- spatial and temporal
- video images
- high level
- video processing
- machine learning
- information extraction
- semantic concepts
- semantic analysis
- video clips
- video retrieval
- video surveillance
- event detection
- question answering