Co-attentional Transformers for Story-Based Video Understanding.
Björn BebenseeByoung-Tak ZhangPublished in: CoRR (2020)
Keyphrases
- real time
- video content
- multimedia
- video sequences
- video data
- video streams
- digital video
- video processing
- video retrieval
- real time video
- video frames
- video analysis
- video segmentation
- story generation
- video database
- space time
- visual search
- content based video retrieval
- image sequences
- event recognition
- deeper understanding
- object recognition
- event detection
- cognitive processes
- video clips
- video surveillance
- human actions