ViViT: A Video Vision Transformer.
Anurag ArnabMostafa DehghaniGeorg HeigoldChen SunMario LucicCordelia SchmidPublished in: CoRR (2021)
Keyphrases
- real time
- vision system
- video frames
- computer vision
- multimedia
- video streams
- video analysis
- video surveillance
- video content
- video sequences
- video database
- video clips
- real time video
- video processing
- video segmentation
- video retrieval
- event detection
- spatial and temporal
- power system
- video data
- image processing
- search engine
- space time
- fuzzy logic
- image retrieval
- video images