Video-FocalNets: Spatio-Temporal Focal Modulation for Video Action Recognition.
Syed Talal WasimMuhammad Uzair KhattakMuzammal NaseerSalman H. KhanMubarak ShahFahad Shahbaz KhanPublished in: CoRR (2023)
Keyphrases
- action recognition
- human actions
- spatial temporal
- spatio temporal
- action classification
- spatio temporal interest points
- action detection
- video dataset
- video database
- video data
- spatial and temporal
- motion features
- recognition of human actions
- space time
- video sequences
- activity recognition
- recognizing human actions
- static images
- view invariant
- multimedia
- video content
- computer vision
- human activities
- video analysis
- human detection
- video shots
- human motion
- video frames
- human pose
- three dimensional
- moving objects
- event recognition
- video retrieval
- video surveillance
- image sequences
- key frames
- depth sensors
- human body
- visual features