RaSTFormer: region-aware spatiotemporal transformer for visual homogenization recognition in short videos.
Shuying ZhangJing ZhangHui ZhangLi ZhuoPublished in: Neural Comput. Appl. (2024)
Keyphrases
- human activities
- visual learning
- recognition rate
- recognition accuracy
- spatiotemporal features
- visual analysis
- object recognition
- visual search
- feature extraction
- visual perception
- visual recognition
- video search
- spatial and temporal
- news video
- action recognition
- video sequences
- activity recognition
- video frames
- visual effects
- visual features
- fuzzy logic
- video indexing and retrieval
- visual data
- recognition algorithm
- video data
- visual information
- fault diagnosis
- face recognition
- region detection
- visual processing
- space time
- moving objects
- image retrieval
- gait recognition
- image data
- video clips
- power system