Hierarchical Temporal Transformer for 3D Hand Pose Estimation and Action Recognition from Egocentric RGB Videos.
Yilin WenHao PanLei YangJia PanTaku KomuraWenping WangPublished in: CVPR (2023)
Keyphrases
- action recognition
- activity recognition
- human actions
- motion history images
- action classification
- video dataset
- recognition of human actions
- human activities
- spatial temporal
- motion features
- ucf sports
- view invariant
- recognizing human actions
- static images
- recognizing actions
- bag of words
- spatio temporal interest points
- space time interest points
- atomic actions
- action recognition in videos
- spatio temporal
- computer vision
- human detection
- action detection
- temporal relationships
- mid level features
- color images
- human activity recognition
- body parts
- human motion
- temporal coherence
- human object interactions
- spatial and temporal
- color space
- space time
- event recognition
- temporal structure
- color information
- event detection
- temporal information
- video frames
- temporal resolution
- temporal relations
- human pose