Hierarchical Temporal Transformer for 3D Hand Pose Estimation and Action Recognition from Egocentric RGB Videos.
Yilin WenHao PanLei YangJia PanTaku KomuraWenping WangPublished in: CoRR (2022)
Keyphrases
- action recognition
- human actions
- activity recognition
- motion history images
- action classification
- video dataset
- recognition of human actions
- spatial temporal
- human activities
- ucf sports
- recognizing human actions
- spatio temporal interest points
- motion features
- recognizing actions
- view invariant
- bag of words
- static images
- human detection
- space time interest points
- spatio temporal
- computer vision
- action detection
- action recognition in videos
- body parts
- atomic actions
- human object interactions
- bag of features
- mid level features
- human activity recognition
- temporal structure
- temporal information
- color images
- temporal coherence
- spatial and temporal
- space time
- color space
- temporal relationships
- event recognition
- human motion
- motion trajectories
- motion capture data
- color information
- video content
- key frames
- video sequences
- human pose
- video clips