Transformer-based Fusion of 2D-pose and Spatio-temporal Embeddings for Distracted Driver Action Recognition.
Erkut AkdagZeqi ZhuEgor BondarevPeter H. N. de WithPublished in: CoRR (2024)
Keyphrases
- action recognition
- human actions
- spatio temporal
- human pose
- recognizing actions
- spatial temporal
- action recognition in videos
- view invariant
- spatio temporal interest points
- bag of words
- recognition of human actions
- pose estimation
- action detection
- activity recognition
- human detection
- computer vision
- action classification
- recognizing human actions
- static images
- spatial and temporal
- image sequences
- body parts
- depth sensors
- human activities
- d objects
- action primitives
- space time
- view invariant action recognition
- bag of features
- partial occlusion
- human motion
- human object interactions
- viewpoint
- video sequences