Attention-Driven Appearance-Motion Fusion Network for Action Recognition.
Shaocan LiuXin MaPublished in: IEEE Trans. Multim. (2023)
Keyphrases
- action recognition
- static images
- recognizing human actions
- recognition of human actions
- human movements
- human actions
- action recognition in videos
- motion features
- bag of words
- view invariant
- activity recognition
- action primitives
- computer vision
- action classification
- motion capture data
- human detection
- mid level
- body parts
- human activities
- motion history images
- recognizing actions
- motion analysis
- image sequences
- depth sensors
- optical flow
- view invariant action recognition
- human activity recognition
- human pose
- human motion
- appearance model
- video frames
- d scene
- camera motion
- human body
- motion estimation
- moving objects
- video sequences
- three dimensional