Residual attention fusion network for video action recognition.
Ao LiYang YiDaan LiangPublished in: J. Vis. Commun. Image Represent. (2024)
Keyphrases
- action recognition
- human actions
- action classification
- spatial temporal
- video dataset
- action detection
- recognizing human actions
- motion features
- recognition of human actions
- bag of words
- activity recognition
- static images
- spatio temporal interest points
- human detection
- space time interest points
- computer vision
- body parts
- human activities
- mid level
- video streams
- video data
- recognizing actions
- depth sensors
- video frames
- video analysis
- video content
- space time
- human pose
- multimedia
- motion capture data
- motion history images
- video retrieval
- spatio temporal