DISNet: A sequential learning framework to handle occlusion in human action recognition with video acquisition sensors.
Suraj Prakash SahooSowjanya ModalavalasaSamit AriPublished in: Digit. Signal Process. (2022)
Keyphrases
- action recognition
- video dataset
- spatial temporal
- human actions
- static images
- action classification
- max margin
- activity recognition
- computer vision
- bag of words
- spatio temporal interest points
- body parts
- human pose
- spatio temporal
- recognizing human actions
- recognition of human actions
- human detection
- action detection
- human activities
- motion history images
- recognizing actions
- video data
- video sequences