Joint Temporal Pooling for Improving Skeleton-based Action Recognition.
Shanaka Ramesh GunasekaraWanqing LiJack YangPhilip OgunbonaPublished in: DICTA (2023)
Keyphrases
- action recognition
- spatial temporal
- human actions
- bag of words
- human detection
- action classification
- activity recognition
- motion history images
- spatio temporal
- computer vision
- recognizing actions
- body parts
- temporal information
- recognizing human actions
- depth sensors
- spatial and temporal
- view invariant
- independent subspace analysis
- video dataset
- machine learning
- bag of features
- action recognition in videos
- static images
- temporal relations
- recognition of human actions
- depth cameras
- space time
- object recognition
- view invariant action recognition
- action primitives
- atomic actions
- max margin
- mid level
- event detection
- human activities