Few-Shot Action Recognition with Permutation-Invariant Attention.
Hongguang ZhangLi ZhangXiaojuan QiHongdong LiPhilip H. S. TorrPiotr KoniuszPublished in: ECCV (5) (2020)
Keyphrases
- action recognition
- human actions
- bag of words
- human detection
- computer vision
- activity recognition
- action classification
- spatial temporal
- body parts
- recognition of human actions
- bag of features
- action detection
- video dataset
- video data
- depth sensors
- view invariant
- video shots
- recognizing actions
- recognizing human actions
- view invariant action recognition
- depth cameras
- human pose
- affine transformation
- invariant representation
- mid level
- video content
- detection algorithm
- spatio temporal
- action recognition in videos
- independent subspace analysis
- image sequences