ESC-ZSAR: Expanded Semantics from Categories with Cross-Attention for Zero-Shot Action Recognition.
Jeong-Cheol LeeDong-Gyu LeePublished in: Expert Syst. Appl. (2024)
Keyphrases
- action recognition
- human actions
- bag of words
- human detection
- spatial temporal
- activity recognition
- computer vision
- action classification
- object categories
- recognizing human actions
- view invariant
- bag of features
- video dataset
- atomic actions
- body parts
- mid level features
- action recognition in videos
- human activities
- static images
- semantic information
- multi view
- low level
- depth sensors
- action primitives
- spatio temporal
- recognition of human actions
- viewpoint