Global Semantic Descriptors for Zero-Shot Action Recognition.
Valter EstevamRayson LarocaHélio PedriniDavid MenottiPublished in: CoRR (2022)
Keyphrases
- action recognition
- action recognition in videos
- bag of features
- human actions
- bag of words
- activity recognition
- human detection
- mid level features
- spatial temporal
- action classification
- computer vision
- body parts
- video dataset
- global features
- action primitives
- semantic information
- recognizing actions
- view invariant
- static images
- mid level
- human activities
- low level features
- depth sensors
- keypoints
- human pose
- recognition of human actions
- recognizing human actions
- feature extraction
- action detection
- low level descriptors
- event detection