An Action Is Worth Multiple Words: Handling Ambiguity in Action Recognition.
Kiyoon KimDavide MoltisantiOisin Mac AodhaLaura Sevilla-LaraPublished in: CoRR (2022)
Keyphrases
- action recognition
- human actions
- action classification
- recognizing human actions
- space time interest points
- recognizing actions
- recognition of human actions
- action primitives
- action detection
- view invariant
- activity recognition
- bag of words
- computer vision
- human detection
- human pose
- spatial temporal
- body parts
- static images
- human activities
- bag of features
- viewpoint
- motion history images
- spatio temporal
- video sequences
- independent subspace analysis
- view invariant action recognition
- human motion
- n gram
- image classification
- probabilistic model
- keywords