Unified Contrastive Fusion Transformer for Multimodal Human Action Recognition.
Kyoung Ok YangJunho KohJun Won ChoiPublished in: CoRR (2023)
Keyphrases
- action recognition
- static images
- human movements
- human activities
- spatio temporal interest points
- bag of words
- human actions
- human detection
- activity recognition
- motion capture data
- motion history images
- body parts
- human object interactions
- computer vision
- spatial temporal
- depth sensors
- recognition of human actions
- action classification
- multi modal
- action detection
- recognizing actions
- bag of features
- view invariant
- independent subspace analysis
- human pose
- human activity recognition
- unified model
- recognizing human actions
- video dataset
- low level
- three dimensional