From CNNs to Transformers in Multimodal Human Action Recognition: A Survey.
Muhammad Bilal ShaikhSyed Mohammed Shamsul IslamDouglas ChaiNaveed AkhtarPublished in: CoRR (2024)
Keyphrases
- action recognition
- static images
- human movements
- human activities
- activity recognition
- human actions
- spatio temporal interest points
- human detection
- bag of words
- spatial temporal
- body parts
- independent subspace analysis
- action classification
- computer vision
- human object interactions
- motion capture data
- mid level
- motion history images
- bag of features
- action detection
- recognizing human actions
- human pose
- depth sensors
- recognition of human actions
- motion features
- view invariant
- recognizing actions
- space time interest points
- view invariant action recognition
- action primitives
- human activity recognition
- video dataset
- multi modal
- image sequences