Ensemble Modeling for Multimodal Visual Action Recognition.
Jyoti KiniSarah FleischerIshan R. DaveMubarak ShahPublished in: CoRR (2023)
Keyphrases
- action recognition
- mid level
- bag of words
- human detection
- human actions
- activity recognition
- computer vision
- action classification
- body parts
- spatial temporal
- recognizing human actions
- visual information
- human pose
- multi modal
- bag of features
- low level
- video dataset
- depth sensors
- view invariant
- human object interactions
- independent subspace analysis
- recognizing actions
- action primitives
- recognition of human actions
- action detection
- static images
- high level
- depth cameras
- motion history images
- bag of visual words
- visual features
- feature vectors
- training set