Domain Generalization through Audio-Visual Relative Norm Alignment in First Person Action Recognition.
Mirco PlanamenteChiara PlizzariEmanuele AlbertiBarbara CaputoPublished in: CoRR (2021)
Keyphrases
- action recognition
- audio visual
- multi modal
- bag of words
- human actions
- visual data
- activity recognition
- action classification
- visual information
- computer vision
- multimedia
- recognizing human actions
- multi stream
- recognition of human actions
- image database
- co occurrence
- spatio temporal
- feature space
- machine learning
- recognizing actions