LARNet: Latent Action Representation for Human Action Synthesis.
Naman BiyaniAayush Jung RanaShruti VyasYogesh Singh RawatPublished in: CoRR (2021)
Keyphrases
- human actions
- recognizing human actions
- action recognition
- view invariant
- recognition of human actions
- action classification
- human motion
- spatio temporal
- space time
- action recognition in videos
- activity recognition
- human activities
- action sequences
- recognizing actions
- visual features
- video sequences
- data sets
- bag of features
- computer vision
- image representation
- three dimensional
- latent space
- single view
- multi view
- global features
- feature extraction
- image sequences
- image classification
- bag of words