Unsupervised Human Action Recognition with Skeletal Graph Laplacian and Self-Supervised Viewpoints Invariance.
Giancarlo PaolettiJacopo CavazzaCigdem BeyanAlessio Del BuePublished in: CoRR (2022)
Keyphrases
- action recognition
- view invariant
- graph laplacian
- view invariant action recognition
- human actions
- human activities
- human motion
- computer vision
- activity recognition
- bag of words
- action classification
- viewpoint
- spectral clustering
- random walk
- unsupervised learning
- single view
- multi view
- supervised learning
- basis functions
- spectral analysis
- human body
- image sequences
- visual words
- probabilistic model
- object recognition