Geometric Deep Learning on Skeleton Sequences for 2D/3D Action Recognition.
Rasha FrijiHassen DriraFaten ChaiebPublished in: VISIGRAPP (5: VISAPP) (2020)
Keyphrases
- action recognition
- deep learning
- human actions
- bag of words
- activity recognition
- computer vision
- recognizing human actions
- motion history images
- unsupervised learning
- machine learning
- mental models
- action classification
- hidden markov models
- human activities
- weakly supervised
- pose estimation
- spatial information
- object recognition