Joint Deep Learning for RGB-D Action Recognition.
Xiaolei QinYongxin GeLiuwei ZhanGuangrui LiSheng HuangHongxing WangFeiyu ChenPublished in: VCIP (2018)
Keyphrases
- action recognition
- deep learning
- depth cameras
- human actions
- unsupervised learning
- bag of words
- machine learning
- computer vision
- mental models
- recognizing human actions
- human activities
- weakly supervised
- depth images
- spatio temporal
- single image
- semi supervised
- depth information
- object segmentation
- multi class
- human pose
- moving objects
- feature space