MAPLE: Masked Pseudo-Labeling autoEncoder for Semi-supervised Point Cloud Action Recognition.
Xiaodong ChenWu LiuXinchen LiuYongdong ZhangJungong HanTao MeiPublished in: ACM Multimedia (2022)
Keyphrases
- action recognition
- point cloud
- semi supervised
- active learning
- structure from motion
- semi supervised learning
- surface reconstruction
- human actions
- labeled data
- computer vision
- activity recognition
- recognizing human actions
- point sets
- supervised learning
- pairwise
- action classification
- image segmentation
- laser scanner
- body parts
- multi view
- recognition of human actions
- stereo camera
- d scene
- action recognition in videos