PeMapNet: Action Recognition from Depth Videos Using Pyramid Energy Maps on Neural Networks.
Jiahao LiHejun WuXinrui ZhouPublished in: ICTAI (2017)
Keyphrases
- action recognition
- human actions
- video dataset
- recognition of human actions
- action classification
- depth sensors
- ucf sports
- recognizing human actions
- depth cameras
- human activities
- motion features
- view invariant
- space time interest points
- bag of words
- recognizing actions
- spatio temporal interest points
- action recognition in videos
- static images
- activity recognition
- action detection
- human detection
- computer vision
- human object interactions
- motion history images
- mid level features
- multiscale
- spatial temporal
- motion capture data
- depth information
- body parts
- atomic actions
- human pose
- depth map
- video sequences
- input image
- bag of features
- spatio temporal
- event recognition
- video data
- image representation