Scene Flow to Action Map: A New Representation for RGB-D Based Action Recognition with Convolutional Neural Networks.
Pichao WangWanqing LiZhimin GaoYuyao ZhangChang TangPhilip OgunbonaPublished in: CVPR (2017)
Keyphrases
- action recognition
- recognizing human actions
- depth sensors
- human actions
- recognition of human actions
- depth cameras
- view invariant
- scene flow
- action classification
- convolutional neural networks
- depth data
- recognizing actions
- computer vision
- action recognition in videos
- activity recognition
- depth information
- d scene
- atomic actions
- human pose
- depth map
- optical flow
- pose estimation
- multi camera
- space time
- image representation
- multi view
- object recognition