Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Video.
Xiaowei ZhouMenglong ZhuSpyridon LeonardosKonstantinos G. DerpanisKostas DaniilidisPublished in: CVPR (2016)
Keyphrases
- video data
- video sequences
- video clips
- multimedia
- video content
- video streams
- image sequences
- real time
- pose estimation
- temporal information
- video database
- event recognition
- video images
- dynamic scenes
- video analysis
- video shots
- event detection
- depth perception
- action detection
- video surveillance
- human activities
- video frames
- object detection
- optical flow
- neural network
- body parts
- multimedia data
- spatial and temporal
- space time
- temporal structure
- real time video
- online video