Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Video.
Xiaowei ZhouMenglong ZhuSpyridon LeonardosKonstantinos G. DerpanisKostas DaniilidisPublished in: CoRR (2015)
Keyphrases
- video data
- video streams
- image sequences
- video frames
- video sequences
- action detection
- multimedia
- video content
- video clips
- real time
- real time video
- video database
- space time
- pose estimation
- neural network
- body parts
- spatial and temporal
- action recognition
- temporal information
- event detection
- multimedia data
- dynamic scenes
- visual data
- moving camera
- feature points
- video segmentation
- stereo camera
- video images
- optical flow
- online video
- action classification
- spatio temporal