MoNet: Deep Motion Exploitation for Video Object Segmentation.
Huaxin XiaoJiashi FengGuosheng LinYu LiuMaojun ZhangPublished in: CVPR (2018)
Keyphrases
- global motion estimation
- motion analysis
- motion estimation
- space time
- image sequences
- global motion
- optical flow
- camera motion
- motion model
- spatial and temporal
- motion field
- human motion
- object motion
- visual cues
- motion segmentation
- motion capture
- reference frame
- motion parameters
- optic flow
- motion tracking
- articulated objects
- image motion
- spatio temporal
- deep learning
- multiscale