TRACL: Temporal reconstruction and adaptive consistency loss for semi-supervised video semantic segmentation.
Zhixue LiangWenyong DongBo ZhangPublished in: IET Image Process. (2024)
Keyphrases
- semantic segmentation
- semi supervised
- weakly supervised
- superpixels
- video sequences
- label transfer
- scene classification
- semi supervised learning
- conditional random fields
- video data
- three dimensional
- object categories
- video frames
- multi view
- pairwise
- object class
- labeled data
- d objects
- object segmentation
- biologically inspired
- high resolution
- object recognition
- object detection