A serial semantic segmentation model based on encoder-decoder architecture.
Yan ZhouPublished in: Knowl. Based Syst. (2024)
Keyphrases
- semantic segmentation
- street scenes
- video codec
- distributed video coding
- label transfer
- scene classification
- superpixels
- conditional random fields
- motion estimation
- object class
- bit rate
- rate distortion
- image understanding
- weakly supervised
- object categories
- wyner ziv
- feature extraction
- visual words
- text classification
- pairwise
- object recognition