Run length encoding turns segmentation masks into compressible token sequences that autoregressive models predict for semantic and panoptic segmentation in images and videos.
Liu et al., Swin Transformer: Hierarchical Vision Transformer using Shifted Windows, ICCV (2021), 9992–10002
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Tokenizing Semantic Segmentation with Run Length Encoding
Run length encoding turns segmentation masks into compressible token sequences that autoregressive models predict for semantic and panoptic segmentation in images and videos.