CSINet combines a full-image remote view with high-resolution close-view patches in a dual-branch transformer to improve referring remote sensing image segmentation, reporting state-of-the-art mIoU on RRSIS-D, RefSegRS, and RIS-Bench.
Linguistic structure guided context modeling for referring image segmentation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Referring Remote Sensing Image Segmentation with Cross-view Semantics Interaction Network
CSINet combines a full-image remote view with high-resolution close-view patches in a dual-branch transformer to improve referring remote sensing image segmentation, reporting state-of-the-art mIoU on RRSIS-D, RefSegRS, and RIS-Bench.