Add MTRefSeg project for bi-temporal vision-language segmentation framework

robmarkcole · robmarkcole · commit c6704412cc7f · 2026-06-06T14:27:48.000+01:00
diff --git a/README.md b/README.md
@@ -3791,6 +3791,8 @@ Explainable AI (XAI) is a field of artificial intelligence that focuses on devel
 
 - [ForestChat](https://github.com/JamesBrockUoB/ForestChat) -> Adapting Vision-Language Models for Interactive Forest Change Analysis.
 
+- [MTRefSeg](https://github.com/LiBingyu01/MTRefSeg) -> MTRefSeg-R1 is a bi-temporal vision-language segmentation framework where the model receives two temporal images (T1, T2) plus a natural-language instruction and predicts the changed region. Built on the SegEarth-R1 codebase, it extends instruction-following change referring segmentation to remote-sensing, aerial, and normal-scene views.
+
 #
 ## Foundational models
 

Original file line number	Diff line number	Diff line change
`@@ -3791,6 +3791,8 @@ Explainable AI (XAI) is a field of artificial intelligence that focuses on devel`
`3791`	`3791`
`3792`	`3792`	`- [ForestChat](https://github.com/JamesBrockUoB/ForestChat) -> Adapting Vision-Language Models for Interactive Forest Change Analysis.`
`3793`	`3793`
	`3794`	`+- [MTRefSeg](https://github.com/LiBingyu01/MTRefSeg) -> MTRefSeg-R1 is a bi-temporal vision-language segmentation framework where the model receives two temporal images (T1, T2) plus a natural-language instruction and predicts the changed region. Built on the SegEarth-R1 codebase, it extends instruction-following change referring segmentation to remote-sensing, aerial, and normal-scene views.`
	`3795`	`+`
`3794`	`3796`	`#`
`3795`	`3797`	`## Foundational models`
`3796`	`3798`