Update README.md

README.md

@@ -37,10 +37,18 @@ This model's text encoder can be used with Stable Diffusion:
 If you use this model in your research, please cite the original paper:
 
 ```
-@article{chen2025lrsclip,
-  title={LRSCLIP: A Vision-Language Foundation Model for Aligning Remote Sensing Image with Longer Text},
-  author={Chen, Weizhi and Chen, Jingbo and Deng, Yupeng and Chen, Jiansheng and Feng, Yuman and Xi, Zhihao and Liu, Diyou and Li, Kai and Meng, Yu},
-  journal={arXiv preprint arXiv:2503.19311},
-  year={2025}
+@article{chenDGTRSDDGTRSCLIPDualGranularity2025a,
+  title = {{{DGTRSD}} and {{DGTRSCLIP}}: {{A Dual-Granularity Remote Sensing Image}}--{{Text Dataset}} and {{Vision}}--{{Language Foundation Model}} for {{Alignment}}},
+  shorttitle = {{{DGTRSD}} and {{DGTRSCLIP}}},
+  author = {Chen, Weizhi and Deng, Yupeng and Jin, Wei and Chen, Jingbo and Chen, Jiansheng and Feng, Yuman and Xi, Zhihao and Liu, Diyou and Li, Kai and Meng, Yu},
+  year = 2025,
+  journal = {IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing},
+  volume = {18},
+  pages = {29113--29130},
+  issn = {2151-1535},
+  doi = {10.1109/JSTARS.2025.3625958},
+  urldate = {2025-12-18},
+  keywords = {Buildings,Cross modal retrieval,Cross-modal alignment,curriculum learning,dual-granularity,Green buildings,Integrated circuit modeling,remote sensing,Remote sensing,Resource management,Semantics,Sports,Training,vision-language foundation models (VLFM),Visualization}
 }
+
 ```