Add pipeline tag

This PR adds the `pipeline_tag` metadata to the model card, making it easier to discover for tasks involving video-to-text translation of sign language. This will help researchers find and utilize this model for sign language understanding tasks. It also updates the citation using the bibtex entry from the Github README.

README.md

@@ -1,5 +1,6 @@
 ---
 license: cc-by-nc-4.0
+pipeline_tag: video-text-to-text
 ---
 
 # Summary
@@ -13,7 +14,7 @@ Here, we provide the model weights for Uni-Sign and the pre-extracted pose files
 
 # Citation
 ```
-@article{li2025uni-sign,
+@article{li2025uni,
   title={Uni-Sign: Toward Unified Sign Language Understanding at Scale},
   author={Li, Zecheng and Zhou, Wengang and Zhao, Weichao and Wu, Kepeng and Hu, Hezhen and Li, Houqiang},
   journal={arXiv preprint arXiv:2501.15187},