Add pipeline tag: video-text-to-text

README.md

@@ -1,20 +1,21 @@
 ---
+datasets:
+- CSL-Daily
+- CSL-News
+language:
+- zh
 library_name: transformers
 license: mit
 model_name: Geo-Sign (Hyperbolic-Token)
-paperswithcode_id: geo-sign-hyperbolic-contrastive-regularisation
 tags:
-  - sign-language-translation
-  - skeleton-based
-  - hyperbolic-geometry
-  - mT5
-datasets:
-  - CSL-Daily
-  - CSL-News
-language:
-  - zh
+- sign-language-translation
+- skeleton-based
+- hyperbolic-geometry
+- mT5
+paperswithcode_id: geo-sign-hyperbolic-contrastive-regularisation
 task:
-  - sign-language-translation
+- sign-language-translation
+pipeline_tag: video-text-to-text
 ---
 
 # Geo-Sign 🌐✋ → 📝  
@@ -43,8 +44,8 @@ Geo-Sign projects pose-based sign-language features into a learnable **Poincaré
 Compared with the strong Uni-Sign pose baseline, Geo-Sign boosts BLEU-4 by **+1.81** and ROUGE-L by **+3.03** on the CSL-Daily benchmark while keeping privacy-friendly skeletal inputs only.
 
 ## Intended Uses & Scope
-* **Primary** – Sign-language-to-text translation research, especially for resource-constrained or privacy-sensitive settings where RGB video is unavailable.  
-* **Out-of-scope** – Real-time production deployments without reliable pose estimation, medical or legal interpretations, or languages beyond datasets the model was trained on.
+*   **Primary** – Sign-language-to-text translation research, especially for resource-constrained or privacy-sensitive settings where RGB video is unavailable.  
+*   **Out-of-scope** – Real-time production deployments without reliable pose estimation, medical or legal interpretations, or languages beyond datasets the model was trained on.
 
 ## Evaluation
 
@@ -58,11 +59,11 @@ Geo-Sign outperforms all previous gloss-free pose-only methods and rivals many R
 
 ## Limitations & Ethical Considerations
 
-* **Pose-estimation dependency** – Errors in upstream key-points propagate to the translation.  
-* **Training latency** – Hyperbolic operations slow training (~4–6 ×) but add **no** cost at inference.  
-* **Generalisation** – Evaluated only on Chinese Sign Language; other sign languages are not guaranteed.  
-* **Mis-translation risk** – Automatic SLT can mis-communicate; keep a human in the loop for critical use cases.  
-* **Biases** – CSL-Daily is domain-specific (news/TV); outputs may reflect that linguistic style.
+*   **Pose-estimation dependency** – Errors in upstream key-points propagate to the translation.  
+*   **Training latency** – Hyperbolic operations slow training (~4–6 ×) but add **no** cost at inference.  
+*   **Generalisation** – Evaluated only on Chinese Sign Language; other sign languages are not guaranteed.  
+*   **Mis-translation risk** – Automatic SLT can mis-communicate; keep a human in the loop for critical use cases.  
+*   **Biases** – CSL-Daily is domain-specific (news/TV); outputs may reflect that linguistic style.
 
 ---
 
@@ -74,5 +75,4 @@ Geo-Sign outperforms all previous gloss-free pose-only methods and rivals many R
   author={Fish, Edward and Bowden, Richard},
   journal={arXiv preprint arXiv:2506.00129},
   year={2025}
-}```
-
+}```