docs: add Hugging Face Spaces demo

Add the official SAGE interactive demo hosted on Hugging Face Spaces to the README.

README.md

@@ -8,6 +8,12 @@ tags:
 - dinov2
 pipeline_tag: image-feature-extraction
 library_name: pytorch
+language:
+- en
+metrics:
+- recall
+base_model:
+- facebook/dinov2-base
 ---
 
 # SAGE-VPR
@@ -15,11 +21,26 @@ Official checkpoints for **SAGE: Spatial-visual Adaptive Graph Exploration for E
 
 Paper: https://arxiv.org/abs/2509.25723  
 GitHub: https://github.com/chenshunpeng/SAGE  
-Project Page: https://chenshunpeng.github.io/projects/SAGE
+Project Page: https://chenshunpeng.github.io/projects/SAGE  
+Demo: https://huggingface.co/spaces/shunpeng/sage-visual-place-recognition
 
 ## Checkpoints
 | File | Description |
 | --- | --- |
 | `SAGE.pth` | Full SAGE checkpoint with the cross-image encoder. |
 | `SAGE_No-Encoder_Vit-B.pth` | SAGE checkpoint without the cross-image encoder, using DINOv2 ViT-B as the backbone. |
-| `SAGE_No-Encoder_Vit-L.pth` | SAGE checkpoint without the cross-image encoder, using DINOv2 ViT-L as the backbone. |
+| `SAGE_No-Encoder_Vit-L.pth` | SAGE checkpoint without the cross-image encoder, using DINOv2 ViT-L as the backbone. |
+
+## Online Demo
+
+An interactive demo is available on Hugging Face Spaces:
+
+[Try the SAGE Visual Place Recognition Demo](https://huggingface.co/spaces/shunpeng/sage-visual-place-recognition)
+
+## Acknowledgements
+
+This interactive demo was originally created by
+[@apolinario](https://github.com/apolinario) and the
+[Hugging Face](https://huggingface.co/) open-source team.
+
+We sincerely appreciate their support in making SAGE more accessible to the community.