Object Detection
Transformers
Safetensors
surgical-video
spatio-temporal-grounding
medical-vision-language-model
eccv-2026
Instructions to use linzher/RefineRank with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use linzher/RefineRank with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("object-detection", model="linzher/RefineRank")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("linzher/RefineRank", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add pipeline tag and paper link
#1
by nielsr HF Staff - opened
README.md
CHANGED
|
@@ -1,15 +1,18 @@
|
|
| 1 |
---
|
| 2 |
-
license: cc-by-4.0
|
| 3 |
library_name: transformers
|
|
|
|
|
|
|
| 4 |
tags:
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
---
|
| 10 |
|
| 11 |
# RefineRank: Joint Box Refinement and Ranking for Surgical Spatio-Temporal Grounding
|
| 12 |
|
|
|
|
|
|
|
| 13 |
Official checkpoints for the ECCV 2026 MedVidU Workshop paper **RefineRank**.
|
| 14 |
|
| 15 |
RefineRank couples two **frozen** backbones — a MedVLM (Qwen2.5-VL
|
|
@@ -79,4 +82,4 @@ python interface.py predict # auto-discovers checkpoints/refinenet/
|
|
| 79 |
booktitle = {ECCV Workshops (MedVidU)},
|
| 80 |
year = {2026}
|
| 81 |
}
|
| 82 |
-
```
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
library_name: transformers
|
| 3 |
+
license: cc-by-4.0
|
| 4 |
+
pipeline_tag: object-detection
|
| 5 |
tags:
|
| 6 |
+
- surgical-video
|
| 7 |
+
- spatio-temporal-grounding
|
| 8 |
+
- medical-vision-language-model
|
| 9 |
+
- eccv-2026
|
| 10 |
---
|
| 11 |
|
| 12 |
# RefineRank: Joint Box Refinement and Ranking for Surgical Spatio-Temporal Grounding
|
| 13 |
|
| 14 |
+
**Paper**: [RefineRank: Joint Box Refinement and Ranking for Surgical Spatio-Temporal Grounding](https://huggingface.co/papers/2608.23928)
|
| 15 |
+
|
| 16 |
Official checkpoints for the ECCV 2026 MedVidU Workshop paper **RefineRank**.
|
| 17 |
|
| 18 |
RefineRank couples two **frozen** backbones — a MedVLM (Qwen2.5-VL
|
|
|
|
| 82 |
booktitle = {ECCV Workshops (MedVidU)},
|
| 83 |
year = {2026}
|
| 84 |
}
|
| 85 |
+
```
|