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
Commit History
-
Add pipeline tag and paper link
Verified signatureThis PR adds the `pipeline_tag: object-detection` to the YAML metadata so the model is correctly categorized on the Hugging Face Hub. It also adds a direct link to the paper page (https://huggingface.co/papers/2608.23928) in the model card content for easy reference.ac01dca
-
Upload README.md with huggingface_hub
Verified signature128f37d -
Flatten checkpoints layout: vlm/, grounding_dino/, refinenet/ hold core files directly
Verified signature30e599f -
Upload folder using huggingface_hub
Verified signature4a24473 -
Remove root-level duplicate deployment_manifest.json; canonical copy under checkpoints/refinenet/run_iter132_submission/
Verified signature69bbc04 -
Remove root-level duplicate proposal_adapter_full.pt; canonical copy under checkpoints/refinenet/run_iter132_submission/
Verified signature63513b2 -
Upload README.md with huggingface_hub
Verified signature3a5f6d9 -
Upload folder using huggingface_hub
Verified signature12b6f85 -
Upload folder using huggingface_hub
Verified signatureac55ccf -
initial commit
Verified signature444805c