Views
No views yet
QueryConditionedProposalAdapter). RefineNet uses
MedVLM language and regional features to predict coordinate corrections and
box-quality scores for GroundingDINO proposals; a parameter-free decoder then
returns the highest-scoring original or refined box.checkpoints/ tree expected by the code
repository — three flat folders, each holding its core files directly:checkpoints/
├── vlm/ # frozen MedVLM, HF format (~16 GB)
│ ├── config.json, generation_config.json, tokenizer*, preprocessor_config.json, ...
│ └── model-00001..00004-of-00004.safetensors
├── grounding_dino/
│ └── groundingdino_swinb_cogcoor.pth # frozen GroundingDINO SwinB (~895 MB)
└── refinenet/ # trained RefineNet, this work (~5 MB)
├── proposal_adapter_full.pt # SHA-256: 932e479b…463d9b
└── deployment_manifest.jsonrefinenet/proposal_adapter_full.pt is the exact checkpoint behind the
paper's MedVidBench submission (run_iter132_submission). SHA-256:
932e479b854c3d5fbafee25a3fcf9e6481e864fe98a6867502d6ebff39463d9b.vlm/ and grounding_dino/ are third-party frozen weights
(uAI-NEXUS-MedVLM by UII-AI and
GroundingDINO by
IDEA-Research), mirrored here for one-stop reproducibility. They are never
fine-tuned by RefineRank; please follow their original licenses and cite the
original works.1pip install "huggingface_hub[hf_transfer]" # hf_transfer optional, faster
2hf download linzher/RefineRank --local-dir . # restores the checkpoints/ tree
3
4git clone https://github.com/linzhe001/RefineRank
5cd RefineRank
6pip install -r requirements.txt
7# place the downloaded checkpoints/ next to interface.py, then:
8python interface.py predict # auto-discovers checkpoints/refinenet/1@inproceedings{jiang2026refinerank,
2 title = {RefineRank: Joint Box Refinement and Ranking for Surgical
3 Spatio-Temporal Grounding},
4 author = {Jiang, Linzhe and Huang, Jiayuan and Zhang, Changhao and
5 Jiang, Chunyang and Mao, Zhehua and
6 Garcia-Peraza-Herrera, Luis C. and Hoque, Mobarak I.},
7 booktitle = {ECCV Workshops (MedVidU)},
8 year = {2026}
9}