AI Paper Atlas

Research map / Video / Video-language understanding

OphCLIP: Hierarchical Retrieval-Augmented Learning for Ophthalmic Surgical Video-Language Pretraining

Ming Hu, Kun Yuan, Yaling Shen, Feilong Tang, Xiaohao Xu, Lin Zhou, Wei Li, Ying Chen, Zhongxing Xu, Zelin Peng, Siyuan Yan, Vinkle Srivastav and 8 more

ICCV 2025 · Video › Video-language understanding · approach: Video LLMs with fine-grained understanding · 31 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
pretrain on OphVL dataset (ablation)CLIP RN50 · Cat-21 zero-shot phaseaccuracy: 13.3 -> 28.8Improved
pretrain on OphVL dataset (ablation)CLIP RN50 · Cataract-1K zero-shot phaseaccuracy: 6.1 -> 20.8Improved
add silent-video knowledge base and hierarchical retrieval (ablation)OphCLIP (Caption prompt) · Cat-21 zero-shot phaseaccuracy: 34.9 -> 39.9Improved
add silent-video knowledge base (ablation)OphCLIP (Caption prompt) · Cataract-1K zero-shot phaseaccuracy: 60.5 -> 61.3Improved
use Mix prompt (caption plus keywords) instead of Caption prompt (ablation)OphCLIP with KB · Cat-21 zero-shot phaseaccuracy: 39.9 -> 41.4Improved
use Mix prompt instead of Caption prompt (ablation)OphCLIP without KB · Cataract-1K zero-shot phaseaccuracy: 60.5 -> 55.9Hurt
add hierarchical retrieval-augmented pretraining over plain OphVL CLIPCLIP* · Cataract-1K zero-shot phaseaccuracy: 20.8 -> 62.8Improved
OphCLIP vs CLIP pretrained on OphVLCLIP* · CaDIS-F zero-shot instrumentFPR: 85.1 -> 54.1Improved
OphCLIP vs CLIP pretrained on OphVLCLIP* · Cat-21 linear probing 100% dataaccuracy: 59.4 -> 72.1Improved
OphCLIP vs CLIP pretrained on OphVLCLIP* · Cat-21 linear probing 10% dataaccuracy: 47.6 -> 59.5Improved
domain pretraining for instrument recognitionCLIP · Cataract-1K zero-shot instrumentFPR: 100.0 -> 45.1Improved
OphCLIP vs CLIP on instrument recognitionCLIP · Cataract-1K zero-shot instrumentmAP: 13.9 -> 21.2Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy