paper-with-me

홈 › Papers

GroundedSurg: A Multi-Procedure Benchmark for Language-Conditioned Surgical Tool Segmentation

2026-03-01 · Tajamul Ashraf, Abrar Ul Riyaz, Wasif Tak, Tavaheed Tariq, Sonia Yadav, Moloud Abdar, Janibul Bashir arxiv

Clinically reliable perception of surgical scenes is essential for advancing intelligent, context-aware intraoperative assistance such as instrument handoff guidance, collision avoidance, and workflow-aware robotic support. Existing surgical tool benchmarks primarily evaluate category-level segmentation, requiring models to detect all instances of predefined instrument classes. However, real-world clinical decisions often require resolving references to a specific instrument instance based on its functional role, spatial relation, or anatomical interaction capabilities not captured by current evaluation paradigms. We introduce GroundedSurg, the first language-conditioned, instance-level surgical grounding benchmark. Each instance pairs a surgical image with a natural-language description targeting a single instrument, accompanied by structured spatial grounding annotations including bounding boxes and point-level anchors. The dataset spans ophthalmic, laparoscopic, robotic, and open procedures, encompassing diverse instrument types, imaging conditions, and operative complexities. By jointly evaluating linguistic reference resolution and pixel-level localization, GroundedSurg enables a systematic and realistic evaluation of vision-language models in clinically realistic multi-instrument scenes. Extensive experiments demonstrate substantial performance gaps across modern segmentation and VLMs, highlighting the urgent need for clinically grounded vision-language reasoning in surgical AI systems. Code and data are publicly available at https://github.com/gaash-lab/GroundedSurg

📄 PDF Abstract BibTeX arXiv:2603.01108

Code (0)

등록된 구현이 없습니다.

Tasks

Collision Avoidance

Similar Papers 제목 키워드 기반

AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?

2023-07-31 · Qi Zhao, Shijie Wang, Ce Zhang, Changcheng Fu 외

Can we better anticipate an actor's future actions (e.g. mix eggs) by knowing what commonly happens after his/her current action (e.g. crack eggs)? What if we also know the longer-term goal of the actor (e.g. making egg …

Action AnticipationcounterfactualLong Term Action Anticipation

Emotion-Conditioned Text Generation through Automatic Prompt Optimization

2023-08-09 · Yarik Menchaca Resendiz, Roman Klinger

Conditional natural language generation methods often require either expensive fine-tuning or training a large language model from scratch. Both are unlikely to lead to good results without a substantial amount of data a…

Conditional Text GenerationFew-Shot Text ClassificationLanguage ModelingLanguage Modelling+6

Swapped goal-conditioned offline reinforcement learning

2023-02-17 · Wenyan Yang, Huiling Wang, Dingding Cai, Joni Pajarinen 외

Offline goal-conditioned reinforcement learning (GCRL) can be challenging due to overfitting to the given dataset. To generalize agents' skills outside the given dataset, we propose a goal-swapping procedure that generat…

Offline RLreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Contrastive Energy Fields for Inference-Time Procedure Planning in Instructional Videos

2026-08-17 · Mohamed Afham, Christoph Reich, Oliver Hahn, Daniel Cremers 외 arxiv

Procedure planning seeks to estimate a sequence of actions to transition from an observed initial state to a given goal state. Current procedure planning approaches directly predict action sequences from latent represent…

Inference in conditioned dynamics through causality restoration

2022-10-18 · Alfredo Braunstein, Giovanni Catania, Luca Dall'Asta, Matteo Mariani 외

Computing observables from conditioned dynamics is typically computationally hard, because, although obtaining independent samples efficiently from the unconditioned dynamics is usually feasible, generally most of the sa…