SurgNarrator: A Generative Retrieval Framework for Surgical Video Understanding

• URL: http://arxiv.org/abs/2608.04676v1
• Date: Wed, 05 Aug 2026 10:39:19 GMT
• Title: SurgNarrator: A Generative Retrieval Framework for Surgical Video Understanding
• Abstract summary: We propose SurgNarrator, a new generative retrieval framework tailored for surgical video understanding.<n>We construct a well-curated surgery-centric vocabulary from surgical captions to define a clinically meaningful retrieval space.<n>During inference, a hierarchical, procedure-aware retrieval strategy narrows the search space to the relevant procedure type, delivering fast and effective responses.
• Score: 35.05885138023876
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Surgical procedures unfold as structured and recurring clinical events, whose real-time understanding via intraoperative surgical videos is critical for intraoperative decision-making and support. However, existing video understanding methods force a trade-off: autoregressive video-language models support comprehensive reasoning but are not practical for time-sensitive clinical applications, whereas contrastive models offer low latency but struggle with complex scene understanding. Recently, generative retrieval has been explored for general-domain video understanding, but transferring it to surgery is not trivial because near-identical visual appearances may indicate semantically distinct events, and the terminology involved is highly surgery-specific. To this end, we propose SurgNarrator, a new generative retrieval framework tailored for surgical video understanding. We construct a well-curated surgery-centric vocabulary from surgical captions to define a clinically meaningful retrieval space. We then adapt the pre-trained Qwen3-VL-Embedding-8B to learn discriminative clinical representations with a temporally-aware contrastive objective. During inference, a hierarchical, procedure-aware retrieval strategy narrows the search space to the relevant procedure type, delivering fast and effective responses. Our method is comprehensively evaluated on twelve benchmarks in a zero-shot setting and achieves consistent performance gains over state-of-the-art baselines, while reducing output-stage latency by more than two orders of magnitude compared with the generative baseline.

Related papers

• HyperVLP: Enhancing Hierarchical Surgical Video-Language Pre-training in Hyperbolic Space [50.603248889968306]
  We propose a hyperbolic surgical video-language pre-training framework that explicitly preserves the hierarchical structure.<n>Experiments on multiple surgical benchmarks show consistent gains in zero- and few-shot phase recognition.
  arXiv  Detail & Related papers  (2026-06-30T07:21:06Z)
• SurgTEMP: Temporal-Aware Surgical Video Question Answering with Text-guided Visual Memory for Laparoscopic Cholecystectomy [12.553409376394162]
  SurgTEMP is a multimodal visual memory framework for surgical video question answering.<n>We introduce CholeVidQA-32K, a surgical video question answering dataset comprising 32K open-ended QA pairs and 3,855 video segments.<n>In comprehensive evaluations against state-of-the-art open-source multimodal and video LLMs (fine-tuned and zero-shot), SurgTEMP achieves substantial performance improvements.
  arXiv  Detail & Related papers  (2026-03-31T16:27:46Z)
• Where It Moves, It Matters: Referring Surgical Instrument Segmentation via Motion [54.359489807885616]
  SurgRef is a motion-guided framework that grounds free-form language expressions in instrument motion, rather than what they look like.<n>To train and evaluate SurgRef, we present Ref-IMotion, a diverse, multi-institutional video dataset with densetemporal masks and rich motion expressions.
  arXiv  Detail & Related papers  (2026-01-18T02:14:08Z)
• Surgical Video Understanding with Label Interpolation [3.880707330499936]
  Robot-assisted surgery (RAS) has become a critical paradigm in modern surgery, promoting patient recovery and reducing the burden on surgeons.<n>Previous studies have predominantly focused on single-task approaches, but real surgical scenes involve complex temporal dynamics and diverse instrument interactions.<n>We propose a novel framework that combines optical flow-based segmentation label with multi-task learning.
  arXiv  Detail & Related papers  (2025-09-23T08:49:07Z)
• Large-scale Self-supervised Video Foundation Model for Intelligent Surgery [27.418249899272155]
  We introduce the first video-level surgical pre-training framework that enables jointtemporal representation learning from large-scale surgical video data.<n>We propose SurgVISTA, a reconstruction-based pre-training method that captures spatial structures and intricate temporal dynamics.<n>In experiments, SurgVISTA consistently outperforms both natural- and surgical-domain pre-trained models.
  arXiv  Detail & Related papers  (2025-06-03T09:42:54Z)
• Surgeons vs. Computer Vision: A comparative analysis on surgical phase recognition capabilities [65.66373425605278]
  Automated Surgical Phase Recognition (SPR) uses Artificial Intelligence (AI) to segment the surgical workflow into its key events.<n>Previous research has focused on short and linear surgical procedures and has not explored if temporal context influences experts' ability to better classify surgical phases.<n>This research addresses these gaps, focusing on Robot-Assisted Partial Nephrectomy (RAPN) as a highly non-linear procedure.
  arXiv  Detail & Related papers  (2025-04-26T15:37:22Z)
• OphCLIP: Hierarchical Retrieval-Augmented Learning for Ophthalmic Surgical Video-Language Pretraining [60.75854609803651]
  OphCLIP is a hierarchical retrieval-augmented vision-language pretraining framework for ophthalmic surgical workflow understanding.<n>OphCLIP learns both fine-grained and long-term visual representations by aligning short video clips with detailed narrative descriptions and full videos with structured titles.<n>Our OphCLIP also designs a retrieval-augmented pretraining framework to leverage the underexplored large-scale silent surgical procedure videos.
  arXiv  Detail & Related papers  (2024-11-23T02:53:08Z)
• Procedure-Aware Surgical Video-language Pretraining with Hierarchical Knowledge Augmentation [51.222684687924215]
  Surgical video-language pretraining faces unique challenges due to the knowledge domain gap and the scarcity of multi-modal data.<n>We propose a hierarchical knowledge augmentation approach and a novel Procedure-Encoded Surgical Knowledge-Augmented Video-Language Pretraining framework to tackle these issues.
  arXiv  Detail & Related papers  (2024-09-30T22:21:05Z)
• Action Recognition in Video Recordings from Gynecologic Laparoscopy [4.002010889177872]
  Action recognition is a prerequisite for many applications in laparoscopic video analysis. In this study, we design and evaluate a CNN-RNN architecture as well as a customized training-inference framework.
  arXiv  Detail & Related papers  (2023-11-30T16:15:46Z)
• GLSFormer : Gated - Long, Short Sequence Transformer for Step Recognition in Surgical Videos [57.93194315839009]
  We propose a vision transformer-based approach to learn temporal features directly from sequence-level patches. We extensively evaluate our approach on two cataract surgery video datasets, Cataract-101 and D99, and demonstrate superior performance compared to various state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-07-20T17:57:04Z)
• Relevance Detection in Cataract Surgery Videos by Spatio-Temporal Action Localization [7.235239641693831]
  In cataract surgery, the operation is performed with the help of a microscope. Since the microscope enables watching real-time surgery by up to two people only, a major part of surgical training is conducted using the recorded videos. To optimize the training procedure with the video content, the surgeons require an automatic relevance detection approach. In this paper, a three- module framework is proposed to detect and classify the relevant phase segments in cataract videos.
  arXiv  Detail & Related papers  (2021-04-29T12:01:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.