解决手术视频长时序问答难题，实现动态推理与精准定位
SurgLQA: Scalable Long-Horizon Surgical Video Question Answering
- 用时序凝聚机制构建紧凑的长程表征，保持时间细节
- 在长视频上提升推理能力，比基线高出12.3%准确率
- 适合临床实时决策支持，尤其对复杂手术流程分析
手术视频问答（VideoQA）为术中动态解读提供了前景广阔的范式，可实现临床环境中的实时决策支持与上下文感知检索。然而，现有方法主要局限于图像或短片段，难以建模长时程手术流程中的动态变化与因果依赖。为此，我们提出SurgLQA，一种面向可扩展手术推理的统一长时序视频问答框架。该框架引入忠实时间聚合（FTC），利用内在时间线索构建紧凑的长程表示，同时保留细粒度时间精度。此外，我们开发了时序锚定多策略扩展（TMS），一种自适应测试时推理范式，在时序锚定上下文中动态调整策略级推理能力。为促进系统评估，我们重构了长时间结肠镜检查视频问答基准Colon-LQA，并在Colon-LQA和REAL-Colon-VQA上进行大量实验。结果表明，该方法在长程推理中持续取得性能提升，具有时序锚定推理优势。代码已开源。
原文摘要 · Abstract (English)
Surgical Video Question Answering (VideoQA) provides a promising paradigm for dynamic intraoperative interpretation, enabling real-time decision support and context-aware retrieval in clinical environments. Nevertheless, existing approaches are predominantly restricted to images or short clips, limiting their ability to model long-range procedural dynamics and causal dependencies across extended surgical workflows. To address this challenge, we propose SurgLQA, a unified long-horizon VideoQA framework for scalable surgical reasoning. This framework incorporates Faithful Temporal Consolidation (FTC), which leverages intrinsic temporal cues to construct compact long-range representations while preserving fine-grained temporal fidelity. Further, we develop Temporally-Grounded Multi-Policy Scaling (TMS), an adaptive test-time inference paradigm that strategically adjusts policy-level reasoning capacity within temporally grounded contexts. To facilitate systematic evaluation, we restructured a long-duration colonoscopy VideoQA benchmark, Colon-LQA, and conducted extensive experiments on Colon-LQA and REAL-Colon-VQA. Experimental results demonstrate that our approach achieves consistent performance gains in long-range reasoning with temporally grounded inference. Code link: https://github.com/RascalGdd/SurgLQA.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。