聚焦到感知表征学习：面向内窥镜视频分析的认知启发分层框架
Focus-to-Perceive Representation Learning: A Cognition-Inspired Hierarchical Framework for Endoscopic Video Analysis
针对内窥镜视频中静态病灶语义被运动偏置淹没的问题，提出教师先验自适应掩码加多视图稀疏采样来聚焦帧内病灶区域，再用跨视图掩码特征补全与注意力引导时序预测建模帧间演化；这套「先聚焦静态语义、再感知时序演化」的分层自监督预训练范式可直接迁移到其他标注稀缺、语义静态性强的专业视频域（如超声、手术、遥感时序）。
原文依据 it begins by capturing static semantics via teacher-prior adaptive masking (TPAM) combined with multi-view sparse sampling
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论内窥镜视频分析对胃肠道早期筛查至关重要，但仍受限于高质量标注的稀缺。尽管自监督视频预训练展现出潜力，但面向自然视频设计的现有方法偏重稠密时空建模并存在运动偏置，忽视了临床决策所依赖的静态、结构化语义。为应对这一挑战，我们提出聚焦到感知表征学习（FPRL），一个模拟临床检查过程的认知启发分层框架。FPRL 首先聚焦于帧内以病灶为中心的区域以学习静态语义，随后感知这些区域在帧间的演化以建模上下文语义。为此，FPRL 采用分层语义建模机制，显式区分并协同学习这两类语义。具体而言，该方法首先通过教师先验自适应掩码（TPAM）结合多视图稀疏采样来捕获静态语义。这一方式缓解了冗余的时序依赖，并使模型能够聚焦于与病灶相关的局部语义。随后，通过跨视图掩码特征补全（CVMFC）与注意力引导时序预测（AGTP）导出上下文语义。这些过程建立跨视图对应关系并有效建模结构化的帧间演化，从而在保持全局上下文完整性的同时强化时序语义连续性。在 11 个内窥镜视频数据集上的大量实验表明，FPRL 在多种下游任务上均取得优越性能，证明了其在内窥镜视频表征学习中的有效性。代码已发布于 https://github.com/MLMIP/FPRL。
英文原文摘要 1758 字符
Endoscopic video analysis is essential for early gastrointestinal screening but remains hindered by limited high-quality annotations. While self-supervised video pre-training shows promise, existing methods developed for natural videos prioritize dense spatio-temporal modeling and exhibit motion bias, overlooking the static, structured semantics critical to clinical decision-making. To address this challenge, we propose Focus-to-Perceive Representation Learning (FPRL), a cognition-inspired hierarchical framework that emulates clinical examination. FPRL first focuses on intra-frame lesion-centric regions to learn static semantics, and then perceives their evolution across frames to model contextual semantics. To achieve this, FPRL employs a hierarchical semantic modeling mechanism that explicitly distinguishes and collaboratively learns both types of semantics. Specifically, it begins by capturing static semantics via teacher-prior adaptive masking (TPAM) combined with multi-view sparse sampling. This approach mitigates redundant temporal dependencies and enables the model to concentrate on lesion-related local semantics. Following this, contextual semantics are derived through cross-view masked feature completion (CVMFC) and attention-guided temporal prediction (AGTP). These processes establish cross-view correspondences and effectively model structured inter-frame evolution, thereby reinforcing temporal semantic continuity while preserving global contextual integrity. Extensive experiments on 11 endoscopic video datasets show that FPRL achieves superior performance across diverse downstream tasks, demonstrating its effectiveness in endoscopic video representation learning. The code is available at https://github.com/MLMIP/FPRL.