真实的眼睛实现更快：用于高效自体学习的 gaze 稳定性和 pupil 新颖性
Real Eyes Realize Faster: Gaze Stability and Pupil Novelty for Efficient Egocentric Learning
AI总结：
该研究提出了一种双标准帧curator，利用 gaze 稳定性和 pupil 新颖性提高自体学习效率，验证了两种信号在不同任务中的不同作用。
摘要：
始终开启的自体摄像头越来越多地用于具身机器人、模仿学习和辅助AR的演示，但由此产生的视频流被冗余和低质量的帧所主导。在可穿戴设备的存储和电池限制下，选择哪些帧来保留与如何从这些帧中学习同样重要。我们观察到，现代眼动追踪头戴设备提供了一个连续的、无需训练的辅助通道，它分解为两个互补的轴：注视固定捕捉视觉稳定性（质量），而瞳孔反应捕捉与唤醒相关的时刻（新颖性）。我们将这一洞察转化为一个双标准帧 curator，首先通过 gaze 质量筛选帧，然后通过 pupil 导出的新颖性对幸存者进行排序。在视觉体验数据集（VEDB）上，10%预算下的curated帧在分类性能上与完整流相当，而naive信号融合一致破坏了两者贡献。该方法的益处是任务依赖性的：瞳孔排序提高了活动识别，而仅 gaze 选择已经主导了场景识别，证实了两个信号确实扮演着不同的角色。我们的方法不需要模型推断，并在捕获时间运行，为高效、始终开启的自体数据curator提供了一条路径。
英文摘要：
Always-on egocentric cameras are increasingly used as demonstrations for embodied robotics, imitation learning, and assistive AR, but the resulting video streams are dominated by redundant and low-quality frames. Under the storage and battery constraints of wearable devices, choosing which frames to keep is as important as how to learn from them. We observe that modern eye-tracking headsets provide a continuous, training-free side channel that decomposes into two complementary axes: gaze fixation captures visual stability (quality), while pupil response captures arousal-linked moments (novelty). We operationalize this insight as a Dual-Criterion Frame Curator that first gates frames by gaze quality and then ranks the survivors by pupil-derived novelty. On the Visual Experience Dataset (VEDB), curated frames at 10% budget match the classification performance of the full stream, and naive signal fusion consistently destroys both contributions. The benefit is task-dependent: pupil ranking improves activity recognition, while gaze-only selection already dominates for scene recognition, confirming that the two signals serve genuinely different roles. Our method requires no model inference and operates at capture time, offering a path toward efficient, always-on egocentric data curation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
