GazeFS：基于注视-头部历史的以目标为中心的注视轨迹预测与稳定
GazeFS: Target-Centered Gaze-Trajectory Forecasting and Stabilization from Gaze-Head History
- Beijing Forestry University（北京林业大学）
- Nanjing University of the Arts（南京艺术学院）
- Peking University（北京大学）
- Dalian University of Technology（大连理工大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
GazeFS模型以目标为中心预测注视轨迹并稳定注视，在30名参与者的实验中，其降低了目标误差等指标，提升了注视聚焦效果。
AI中文摘要：
以目标为中心的注视交互不仅需要抑制帧间波动，目标获取还会产生与任务对齐的注视-头部动态变化，同时注视轨迹可能保留持续的目标相对残差方向。我们将注视校正建模为在线以目标为中心的注视轨迹预测与稳定问题，并引入GazeFS，该模型可将可变长度的注视-头部历史映射到下一个目标中心方向和短时间范围的搜索/聚焦估计，推理时无需目标信息。在30名参与者的7960次获取回合中，搜索-聚焦差异在质量控制、起始排除和时长匹配下保持稳定；历史窗口相比当前端点提升了相位解码，但明确的任务进度仍是强控制因素。在30名参与者、五折分组留一协议（跨三个随机种子）下，与原始保持聚焦回合的偏差、回合内离散度和P90目标误差相比，分别降低了0.182度、0.257度和0.400度，参与者自助法95%置信区间不包含零；从空历史进行无端点重放保留了聚焦优势，原始网络的相位平衡准确率/AUPRC为0.925/0.993；坐标控制进一步表明，近期历史除了明确的进度元数据外还有额外贡献。因此，GazeFS可提升聚焦目标的中心性和经验残差收缩，同时将时间平滑性作为独立目标。
英文摘要：
Target-centered gaze interaction requires more than suppressing frame-to-frame fluctuations: target acquisition produces task-aligned changes in gaze-head dynamics, while a gaze trace may retain a persistent target-relative residual direction. We formulate gaze correction as online target-centered gaze-trajectory forecasting and stabilization and introduce GazeFS, which maps a variable-length gaze-head history to the next target-center direction and a short-horizon Search/Focus estimate without target information at inference. Across 7,960 acquisition episodes from 30 participants, Search-Focus differences remain stable under quality control, onset exclusion, and duration matching. History windows improve phase decoding over the current endpoint, but explicit task progress remains a strong control. Under the 30-participant, five-fold grouped out-of-fold protocol across three seeds, the reductions relative to raw hold in Focus episode bias, within-episode dispersion, and P90 target error are 0.182 degrees, 0.257 degrees, and 0.400 degrees, with participant-bootstrap 95% confidence intervals excluding zero. Endpoint-free replay from empty history preserves the Focus advantage and yields raw-network phase balanced accuracy/AUPRC of 0.925/0.993; coordinate controls further show that recent history contributes beyond explicit progress metadata. GazeFS therefore improves Focus target centering and empirical residual contraction while leaving temporal smoothness as a separate objective.
