用神经点过程建模注视的时间与空间动态，提升眼动预测精度。
TPP-Gaze: Modelling Gaze Dynamics in Space and Time with Neural Temporal Point Processes
- 基于神经点过程联合建模注视位置与持续时间
- 在5个公开数据集上优于现有最优方法
- 适合关注眼动时序建模的研究者
注意力引导我们的视线聚焦场景中的合适位置，并根据当前认知需求保持注视一段时间，随后转向下一个目标。因此，注视行为本质上是一个时间过程。现有计算模型在预测观察者的视觉扫描路径（看哪里）方面取得显著进展，但往往忽视了注意力动态的时间特性（何时）。本文提出TPP-Gaze，一种基于神经时间点过程（Neural Temporal Point Process, TPP）的新颖且原理清晰的方法，可联合学习注视位置与持续时间的时序动态，融合深度学习与点过程理论。我们在五个公开可用数据集上进行了大量实验，结果表明该模型在整体性能上优于现有最先进方法。源代码和训练模型已公开：https://github.com/phuselab/tppgaze。
原文摘要 · Abstract (English)
Attention guides our gaze to fixate the proper location of the scene and holds it in that location for the deserved amount of time given current processing demands, before shifting to the next one. As such, gaze deployment crucially is a temporal process. Existing computational models have made significant strides in predicting spatial aspects of observer's visual scanpaths (where to look), while often putting on the background the temporal facet of attention dynamics (when). In this paper we present TPP-Gaze, a novel and principled approach to model scanpath dynamics based on Neural Temporal Point Process (TPP), that jointly learns the temporal dynamics of fixations position and duration, integrating deep learning methodologies with point process theory. We conduct extensive experiments across five publicly available datasets. Our results show the overall superior performance of the proposed model compared to state-of-the-art approaches. Source code and trained models are publicly available at: https://github.com/phuselab/tppgaze.
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。