超越扫描路径：动态场景中基于图的注视模拟
Beyond Scanpaths: Graph-Based Gaze Simulation in Dynamic Scenes
把注视轨迹当作自回归动力系统逐帧展开，并用异构图Transformer建模注视、交通目标与道路结构的关系，为动态场景中的注意力/显著性预测提供了可复用的时序建模范式。
原文依据 We instead formulate gaze modelling as an autoregressive dynamical system and explicitly unroll raw gaze trajectories over time
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论准确建模人类注意力对众多计算机视觉应用至关重要，尤其是在汽车安全领域。现有方法通常将注视压缩为显著性图或扫描路径，仅隐式地处理注视动态。本文转而将注视建模为自回归动力系统，并在注视历史与不断变化的环境条件下，显式地随时间展开原始注视轨迹。驾驶场景被表示为以注视为中心的图，并由亲和关系 Transformer（ART）处理；ART 是一种异构图 Transformer，用于建模驾驶员注视、交通目标与道路结构之间的交互。我们进一步引入目标密度网络（ODN）来预测下一步的注视分布，从而刻画复杂环境中注意力转移的随机性与以目标为中心的特性。我们还发布了 Focus100，这是一个新的数据集，包含 30 名参与者观看第一人称驾驶视频时的原始注视数据。我们的统一方法直接在原始注视数据上训练，无需注视点过滤，能够生成比现有注意力模型更自然的注视轨迹、扫描路径动态和显著性图，为动态环境中人类注意力的时序建模提供了有价值的见解。
英文原文摘要 1266 字符
Accurately modelling human attention is essential for numerous computer vision applications, particularly in the domain of automotive safety. Existing methods typically collapse gaze into saliency maps or scanpaths, treating gaze dynamics only implicitly. We instead formulate gaze modelling as an autoregressive dynamical system and explicitly unroll raw gaze trajectories over time, conditioned on both gaze history and the evolving environment. Driving scenes are represented as gaze-centric graphs processed by the Affinity Relation Transformer (ART), a heterogeneous graph transformer that models interactions between driver gaze, traffic objects, and road structure. We further introduce the Object Density Network (ODN) to predict next-step gaze distributions, capturing the stochastic and object-centric nature of attentional shifts in complex environments. We also release Focus100, a new dataset of raw gaze data from 30 participants viewing egocentric driving footage. Trained directly on raw gaze, without fixation filtering, our unified approach produces more natural gaze trajectories, scanpath dynamics, and saliency maps than existing attention models, offering valuable insights for the temporal modelling of human attention in dynamic environments.