paper-with-me

Papers

Beyond Scanpaths: Graph-Based Gaze Simulation in Dynamic Scenes

2026-03-30 · Luke Palmer, Petar Palasek, Hazem Abdelkawy arxiv

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.

📄 PDF Abstract BibTeX arXiv:2603.28319

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

ScanGAN360: A Generative Model of Realistic Scanpaths for 360$^{\circ}$ Images

2021-03-25 · Daniel Martin, Ana Serrano, Alexander W. Bergman, Gordon Wetzstein 외

Understanding and modeling the dynamics of human gaze behavior in 360$^\circ$ environments is a key challenge in computer vision and virtual reality. Generative adversarial approaches could alleviate this challenge by ge…

Dynamic Time Warping

Scanpath Prediction on Information Visualisations

2021-12-04 · Yao Wang, Mihai Bâce, Andreas Bulling

We propose Unified Model of Saliency and Scanpaths (UMSS) -- a model that learns to predict visual saliency and scanpaths (i.e. sequences of eye fixations) on information visualisations. Although scanpaths provide rich i…

PredictionSaliency PredictionScanpath prediction

ST-DiffEye: Diffusion-based Continuous Gaze Generation via Joint Scanpath-Trajectory Modeling

2026-06-13 · Brian Nlong Zhao, Ozgur Kara, Junho Kim, James M. Rehg arxiv

We study the problem of human gaze modeling, which aims to generate the gaze patterns a viewer produces while observing a visual stimulus. Gaze is primarily captured through two modalities: continuous eye-tracking trajec…

Trajectory Modeling

Perceived Text Relevance Estimation Using Scanpaths and GNNs

2024-11-04 · International Conference on Multimodal Interaction 2024 11 · Abdulrahman Mohamed Selim, Omair Shahzad Bhatti, Michael Barz, Daniel Sonntag

A scanpath is an important concept in eye tracking that represents a person’s eye movements in a graph-like structure. Passive gaze-based interfaces, in which users do not consciously interact using their eyes, typically…

Synthesizing Human Gaze Feedback for Improved NLP Performance

2023-02-11 · Varun Khurana, Yaman Kumar Singla, Nora Hollenstein, Rajesh Kumar 외

Integrating human feedback in models can improve the performance of natural language processing (NLP) models. Feedback can be either explicit (e.g. ranking used in training language models) or implicit (e.g. using human …