English(EN) GazeFlow: From Human Gaze Behavior to Generative Egocentric Gaze Prediction

GazeFlow框架使用条件流匹配预测自我中心注视

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-01 04:00

研究人员推出GazeFlow，一个旨在通过将注视建模为时间位置的联合分布来预测自我中心注视轨迹的新框架。该模型利用条件流匹配（CFM）来学习一个速度场，该速度场将高斯噪声样本转换为合理的注视轨迹。GazeFlow将此速度场与从视频中提取的视觉特征和自顶向下的任务信息相结合，在标准数据集上取得了最先进的性能，并展示了与人类注视动态的更好对齐。 AI

影响这项研究推进了自我中心注视预测，可能改进那些依赖于理解人类视觉注意力的应用。

排序理由该集群包含一篇详细介绍注视预测新框架的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 22 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍注视预测新框架的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, other; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CV TIER_1 English(EN) · Sheng Zhao, Weikai Lin, Yuhao Zhu · 2026-10-01 04:00

GazeFlow：从人类注视行为到生成式自我中心注视预测

arXiv:2609.38519v1 Announce Type: new Abstract: Egocentric gaze prediction enables many downstream applications but remains challenging, as human gaze is inherently stochastic. This stochasticity is constrained by structured temporal dynamics alternating between fixations and sac…

本文如何被排名

报道来源 [1]

GazeFlow：从人类注视行为到生成式自我中心注视预测

相关实体

相关话题