通过群体检测实现端到端共享注意力估计，更准地定位多人共同关注点。
End-to-End Shared Attention Estimation via Group Detection with Feedback Refinement
- 先基于个体注视热图和群体归属度生成初始注意力热图
- 再通过反馈迭代优化群体归属，提升注意力预测精度
- 适用于多人协作场景分析，适合视觉认知研究者
本文提出一种基于群体检测的端到端共享注意力估计方法。现有方法要么不检测实际关注群体，要么假设图像中仅存在单一共享注意力点，限制了其实际应用并影响性能。为此，我们采用两步流程：(i) 基于个体注视热图与群体归属标量，在群体推理中生成共享注意力热图；(ii) 利用初始注意力热图反馈优化初始群体归属，并最终输出共享注意力热图。实验表明，该方法在群体检测与共享注意力估计任务上均优于现有方法。额外分析验证了各组件的有效性。代码已开源：https://github.com/chihina/sagd-CVPRW2026。
原文摘要 · Abstract (English)
This paper proposes an end-to-end shared attention estimation method via group detection. Most previous methods estimate shared attention (SA) without detecting the actual group of people focusing on it, or assume that there is a single SA point in a given image. These issues limit the applicability of SA detection in practice and impact performance. To address them, we propose to simultaneously achieve group detection and shared attention estimation using a two step process: (i) the generation of SA heatmaps relying on individual gaze attention heatmaps and group membership scalars estimated in a group inference; (ii) a refinement of the initial group memberships allowing to account for the initial SA heatmaps, and the final prediction of the SA heatmap. Experiments demonstrate that our method outperforms other methods in group detection and shared attention estimation. Additional analyses validate the effectiveness of the proposed components. Code: https://github.com/chihina/sagd-CVPRW2026.
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。