End-to-End Shared Attention Estimation via Group Detection with Feedback Refinement

TL;DR

This paper introduces an end-to-end method for shared attention estimation that simultaneously detects groups and refines attention heatmaps, improving accuracy over previous approaches.

Contribution

It presents a novel two-step process combining group detection with shared attention estimation, including a feedback refinement mechanism.

Findings

Outperforms existing methods in group detection accuracy.

Achieves superior shared attention estimation results.

Validates effectiveness through comprehensive experiments.

Abstract

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.