AI RESEARCH
End-to-End Shared Attention Estimation via Group Detection with Feedback Refinement
arXiv CS.CV
•
ArXi:2604.01714v1 Announce Type: new 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.