A Study of Failure Modes in Two-Stage Human-Object Interaction Detection

ArXi:2604.13448v1 Announce Type: cross Human-object interaction (HOI) detection aims to detect interactions between humans and objects in images. While recent advances have improved performance on existing benchmarks, their evaluations mainly focus on overall prediction accuracy and provide limited insight into the underlying causes of model failures. In particular, modern models often struggle in complex scenes involving multiple people and rare interaction combinations.