# Detecting Visual Relationships Using Box Attention Source: [Detecting Visual Relationships Using Box Attention]() Collection index: [llms.txt]() Data updated: 2025-10-27T05:58:47.394Z Authors: Alexander Kolesnikov, Alina Kuznetsova, Christoph H. Lampert, Vittorio Ferrari Published: 2018-07-05T18:24:56.000Z ## Abstract We propose a new model for detecting visual relationships, such as "person riding motorcycle" or "bottle on table". This task is an important step towards comprehensive structured image understanding, going beyond detecting individual objects. Our main novelty is a Box Attention mechanism that allows to model pairwise interactions between objects using standard object detection pipelines. The resulting model is conceptually clean, expressive and relies on well-justified training and prediction procedures. Moreover, unlike previously proposed approaches, our model does not introduce any additional complex components or hyperparameters on top of those already required by the underlying detection model. We conduct an experimental evaluation on three challenging datasets, V-COCO, Visual Relationships and Open Images, demonstrating strong quantitative and qualitative results. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Human-Object Interaction Detection on V-COCO (AP\_role)](): Human-Object Interaction Detection; V-COCO; AP (Role): 43.6. - [Human-Object Interaction Detection on V-COCO (test)](): Human-Object Interaction Detection; V-COCO (test); AP (Role, Scenario 1): 43.6. ## Original sources and implementation [Original paper]() [PDF]()