# DIRV: Dense Interaction Region Voting for End-to-End Human-Object Interaction Detection Source: [DIRV: Dense Interaction Region Voting for End-to-End Human-Object Interaction Detection]() Collection index: [llms.txt]() Data updated: 2026-01-04T04:08:08.348Z Authors: Hao-Shu Fang, Yichen Xie, Dian Shao, Cewu Lu Published: 2020-10-02T13:57:58.000Z ## Abstract Recent years, human-object interaction (HOI) detection has achieved impressive advances. However, conventional two-stage methods are usually slow in inference. On the other hand, existing one-stage methods mainly focus on the union regions of interactions, which introduce unnecessary visual information as disturbances to HOI detection. To tackle the problems above, we propose a novel one-stage HOI detection approach DIRV in this paper, based on a new concept called interaction region for the HOI problem. Unlike previous methods, our approach concentrates on the densely sampled interaction regions across different scales for each human-object pair, so as to capture the subtle visual features that is most essential to the interaction. Moreover, in order to compensate for the detection flaws of a single interaction region, we introduce a novel voting strategy that makes full use of those overlapped interaction regions in place of conventional Non-Maximal Suppression (NMS). Extensive experiments on two popular benchmarks: V-COCO and HICO-DET show that our approach outperforms existing state-of-the-arts by a large margin with the highest inference speed and lightest network architecture. We achieved 56.1 mAP on V-COCO without addtional input. Our code is publicly available at: https://github.com/MVIG-SJTU/DIRV ## 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 (Box/Mask mAP Scenarios)](): Human-Object Interaction Detection; V-COCO; Box mAP (Scenario 1): 56.1. - [Human-Object Interaction Detection on V-COCO (test)](): Human-Object Interaction Detection; V-COCO (test); AP (Role, Scenario 1): 56.1. - [Human-Object Interaction Detection on HICO-DET (test)](): Human-Object Interaction Detection; HICO-DET (test); mAP (full): 21.8. - [Human-Object Interaction Detection on HICO-DET](): Human-Object Interaction Detection; HICO-DET; mAP (Full): not recorded. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()