# ACP++: Action Co-occurrence Priors for Human-Object Interaction Detection Source: [ACP++: Action Co-occurrence Priors for Human-Object Interaction Detection]() Collection index: [llms.txt]() Data updated: 2026-01-04T03:33:52.784Z Authors: Dong-Jin Kim, Xiao Sun, Jinsoo Choi, Stephen Lin, In So Kweon Published: 2021-09-09T06:02:50.000Z ## Abstract A common problem in the task of human-object interaction (HOI) detection is that numerous HOI classes have only a small number of labeled examples, resulting in training sets with a long-tailed distribution. The lack of positive labels can lead to low classification accuracy for these classes. Towards addressing this issue, we observe that there exist natural correlations and anti-correlations among human-object interactions. In this paper, we model the correlations as action co-occurrence matrices and present techniques to learn these priors and leverage them for more effective training, especially on rare classes. The efficacy of our approach is demonstrated experimentally, where the performance of our approach consistently improves over the state-of-the-art methods on both of the two leading HOI detection benchmark datasets, HICO-Det and V-COCO. ## 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 HICO-DET (test)](): Human-Object Interaction Detection; HICO-DET (test); mAP (full): not recorded. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()