ACP++: Action Co-occurrence Priors for Human-Object Interaction Detection

TL;DR

This paper introduces ACP++, a method that models action co-occurrence priors to improve human-object interaction detection, especially for rare classes, resulting in better performance on standard benchmarks.

Contribution

The paper proposes a novel approach to incorporate action co-occurrence priors into HOI detection, addressing class imbalance and improving accuracy for rare interactions.

Findings

Consistent performance improvements over state-of-the-art methods.

Effective modeling of action correlations enhances detection accuracy.

Demonstrated improvements on HICO-Det and V-COCO datasets.

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.