Detecting Human-Object Interactions with Action Co-occurrence Priors
This addresses the issue of imbalanced data in HOI detection for computer vision applications, though it is incremental as it builds on existing methods with a novel prior-based approach.
The paper tackled the problem of low classification accuracy for rare human-object interaction (HOI) classes due to long-tailed training data by modeling action co-occurrence priors, resulting in state-of-the-art performance on HICO-Det and V-COCO benchmarks.
A common problem in human-object interaction (HOI) detection task 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 in rare classes. The utility of our approach is demonstrated experimentally, where the performance of our approach exceeds the state-of-the-art methods on both of the two leading HOI detection benchmark datasets, HICO-Det and V-COCO.