The reviewed record of science sign in
Pith

arxiv: 2007.08728 · v2 · pith:LNM3CFK2 · submitted 2020-07-17 · cs.CV · cs.LG

Detecting Human-Object Interactions with Action Co-occurrence Priors

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:LNM3CFK2record.jsonopen to challenge →

classification cs.CV cs.LG
keywords classeshuman-objectactionapproachco-occurrencecorrelationsdetectioninteractions
0
0 comments X
read the original abstract

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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.