Pith. sign in

REVIEW

Detecting Human-Object Interactions with Action Co-occurrence Priors

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

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

classification cs.CVcs.LG
keywords classeshuman-objectactionapproachco-occurrencecorrelationsdetectioninteractions
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
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.

Discussion (0). Sign in to comment.

Pith tools