Joint Person Objectness and Repulsion for Person Search
Hantao Yao, Changsheng Xu

TL;DR
This paper introduces a novel OR similarity measure for person search that jointly considers objectness and repulsion to improve ranking accuracy and reduce distractor influence, leading to state-of-the-art results.
Contribution
It proposes a new OR similarity combining objectness and repulsion terms, enhancing person search performance over traditional methods.
Findings
Improves mAP from 92.32% to 93.23% on CUHK-SYSU
Increases mAP from 50.91% to 52.30% on PRW
Effectively reduces distractor similarity in person search
Abstract
Person search targets to search the probe person from the unconstrainted scene images, which can be treated as the combination of person detection and person matching. However, the existing methods based on the Detection-Matching framework ignore the person objectness and repulsion (OR) which are both beneficial to reduce the effect of distractor images. In this paper, we propose an OR similarity by jointly considering the objectness and repulsion information. Besides the traditional visual similarity term, the OR similarity also contains an objectness term and a repulsion term. The objectness term can reduce the similarity of distractor images that not contain a person and boost the performance of person search by improving the ranking of positive samples. Because the probe person has a different person ID with its \emph{neighbors}, the gallery images having a higher similarity with…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
MethodsSoftmax · Region Proposal Network · Convolution · RoIPool · Faster R-CNN
