Aug 25, 2020 · Generally speaking, person re-identification (re-ID) involves matching people across non-overlapping camera views. This process plays an ...

Accordingly, we propose a novel background-transferable per- son re-identification framework that greatly enhances the cross- domain re-ID model in this paper.

First, we propose a joint learning framework for unsupervised cross-domain person re-id to disentangle id-related/unrelated factors so that adaptation can be ...

Unsupervised object Re-ID aims to learn discriminative identity features from a fully unlabeled dataset to solve the open-class re-identification problem.

In this paper, we present DRANet, a network architecture that disentangles image representations and transfers the visual attributes in a latent space for  ...

This is a repository for organizing articles related to person re-identification. Most papers are linked to the pdf address provided by "arXiv" or ...

Oct 9, 2023 · This paper proposes a weakly supervised cross-domain person re-identification (Re-ID) method based on small sample data.

Jul 30, 2020 · In this paper, we introduce a novel unsupervised disentanglement generative adversarial network (UD-GAN) to address the domain adaptation issue ...

Mar 25, 2021 · Unsupervised domain adaptive (UDA) person re-identification (ReID) aims to transfer the knowledge from the labeled source domain to the ...

3 hours ago · The task of unsupervised person re-identification (Re-ID) is to transfer the knowledge learned in the source domain with no labels to the ...