This paper applies the Attribute Enhancement Module (AEM), which utilizes Graph Convolutional Network to integrate the correlations between attributes, human ...

The contrastive learning controls the relative distance among the samples in the same cluster and different clusters to improve the quality of the extracted ...

Request PDF | On Aug 17, 2022, Ge Cao and others published Graph-based Attribute-aware Unsupervised Person Re-identification with Contrastive learning ...

In this work, we propose a novel unsupervised Re-ID approach which requires no labelled training data yet is able to capture discriminative information for ...

The task of person re-identification (ReID) is to match images of the same person over multiple non-overlapping camera views.

We design a novel adversarial contrastive feature learning (ACFL) framework for unsupervised person Re-ID, which can generate hard samples with high-confidence ...

Dec 19, 2021 · ABSTRACT. Unsupervised person re-identification (ReID) is a challenging task without data annotation to guide discriminative learning.

Awesome Unsupervised person re-identification is a computer vision task that involves identifying and matching individuals across different non-overlapping ...

This paper proposes a new method to effectively aggregate detailed person descriptions and visual features into a graph, namely Graph-based Person Signature ...

To optimize the model without human supervision, we propose two types of self-supervision: (1) contrastive learning. (Lc) and (2) clustering-based learning (Lcl) ...