In this paper, a patch-based nearest neighbor mining (PNNM) method is proposed to solve the unsupervised person re-identification problem. Specifically, a patch ...

Mar 1, 2023 · To address the unsupervised person re-ID, this paper proposes a patch-based nearest neighbor mining (PNNM) method. The proposed PNNM utilizes a ...

Unsupervised person re-identification by patch-based nearest neighbor mining ... To read the full-text of this research, you can request a copy directly from the ...

This work tackles a more realistic scenario and proposes two strategies to learn from large-scale unlabeled data, which outperforms the state-of-the-art ...

(b) One nearest neighbor from each reference image is returned by adjacency search for each patch on the left, and then N nearest neighbors from N reference ...

Dec 9, 2022 · Unsupervised person re-identification (re-ID) is still challenging due to the difficulty in learning discriminative features without ...

This is the first survey dedicated to unsupervised person Re- ID, as far as we know. Table 1 Summary of the main differences between the related person Re-ID ...

In this work, we develop a patch-based unsupervised learning framework (PAUL) for person re-id, and this framework is designed specially for learning discrimina ...

Sep 15, 2022 · The idea of unsupervised-learning person re-identification is usually to use a pseudo-label-generation approach to train the model directly ...

Awesome Person Re-identification (Person ReID) Awesome. This is a repository for organizing articles related to person re-identification. Most papers are linked ...