English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Although unsupervised person re-identification (Re-ID) has drawn increasingresearch attention recently, it remains challenging to learn discriminativefeatures without annotations across disjoint camera views. In this paper, weaddress the unsupervised person Re-ID with a conceptually novel yet simpleframework, termed as Multi-label Learning guided self-paced Clustering (MLC).MLC mainly learns discriminative features with three crucial modules, namely amulti-scale network, a multi-label learning module, and a self-paced clusteringmodule. Specifically, the multi-scale network generates multi-granularityperson features in both global and local views. The multi-label learning moduleleverages a memory feature bank and assigns each image with a multi-labelvector based on the similarities between the image and feature bank. Aftermulti-label training for several epochs, the self-paced clustering joins intraining and assigns a pseudo label for each image. The benefits of our MLCcome from three aspects: i) the multi-scale person features for bettersimilarity measurement, ii) the multi-label assignment based on the wholedataset ensures that every image can be trained, and iii) the self-pacedclustering removes some noisy samples for better feature learning. Extensiveexperiments on three popular large-scale Re-ID benchmarks demonstrate that ourMLC outperforms previous state-of-the-art methods and significantly improvesthe performance of unsupervised person Re-ID.

Unsupervised Person Re-Identification with Multi-Label Learning Guided Self-Paced Clustering