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

Unsupervised visible-infrared person re-identification (USL-VI-ReID) aims tomatch pedestrian images of the same identity from different modalities withoutannotations. Existing works mainly focus on alleviating the modality gap byaligning instance-level features of the unlabeled samples. However, therelationships between cross-modality clusters are not well explored. To thisend, we propose a novel bilateral cluster matching-based learning framework toreduce the modality gap by matching cross-modality clusters. Specifically, wedesign a Many-to-many Bilateral Cross-Modality Cluster Matching (MBCCM)algorithm through optimizing the maximum matching problem in a bipartite graph.Then, the matched pairwise clusters utilize shared visible and infraredpseudo-labels during the model training. Under such a supervisory signal, aModality-Specific and Modality-Agnostic (MSMA) contrastive learning frameworkis proposed to align features jointly at a cluster-level. Meanwhile, thecross-modality Consistency Constraint (CC) is proposed to explicitly reduce thelarge modality discrepancy. Extensive experiments on the public SYSU-MM01 andRegDB datasets demonstrate the effectiveness of the proposed method, surpassingstate-of-the-art approaches by a large margin of 8.76% mAP on average.

Efficient Bilateral Cross-Modality Cluster Matching for Unsupervised Visible-Infrared Person ReID