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

Visible-infrared person re-identification (VI-ReID) aims to retrieve imagesof the same pedestrian from different modalities, where the challenges lie inthe significant modality discrepancy. To alleviate the modality gap, recentmethods generate intermediate images by GANs, grayscaling, or mixup strategies.However, these methods could ntroduce extra noise, and the semanticcorrespondence between the two modalities is not well learned. In this paper,we propose a Patch-Mixed Cross-Modality framework (PMCM), where two images ofthe same person from two modalities are split into patches and stitched into anew one for model learning. In this way, the modellearns to recognize a personthrough patches of different styles, and the modality semantic correspondenceis directly embodied. With the flexible image generation strategy, thepatch-mixed images freely adjust the ratio of different modality patches, whichcould further alleviate the modality imbalance problem. In addition, therelationship between identity centers among modalities is explored to furtherreduce the modality variance, and the global-to-part constraint is introducedto regularize representation learning of part features. On two VI-ReIDdatasets, we report new state-of-the-art performance with the proposed method.

Visible-Infrared Person Re-Identification via Patch-Mixed Cross-Modality Learning