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

The re-identification (ReID) of individuals over a complex network of camerasis a challenging task, especially under real-world surveillance conditions.Several deep learning models have been proposed for visible-infrared (V-I)person ReID to recognize individuals from images captured using RGB and IRcameras. However, performance may decline considerably if RGB and IR imagescaptured at test time are corrupted (e.g., noise, blur, and weatherconditions). Although various data augmentation (DA) methods have been exploredto improve the generalization capacity, these are not adapted for V-I personReID. In this paper, a specialized DA strategy is proposed to address thismultimodal setting. Given both the V and I modalities, this strategy allows todiminish the impact of corruption on the accuracy of deep person ReID models.Corruption may be modality-specific, and an additional modality often providescomplementary information. Our multimodal DA strategy is designed specificallyto encourage modality collaboration and reinforce generalization capability.For instance, punctual masking of modalities forces the model to select theinformative modality. Local DA is also explored for advanced selection offeatures within and among modalities. The impact of training baseline fusionmodels for V-I person ReID using the proposed multimodal DA strategy isassessed on corrupted versions of the SYSU-MM01, RegDB, and ThermalWORLDdatasets in terms of complexity and efficiency. Results indicate that using ourstrategy provides V-I ReID models the ability to exploit both shared andindividual modality knowledge so they can outperform models trained with no orunimodal DA. GitHub code: https://github.com/art2611/ML-MDA.

Multimodal Data Augmentation for Visual-Infrared Person ReID with Corrupted Data