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

Person re-identification (person Re-Id) aims to retrieve the pedestrianimages of a same person that captured by disjoint and non-overlapping cameras.Lots of researchers recently focuse on this hot issue and propose deep learningbased methods to enhance the recognition rate in a supervised or unsupervisedmanner. However, two limitations that cannot be ignored: firstly, compared withother image retrieval benchmarks, the size of existing person Re-Id datasetsare far from meeting the requirement, which cannot provide sufficientpedestrian samples for the training of deep model; secondly, the samples inexisting datasets do not have sufficient human motions or postures coverage toprovide more priori knowledges for learning. In this paper, we introduce anovel unsupervised pose augmentation cross-view person Re-Id scheme calledPAC-GAN to overcome these limitations. We firstly present the formal definitionof cross-view pose augmentation and then propose the framework of PAC-GAN thatis a novel conditional generative adversarial network (CGAN) based approach toimprove the performance of unsupervised corss-view person Re-Id. Specifically,The pose generation model in PAC-GAN called CPG-Net is to generate enoughquantity of pose-rich samples from original image and skeleton samples. Thepose augmentation dataset is produced by combining the synthesized pose-richsamples with the original samples, which is fed into the corss-view personRe-Id model named Cross-GAN. Besides, we use weight-sharing strategy in theCPG-Net to improve the quality of new generated samples. To the best of ourknowledge, we are the first try to enhance the unsupervised cross-view personRe-Id by pose augmentation, and the results of extensive experiments show thatthe proposed scheme can combat the state-of-the-arts.

PAC-GAN: An Effective Pose Augmentation Scheme for Unsupervised Cross-View Person Re-identification