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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Group re-identification (G-ReID) is an important yet less-studied task. Itschallenges not only lie in appearance changes of individuals which have beenwell-investigated in general person re-identification (ReID), but also derivefrom group layout and membership changes. So the key task of G-ReID is to learnrepresentations robust to such changes. To address this issue, we propose aTransferred Single and Couple Representation Learning Network (TSCN). Itsmerits are two aspects: 1) Due to the lack of labelled training samples,existing G-ReID methods mainly rely on unsatisfactory hand-crafted features. Togain the superiority of deep learning models, we treat a group as multiplepersons and transfer the domain of a labeled ReID dataset to a G-ReID targetdataset style to learn single representations. 2) Taking into account theneighborhood relationship in a group, we further propose learning a novelcouple representation between two group members, that achieves morediscriminative power in G-ReID tasks. In addition, an unsupervised weightlearning method is exploited to adaptively fuse the results of different viewstogether according to result patterns. Extensive experimental resultsdemonstrate the effectiveness of our approach that significantly outperformsstate-of-the-art methods by 11.7\% CMC-1 on the Road Group dataset and by39.0\% CMC-1 on the DukeMCMT dataset.

DotSCN: Group Re-identification via Domain-Transferred Single and Couple Representation Learning