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

We address the problem of cross-domain image retrieval, considering thefollowing practical application: given a user photo depicting a clothing image,our goal is to retrieve the same or attribute-similar clothing items fromonline shopping stores. This is a challenging problem due to the largediscrepancy between online shopping images, usually taken in ideallighting/pose/background conditions, and user photos captured in uncontrolledconditions. To address this problem, we propose a Dual Attribute-aware RankingNetwork (DARN) for retrieval feature learning. More specifically, DARN consistsof two sub-networks, one for each domain, whose retrieval featurerepresentations are driven by semantic attribute learning. We show that thisattribute-guided learning is a key factor for retrieval accuracy improvement.In addition, to further align with the nature of the retrieval problem, weimpose a triplet visual similarity constraint for learning to rank across thetwo sub-networks. Another contribution of our work is a large-scale datasetwhich makes the network learning feasible. We exploit customer review websitesto crawl a large set of online shopping images and corresponding offline userphotos with fine-grained clothing attributes, i.e., around 450,000 onlineshopping images and about 90,000 exact offline counterpart images of thoseonline ones. All these images are collected from real-world consumer websitesreflecting the diversity of the data modality, which makes this dataset uniqueand rare in the academic community. We extensively evaluate the retrievalperformance of networks in different configurations. The top-20 retrievalaccuracy is doubled when using the proposed DARN other than the current popularsolution using pre-trained CNN features only (0.570 vs. 0.268).

Cross-domain Image Retrieval with a Dual Attribute-aware Ranking Network