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

Matching information across image and text modalities is a fundamentalchallenge for many applications that involve both vision and natural languageprocessing. The objective is to find efficient similarity metrics to comparethe similarity between visual and textual information. Existing approachesmainly match the local visual objects and the sentence words in a shared spacewith attention mechanisms. The matching performance is still limited becausethe similarity computation is based on simple comparisons of the matchingfeatures, ignoring the characteristics of their distribution in the data. Inthis paper, we address this limitation with an efficient learning objectivethat considers the discriminative feature distributions between the visualobjects and sentence words. Specifically, we propose a novel AdversarialDiscriminative Domain Regularization (ADDR) learning framework, beyond theparadigm metric learning objective, to construct a set of discriminative datadomains within each image-text pairs. Our approach can generally improve thelearning efficiency and the performance of existing metrics learning frameworksby regulating the distribution of the hidden space between the matching pairs.The experimental results show that this new approach significantly improves theoverall performance of several popular cross-modal matching techniques (SCAN,VSRN, BFAN) on the MS-COCO and Flickr30K benchmarks.

Beyond the Deep Metric Learning: Enhance the Cross-Modal Matching with Adversarial Discriminative Domain Regularization