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

Cross-lingual cross-modal retrieval has garnered increasing attentionrecently, which aims to achieve the alignment between vision and targetlanguage (V-T) without using any annotated V-T data pairs. Current methodsemploy machine translation (MT) to construct pseudo-parallel data pairs, whichare then used to learn a multi-lingual and multi-modal embedding space thataligns visual and target-language representations. However, the largeheterogeneous gap between vision and text, along with the noise present intarget language translations, poses significant challenges in effectivelyaligning their representations. To address these challenges, we propose ageneral framework, Cross-Lingual to Cross-Modal (CL2CM), which improves thealignment between vision and target language using cross-lingual transfer. Thisapproach allows us to fully leverage the merits of multi-lingual pre-trainedmodels (e.g., mBERT) and the benefits of the same modality structure, i.e.,smaller gap, to provide reliable and comprehensive semantic correspondence(knowledge) for the cross-modal network. We evaluate our proposed approach ontwo multilingual image-text datasets, Multi30K and MSCOCO, and one video-textdataset, VATEX. The results clearly demonstrate the effectiveness of ourproposed method and its high potential for large-scale retrieval.

CL2CM: Improving Cross-Lingual Cross-Modal Retrieval via Cross-Lingual Knowledge Transfer