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

Pre-trained vision and language models such as CLIP have witnessed remarkablesuccess in connecting images and texts with a primary focus on English texts.Despite recent efforts to extend CLIP to support other languages, disparitiesin performance among different languages have been observed due to unevenresource availability. Additionally, current cross-lingual transfer methods ofthose pre-trained models would consume excessive resources for a large numberof languages. Therefore, we propose a new parameter-efficient cross-lingualtransfer learning framework that utilizes a translation-based alignment methodto mitigate multilingual disparities and explores parameter-efficientfine-tuning methods for parameter-efficient cross-lingual transfer. Extensiveexperiments on XTD and Multi30K datasets, covering 11 languages underzero-shot, few-shot, and full-dataset learning scenarios, show that ourframework significantly reduces the multilingual disparities among languagesand improves cross-lingual transfer results, especially in low-resourcescenarios, while only keeping and fine-tuning an extremely small number ofparameters compared to the full model (e.g., Our framework only requires 0.16\%additional parameters of a full-model for each language in the few-shotlearning scenario). The codes are available at\url{https://github.com/eric-ai-lab/PECTVLM}. The codes are available at\url{https://github.com/eric-ai-lab/PECTVLM}.

Parameter-Efficient Cross-lingual Transfer of Vision and Language Models via Translation-based Alignment