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

Multilingual text-video retrieval methods have improved significantly inrecent years, but the performance for other languages lags behind English. Wepropose a Cross-Lingual Cross-Modal Knowledge Distillation method to improvemultilingual text-video retrieval. Inspired by the fact that English text-videoretrieval outperforms other languages, we train a student model using inputtext in different languages to match the cross-modal predictions from teachermodels using input text in English. We propose a cross entropy based objectivewhich forces the distribution over the student's text-video similarity scoresto be similar to those of the teacher models. We introduce a new multilingualvideo dataset, Multi-YouCook2, by translating the English captions in theYouCook2 video dataset to 8 other languages. Our method improves multilingualtext-video retrieval performance on Multi-YouCook2 and several other datasetssuch as Multi-MSRVTT and VATEX. We also conducted an analysis on theeffectiveness of different multilingual text models as teachers. The code,models, and dataset are available at https://github.com/roudimit/c2kd.

C2KD: Cross-Lingual Cross-Modal Knowledge Distillation for Multilingual Text-Video Retrieval