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

Vision-Language Models pre-trained on large-scale image-text datasets haveshown superior performance in downstream tasks such as image retrieval. Most ofthe images for pre-training are presented in the form of open domaincommon-sense visual elements. Differently, video covers in short video searchscenarios are presented as user-originated contents that provide importantvisual summaries of videos. In addition, a portion of the video covers comewith manually designed cover texts that provide semantic complements. In orderto fill in the gaps in short video cover data, we establish the firstlarge-scale cover-text benchmark for Chinese short video search scenarios.Specifically, we release two large-scale datasets CBVS-5M/10M to provide shortvideo covers, and the manual fine-labeling dataset CBVS-20K to provide realuser queries, which serves as an image-text benchmark test in the Chinese shortvideo search field. To integrate the semantics of cover text in the case ofmodality missing, we propose UniCLIP where cover texts play a guiding roleduring training, however are not relied upon by inference. Extensive evaluationon CBVS-20K demonstrates the excellent performance of our proposal. UniCLIP hasbeen deployed to Tencent's online video search systems with hundreds ofmillions of visits and achieved significant gains. The dataset and code areavailable at https://github.com/QQBrowserVideoSearch/CBVS-UniCLIP.

CBVS: A Large-Scale Chinese Image-Text Benchmark for Real-World Short Video Search Scenarios