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

Text-video retrieval, a prominent sub-field within the domain of multimodalinformation retrieval, has witnessed remarkable growth in recent years.However, existing methods assume video scenes are consistent with unbiaseddescriptions. These limitations fail to align with real-world scenarios sincedescriptions can be influenced by annotator biases, diverse writing styles, andvarying textual perspectives. To overcome the aforementioned problems, weintroduce $\texttt{WAVER}$, a cross-domain knowledge distillation framework viavision-language models through open-vocabulary knowledge designed to tackle thechallenge of handling different writing styles in video descriptions.$\texttt{WAVER}$ capitalizes on the open-vocabulary properties that lie inpre-trained vision-language models and employs an implicit knowledgedistillation approach to transfer text-based knowledge from a teacher model toa vision-based student. Empirical studies conducted across four standardbenchmark datasets, encompassing various settings, provide compelling evidencethat $\texttt{WAVER}$ can achieve state-of-the-art performance in text-videoretrieval task while handling writing-style variations. The code is availableat: https://github.com/Fsoft-AIC/WAVER

WAVER: Writing-style Agnostic Text-Video Retrieval via Distilling Vision-Language Models Through Open-Vocabulary Knowledge