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/

Zendy Plus

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

Zendy Tools

Zendy Open

In this paper, we re-examine the task of cross-modal clip-sentence retrieval,where the clip is part of a longer untrimmed video. When the clip is short orvisually ambiguous, knowledge of its local temporal context (i.e. surroundingvideo segments) can be used to improve the retrieval performance. We proposeContext Transformer (ConTra); an encoder architecture that models theinteraction between a video clip and its local temporal context in order toenhance its embedded representations. Importantly, we supervise the contexttransformer using contrastive losses in the cross-modal embedding space. Weexplore context transformers for video and text modalities. Resultsconsistently demonstrate improved performance on three datasets: YouCook2,EPIC-KITCHENS and a clip-sentence version of ActivityNet Captions. Exhaustiveablation studies and context analysis show the efficacy of the proposed method.

ConTra: (Con)text (Tra)nsformer for Cross-Modal Video Retrieval