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

Video moment retrieval aims to search the moment most relevant to a givenlanguage query. However, most existing methods in this community often requiretemporal boundary annotations which are expensive and time-consuming to label.Hence weakly supervised methods have been put forward recently by only usingcoarse video-level label. Despite effectiveness, these methods usually processmoment candidates independently, while ignoring a critical issue that thenatural temporal dependencies between candidates in different temporal scales.To cope with this issue, we propose a Multi-scale 2D Representation Learningmethod for weakly supervised video moment retrieval. Specifically, we firstconstruct a two-dimensional map for each temporal scale to capture the temporaldependencies between candidates. Two dimensions in this map indicate the startand end time points of these candidates. Then, we select top-K candidates fromeach scale-varied map with a learnable convolutional neural network. With anewly designed Moments Evaluation Module, we obtain the alignment scores of theselected candidates. At last, the similarity between captions and languagequery is served as supervision for further training the candidates' selector.Experiments on two benchmark datasets Charades-STA and ActivityNet Captionsdemonstrate that our approach achieves superior performance to state-of-the-artresults.

Multi-scale 2D Representation Learning for weakly-supervised moment retrieval