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

The objective of this work is to localize the sound sources in visual scenes.Existing audio-visual works employ contrastive learning by assigningcorresponding audio-visual pairs from the same source as positives whilerandomly mismatched pairs as negatives. However, these negative pairs maycontain semantically matched audio-visual information. Thus, these semanticallycorrelated pairs, "hard positives", are mistakenly grouped as negatives. Ourkey contribution is showing that hard positives can give similar response mapsto the corresponding pairs. Our approach incorporates these hard positives byadding their response maps into a contrastive learning objective directly. Wedemonstrate the effectiveness of our approach on VGG-SS and SoundNet-Flickrtest sets, showing favorable performance to the state-of-the-art methods.

Learning Sound Localization Better From Semantically Similar Samples