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 paper is to perform visual sound separation: i) westudy visual sound separation on spectrograms of different temporalresolutions; ii) we propose a new light yet efficient three-stream frameworkV-SlowFast that operates on Visual frame, Slow spectrogram, and Fastspectrogram. The Slow spectrogram captures the coarse temporal resolution whilethe Fast spectrogram contains the fine-grained temporal resolution; iii) weintroduce two contrastive objectives to encourage the network to learndiscriminative visual features for separating sounds; iv) we propose anaudio-visual global attention module for audio and visual feature fusion; v)the introduced V-SlowFast model outperforms previous state-of-the-art insingle-frame based visual sound separation on small- and large-scale datasets:MUSIC-21, AVE, and VGG-Sound. We also propose a small V-SlowFast architecturevariant, which achieves 74.2% reduction in the number of model parameters and81.4% reduction in GMACs compared to the previous multi-stage models. Projectpage: https://ly-zhu.github.io/V-SlowFast

V-SlowFast Network for Efficient Visual Sound Separation