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

In this paper, we propose two techniques, namely joint modeling and dataaugmentation, to improve system performances for audio-visual sceneclassification (AVSC). We employ pre-trained networks trained only on imagedata sets to extract video embedding; whereas for audio embedding models, wedecide to train them from scratch. We explore different neural networkarchitectures for joint modeling to effectively combine the video and audiomodalities. Moreover, data augmentation strategies are investigated to increaseaudio-visual training set size. For the video modality the effectiveness ofseveral operations in RandAugment is verified. An audio-video joint mixupscheme is proposed to further improve AVSC performances. Evaluated on thedevelopment set of TAU Urban Audio Visual Scenes 2021, our final system canachieve the best accuracy of 94.2% among all single AVSC systems submitted toDCASE 2021 Task 1b.

A study on joint modeling and data augmentation of multi-modalities for audio-visual scene classification