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

Audio visual segmentation (AVS) aims to segment the sounding objects for eachframe of a given video. To distinguish the sounding objects from silent ones,both audio-visual semantic correspondence and temporal interaction arerequired. The previous method applies multi-frame cross-modal attention toconduct pixel-level interactions between audio features and visual features ofmultiple frames simultaneously, which is both redundant and implicit. In thispaper, we propose an Audio-Queried Transformer architecture, AQFormer, where wedefine a set of object queries conditioned on audio information and associateeach of them to particular sounding objects. Explicit object-level semanticcorrespondence between audio and visual modalities is established by gatheringobject information from visual features with predefined audio queries. Besides,an Audio-Bridged Temporal Interaction module is proposed to exchange soundingobject-relevant information among multiple frames with the bridge of audiofeatures. Extensive experiments are conducted on two AVS benchmarks to showthat our method achieves state-of-the-art performances, especially 7.1% M_J and7.6% M_F gains on the MS3 setting.

Discovering Sounding Objects by Audio Queries for Audio Visual Segmentation