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

Listeners use short interjections, so-called backchannels, to signifyattention or express agreement. The automatic analysis of this behavior is ofkey importance for human conversation analysis and interactive conversationalagents. Current state-of-the-art approaches for backchannel analysis fromvisual behavior make use of two types of features: features based on body poseand features based on facial behavior. At the same time, transformer neuralnetworks have been established as an effective means to fuse input fromdifferent data sources, but they have not yet been applied to backchannelanalysis. In this work, we conduct a comprehensive evaluation of multi-modaltransformer architectures for automatic backchannel analysis based on pose andfacial information. We address both the detection of backchannels as well asthe task of estimating the agreement expressed in a backchannel. In evaluationson the MultiMediate'22 backchannel detection challenge, we reach 66.4% accuracywith a one-layer transformer architecture, outperforming the previous state ofthe art. With a two-layer transformer architecture, we furthermore set a newstate of the art (0.0604 MSE) on the task of estimating the amount of agreementexpressed in a backchannel.

Backchannel Detection and Agreement Estimation from Video with Transformer Networks