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

Recognizing who is speaking in a crowded scene is a key challenge towards theunderstanding of the social interactions going on within. Detecting speakingstatus from body movement alone opens the door for the analysis of socialscenes in which personal audio is not obtainable. Video and wearable sensorsmake it possible recognize speaking in an unobtrusive, privacy-preserving way.When considering the video modality, in action recognition problems, a boundingbox is traditionally used to localize and segment out the target subject, tothen recognize the action taking place within it. However, cross-contamination,occlusion, and the articulated nature of the human body, make this approachchallenging in a crowded scene. Here, we leverage articulated body poses forsubject localization and in the subsequent speech detection stage. We show thatthe selection of local features around pose keypoints has a positive effect ongeneralization performance while also significantly reducing the number oflocal features considered, making for a more efficient method. Using twoin-the-wild datasets with different viewpoints of subjects, we investigate therole of cross-contamination in this effect. We additionally make use ofacceleration measured through wearable sensors for the same task, and present amultimodal approach combining both methods.

No-audio speaking status detection in crowded settings via visual pose-based filtering and wearable acceleration