# How to Design a Three-Stage Architecture for Audio-Visual Active Speaker Detection in the Wild

> Research article (2021 IEEE/CVF International Conference on Computer Vision (ICCV), 2021) · cited 50× · AI/ML

**Wikidata**: [openalex:W3172472082](https://www.wikidata.org/wiki/openalex:W3172472082)  
**Source**: https://4ort.xyz/entity/how-to-design-a-three-stage-architecture-for-audio-visual-active-speaker-detection-in-the-wild