← Search

Okan Köpüklü

2 accepted papers

2021

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

ICCV 2021poster

Successful active speaker detection requires a three-stage pipeline: (i) audio-visual encoding for all speakers in the clip, (ii) inter-speaker relation modeling between a reference speaker and the background speakers within each frame, and (iii) temporal modeling for the reference speaker. Each sta…

Cited by 62PDFcodeScholar