Automatic Signer Diarization - The Mover Is the Signer Approach

Author

Gebre, Binyam Gebrekidan ; Wittenburg, Peter ; Heskes, Tom

Author_Institution

Max Planck Inst. for Psycholinguistics, Nijmegen, Netherlands

fYear

2013

fDate

23-28 June 2013

Firstpage

283

Lastpage

287

Abstract

We present a vision-based method for signer diarization - the task of automatically determining "who signed when?" in a video. This task has similar motivations and applications as speaker diarization but has received little attention in the literature. In this paper, we motivate the problem and propose a method for solving it. The method is based on the hypothesis that signers make more movements than their interlocutors. Experiments on four videos (a total of 1.4 hours and each consisting of two signers) show the applicability of the method. The best diarization error rate (DER) obtained is 0.16.

Keywords

computer vision; gesture recognition; image motion analysis; object recognition; video signal processing; DER; automatic signer determination; automatic signer diarization; diarization error rate; interlocutor; speaker diarization; video; vision-based method; Assistive technology; Density estimation robust algorithm; Error analysis; Gesture recognition; Hidden Markov models; Manuals; Motion segmentation; signer diarization; speaker diarization;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Vision and Pattern Recognition Workshops (CVPRW), 2013 IEEE Conference on

Conference_Location

Portland, OR

Type

conf

DOI

10.1109/CVPRW.2013.49

Filename

6595888