A compact representation of visual speech data using latent variables

A compact representation of visual speech data using latent variables

The problem of visual speech recognition involves the decoding of the video dynamics of a talking mouth in a high-dimensional visual space. In this paper, we propose a generative latent variable model to provide a compact representation of visual speech data. The model uses latent variables to separ...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 36(2014), 1 vom: 28. Jan., Seite 181-7
1. Verfasser: Zhou, Ziheng (VerfasserIn)
Weitere Verfasser: Hong, Xiaopeng, Zhao, Guoying, Pietikäinen, Matti
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2014
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article Research Support, Non-U.S. Gov't
LEADER 01000naa a22002652 4500
001 NLM232652031
003 DE-627
005 20231224093441.0
007 cr uuu---uuuuu
008 231224s2014 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2013.173  |2 doi 
028 5 2 |a pubmed24n0775.xml 
035 |a (DE-627)NLM232652031 
035 |a (NLM)24231875 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Zhou, Ziheng  |e verfasserin  |4 aut 
245 1 2 |a A compact representation of visual speech data using latent variables 
264 1 |c 2014 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Completed 30.06.2014 
500 |a Date Revised 15.11.2013 
500 |a published: Print 
500 |a Citation Status MEDLINE 
520 |a The problem of visual speech recognition involves the decoding of the video dynamics of a talking mouth in a high-dimensional visual space. In this paper, we propose a generative latent variable model to provide a compact representation of visual speech data. The model uses latent variables to separately represent the interspeaker variations of visual appearances and those caused by uttering within images, and incorporates the structural information of the visual data through placing priors of the latent variables along a curve embedded within a path graph 
650 4 |a Journal Article 
650 4 |a Research Support, Non-U.S. Gov't 
700 1 |a Hong, Xiaopeng  |e verfasserin  |4 aut 
700 1 |a Zhao, Guoying  |e verfasserin  |4 aut 
700 1 |a Pietikäinen, Matti  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 36(2014), 1 vom: 28. Jan., Seite 181-7  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:36  |g year:2014  |g number:1  |g day:28  |g month:01  |g pages:181-7 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2013.173  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 36  |j 2014  |e 1  |b 28  |c 01  |h 181-7