LISTEN: a system for locating and tracking individual speakers

Collobert, M.; Féraud, Raphaël; Tourneur, G. Le; Bernier, Olivier; Viallet, J.E.; Mahieux, Y.; Collobert, D.

doi:10.1109/afgr.1996.557278

Cited by 24 publications

(9 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The gazing angle is computed based on the hairline (the border between an individuals hair and skin). Approaches which focus on single camera control include LISTEN [19], SAVI [60], LAFTER [139], Rits Eye [212], and the system of Morimoto and Flickner [135].…”

Section: Applicationsmentioning

confidence: 99%

Face Detection: A Survey

Hjelmås

Low

2001

Computer Vision and Image Understanding

953

426

View full text Add to dashboard Cite

Section: Applicationsmentioning

confidence: 99%

Face Detection: A Survey

Hjelmås

Low

2001

Computer Vision and Image Understanding

953

426

View full text Add to dashboard Cite

“…Both systems use similar preprocessing algorithms and multi-scale searching mechanism, except that Sung and Poggio's system uses multimodal Gaussian clustering method as classifier while Rowley and Kanade's system uses neural network as classifier. Similar systems available in the literature also include: Low [9]'s work that uses information theory, Collobert et al [5]'s and McKenna [10]'s works that use neural networks, Yang and Ahuja [20]'s work that uses factor analyzer and Osuna et al [14]'s work that uses support vector machine (SVM) as classifiers. They all reported close detection performance on some common testing pictures, for example the CMU testing database.…”

Section: Introductionmentioning

confidence: 96%

On face detection in the compressed domain

Luo

Eleftheriadis

2000

Proceedings of the Eighth ACM International Conference on Multimedia

View full text Add to dashboard Cite

We propose a fast face detection algorithm that works directly on the compressed DCT domain. Unlike the previous DCT domain processing designs that are mainly based on skin-color detection, our algorithm analyzes both color and texture information contained in the DCT parameters, therefore could generate more reliable detection results. Our texture analysis is mainly based on statistical model training and detection. A number of fundamental problems, e.g., block quantization, preprocessing in the DCT domain, and feature vector selection and classification in the DCT domain, are discussed.

show abstract

“…Individual color spaces used in prior skin detection methods include HSV ( [9,12,13]), a variant of Hue and Saturation ( [6]), Normalized RGB ( [1,7,16,17]), simple RGB ( [10,11]), YUV ( [4]), and transformations from CIE XYZ, including Farnsworth ( [3,15]) and CIE L*a*b* ( [2]). Five of these color spaces are compared in the current paper.…”

Section: Introductionmentioning

confidence: 99%