Výsledky vyhledávání

Akademický článek

Expectation-maximisation for speech source separation using convolutive transfer function

Autor: Xiaofei Li, Laurent Girin, Radu Horaud

Publikováno v: CAAI Transactions on Intelligence Technology (2019)

This study addresses the problem of under-determined speech source separation from multichannel microphone signals, i.e. the convolutive mixtures of multiple sources. The time-domain signals are first transformed to the short-time Fourier transform (

Externí odkaz: https://doaj.org/article/4df52cc4673c4bee983dfcea439ccb4e

Zobrazit plný text záznamu

Expression-preserving face frontalization improves visually assisted speech processing

Autor: Zhiqi Kang, Mostafa Sadeghi, Radu Horaud, Xavier Alameda-Pineda

Publikováno v: International Journal of Computer Vision
International Journal of Computer Vision, 2023, 131 (5), pp.1122-1140. ⟨10.1007/s11263-022-01742-1⟩
International Journal of Computer Vision, 2023, ⟨10.1007/s11263-022-01742-1⟩

Face frontalization consists of synthesizing a frontally-viewed face from an arbitrarily-viewed one. The main contribution of this paper is a frontalization methodology that preserves non-rigid facial deformations in order to boost the performance of

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3c40086506c136bd4980819f02ce1113
https://hal.science/hal-03902610v2/document

Zobrazit plný text záznamu

Robust Face Frontalization For Visual Speech Recognition

Autor: Radu Horaud, Zhiqi Kang, Mostafa Sadeghi

Publikováno v: ICCV 2021-International Conference on Computer Vision Workshops
ICCV 2021-International Conference on Computer Vision Workshops, IEEE, Oct 2021, Montreal-Virtual, Canada. pp.1-16
ICCVW 2021-International Conference on Computer Vision Workshops
ICCVW 2021-International Conference on Computer Vision Workshops, IEEE, Oct 2021, Montreal-Virtual, Canada. pp.2485-2495, ⟨10.1109/ICCVW54120.2021.00281⟩
International Conference on Computer Vision Workshops
International Conference on Computer Vision Workshops, IEEE, Oct 2021, Montreal-Virtual, Canada

International audience; Face frontalization consists of synthesizing a frontallyviewed face from an arbitrarily-viewed one. The main contribution of this paper is a robust frontalization method that preserves non-rigid facial deformations, i.e. expre

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e51e6eb84bd450e894cf6d9e1edd1993
https://hal.inria.fr/hal-03326002v3/file/Kang-ICCV21W-HAL.pdf

Zobrazit plný text záznamu

Tracking Multiple Audio Sources With the von Mises Distribution and Variational EM

Autor: Radu Horaud, Christine Evers, Xavier Alameda-Pineda, Yutong Ban

Publikováno v: IEEE Signal Processing Letters
IEEE Signal Processing Letters, Institute of Electrical and Electronics Engineers, 2019, 26 (6), pp.798-802. ⟨10.1109/LSP.2019.2908376⟩
IEEE Signal Processing Letters, 2019, 26 (6), pp.798-802. ⟨10.1109/LSP.2019.2908376⟩

In this paper we address the problem of simultaneously tracking several moving audio sources, namely the problem of estimating source trajectories from a sequence of observed features. We propose to use the von Mises distribution to model audio-sourc

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a66b575c33d60722f55d4a4863027db6
https://doi.org/10.1109/lsp.2019.2908376

Zobrazit plný text záznamu

CANU-ReID: A Conditional Adversarial Network for Unsupervised person Re-IDentification

Autor: Radu Horaud, Stéphane Lathuilière, Yihong Xu, Xavier Alameda-Pineda, Guillaume Delorme

Publikováno v: ICPR 2020-25th International Conference on Pattern Recognition
ICPR 2020-25th International Conference on Pattern Recognition, Jan 2021, Milano, Italy. pp.1-8
ICPR 2020-25th International Conference on Pattern Recognition, Jan 2021, Milano, Italy. pp.4428-4435, ⟨10.1109/ICPR48806.2021.9412431⟩
ICPR

International audience; Fig. 1: Clustering-based (left) vs. conditional adversarial clustering-based (right) unsupervised person re-ID. Our intuition is that features should be camera-independent, and thus the clustering result should group visual fe

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e23331ad91ac3d5406a7b55eb5122d00
https://hal.inria.fr/hal-02882285

Zobrazit plný text záznamu

3D Shape Registration Using Spectral Graph Embedding and Probabilistic Matching

Autor: Diana Mateus, Radu Horaud, Avinash Sharma

Publikováno v: Image Processing and Analysing With Graphs: Theory and Practice
Olivier Lezoray and Leo Grady. Image Processing and Analysing With Graphs: Theory and Practice, CRC Press, pp.441-474, 2012

International audience; In this book chapter we address the problem of 3D shape registration and we propose a novel technique based on spectral graph theory and probabilistic matching. Recent advancement in shape acquisition technology has led to the

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ece2b284351cb6a234959ac3dc484e2f

Zobrazit plný text záznamu

Robust Factorization Methods Using a Gaussian/Uniform Mixture Model

Autor: Radu Horaud, Andrei Zaharescu

Publikováno v: International Journal of Computer Vision
International Journal of Computer Vision, Springer Verlag, 2009, 81 (3), pp.240-258. ⟨10.1007/s11263-008-0169-x⟩
International Journal of Computer Vision, 2009, 81 (3), pp.240-258. ⟨10.1007/s11263-008-0169-x⟩

International audience; In this paper we address the problem of building a class of robust factorization algorithms that solve for the shape and motion parameters with both affine (weak perspective) and perspective camera models. We introduce a Gauss

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::750a8ecdd84fe2312d2ce05194b5b913
http://arxiv.org/abs/2012.08243

Zobrazit plný text záznamu

Articulated Shape Matching Using Laplacian Eigenfunctions and Unsupervised Point Registration

Autor: Radu Horaud, Fabio Cuzzolin, David Knossow, Diana Mateus, Edmond Boyer

Publikováno v: CVPR 2008-IEEE Conference on Computer Vision and Pattern Recognition
CVPR 2008-IEEE Conference on Computer Vision and Pattern Recognition, Jun 2008, Anchorage, United States. pp.1-8, ⟨10.1109/CVPR.2008.4587538⟩

International audience; Matching articulated shapes represented by voxelsets reduces to maximal sub-graph isomorphism when each set is described by a weighted graph. Spectral graph theory can be used to isometrically map these graphs onto lower dimen

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0c4373636dc8a6bd2f9b6437b3add075
http://arxiv.org/abs/2012.07340

Zobrazit plný text záznamu

Cyclopean Geometry of Binocular Vision

Autor: Radu Horaud, Miles Hansard

Publikováno v: Journal of the Optical Society of America. A Optics, Image Science, and Vision
Journal of the Optical Society of America. A Optics, Image Science, and Vision, Optical Society of America, 2008, 25 (9), pp.2357-2369. ⟨10.1364/JOSAA.25.002357⟩
Journal of the Optical Society of America. A Optics, Image Science, and Vision, 2008, 25 (9), pp.2357-2369. ⟨10.1364/JOSAA.25.002357⟩

The geometry of binocular projection is analyzed, with reference to the primate visual system. In particular, the effects of coordinated eye movements on the retinal images are investigated. An appropriate oculomotor parameterization is defined, and

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9dd2ab08e600445004d5ec266c91c28c
http://arxiv.org/abs/2012.06363

Zobrazit plný text záznamu

A Differential Model of the Complex Cell

Autor: Radu Horaud, Miles Hansard

Publikováno v: Neural Computation
Neural Computation, Massachusetts Institute of Technology Press (MIT Press), 2011, 23 (9), pp.2324-2357. ⟨10.1162/NECO_a_00163⟩
Neural Computation, 2011, 23 (9), pp.2324-2357. ⟨10.1162/NECO_a_00163⟩

International audience; The receptive fields of simple cells in the visual cortex can be understood as linear filters. These filters can be modelled by Gabor functions, or by Gaussian derivatives. Gabor functions can also be combined in an energy mod

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fce7a80020261906ab10288adea8cfc7
http://arxiv.org/abs/2012.09027

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání