no code implementations • 17 Oct 2023 • Matthis Manthe, Stefan Duffner, Carole Lartizien
We propose a novel personalization algorithm tailored to the feature shift induced by the usage of different scanners and acquisition parameters by different institutions.
1 code implementation • 11 Sep 2023 • Thibault Douzon, Stefan Duffner, Christophe Garcia, Jérémy Espinas
These tasks force the model to learn better-contextualized representations of the scanned documents.
1 code implementation • 11 Sep 2023 • Thibault Douzon, Stefan Duffner, Christophe Garcia, Jérémy Espinas
They are based on efficient implementations of Transformers for long sequences.
no code implementations • 1 Jan 2021 • Paul Compagnon, Grégoire Lefebvre, Stefan Duffner, Christophe Garcia
Sequence metric learning is becoming a widely adopted approach for various applications dealing with sequential multi-variate data such as activity recognition or natural language processing and is most of the time tackled with sequence alignment approaches or representation learning.
no code implementations • 20 Jul 2020 • Anthony Berthelier, Yongzhe Yan, Thierry Chateau, Christophe Blanc, Stefan Duffner, Christophe Garcia
Moreover, the trade-off between the sparsity and the accuracy is compared to other loss regularization terms based on the l1 or l2 norm as well as the SSL, NISP and GAL methods and shows that our approach is outperforming them.
no code implementations • 24 Nov 2019 • Yongzhe Yan, Stefan Duffner, Priyanka Phutane, Anthony Berthelier, Christophe Blanc, Christophe Garcia, Thierry Chateau
The recent performance of facial landmark detection has been significantly improved by using deep Convolutional Neural Networks (CNNs), especially the Heatmap Regression Models (HRMs).
no code implementations • 24 Nov 2019 • Yongzhe Yan, Stefan Duffner, Priyanka Phutane, Anthony Berthelier, Christophe Blanc, Christophe Garcia, Thierry Chateau
We propose two applications based on this analysis.
no code implementations • 8 Jul 2019 • Paul Compagnon, Grégoire Lefebvre, Stefan Duffner, Christophe Garcia
Traditionally, the automatic recognition of human activities is performed with supervised learning algorithms on limited sets of specific activities.
no code implementations • 27 Dec 2016 • Lilei Zheng, Ying Zhang, Stefan Duffner, Khalid Idrissi, Christophe Garcia, Atilla Baskurt
This paper presents a deep nonlinear metric learning framework for data visualization on an image dataset.