50 citations · 64 across the 7 of their papers we have counts for
9 papers
Long-Range Transformer Architectures for Document Understanding
Thibault Douzon, Stefan Duffner, Christophe Garcia +1
Since their release, Transformers have revolutionized many fields from Natural Language Understanding to Computer Vision. Document Understanding (DU) was not left behind with first…
Improving Information Extraction on Business Documents with Specific Pre-Training Tasks
Thibault Douzon, Stefan Duffner, Christophe Garcia +1
Transformer-based Language Models are widely used in Natural Language Processing related tasks. Thanks to their pre-training, they have been successfully adapted to Information Ext…
Low-complexity Approximate Convolutional Neural Networks
R. J. Cintra, S. Duffner, C. Garcia +1
In this paper, we present an approach for minimizing the computational complexity of trained Convolutional Neural Networks (ConvNet). The idea is to approximate all elements of a g…
Learning Sparse Filters in Deep Convolutional Neural Networks with a l1/l2 Pseudo-Norm
Anthony Berthelier, Yongzhe Yan, Thierry Chateau +3
While deep neural networks (DNNs) have proven to be efficient for numerous tasks, they come at a high memory and computation cost, thus making them impractical on resource-limited…
Facial Landmark Correlation Analysis
Yongzhe Yan, Stefan Duffner, Priyanka Phutane +4
We present a facial landmark position correlation analysis as well as its applications. Although numerous facial landmark detection methods have been presented in the literature, f…
2D Wasserstein Loss for Robust Facial Landmark Detection
Yongzhe Yan, Stefan Duffner, Priyanka Phutane +4
The recent performance of facial landmark detection has been significantly improved by using deep Convolutional Neural Networks (CNNs), especially the Heatmap Regression Models (HR…
Routine Modeling with Time Series Metric Learning
Paul Compagnon, Grégoire Lefebvre, Stefan Duffner +1
Traditionally, the automatic recognition of human activities is performed with supervised learning algorithms on limited sets of specific activities. This work proposes to recogniz…
End-to-End Data Visualization by Metric Learning and Coordinate Transformation
Lilei Zheng, Ying Zhang, Stefan Duffner +3
This paper presents a deep nonlinear metric learning framework for data visualization on an image dataset. We propose the Triangular Similarity and prove its equivalence to the Cos…
Improving Texture Categorization with Biologically Inspired Filtering
Ngoc-Son Vu, Thanh Phuong Nguyen, Christophe Garcia
Within the domain of texture classification, a lot of effort has been spent on local descriptors, leading to many powerful algorithms. However, preprocessing techniques have receiv…