Consulter le flux RSS

Publications

Cette page présente les publications du Centre Borelli déposées sur le serveur HAL.

Affichage des publications 601 à 610 sur 1122 au total

Machine Learning

Classification non-supervisée de documents à partir des modèles Transformeurs

Pre-trained Transformer-based word embeddings are now widely used in text mining where they are known to significantly improve supervised tasks such as text classification, named entity recognition and question answering. Since the Transformer…

Mira Ait-Saada, François Role, Mohamed Nadif

Revue des Nouvelles Technologies de l'Information, Extraction et Gestion des Connaissances, RNTI-E-38 -

Statistics

Demosaicing to Detect Demosaicing and Image Forgeries

The trustfulness of images is a critical concern. Digital photographs can no longer be assumed to be truthful; indeed, digital image editing tools can easily and convincingly alter the semantic content of an image.Being able to analyse an image to…

Quentin Bammey, Rafael Grompone von Gioi, Jean-Michel Morel

2022 IEEE International Workshop on Information Forensics and Security (WIFS) -

Statistics

Bayesian causal network modeling suggests adolescent cannabis use accelerates prefrontal cortical thinning

Abstract While there is substantial evidence that cannabis use is associated with differences in human brain development, most of this evidence is correlational in nature. Bayesian causal network (BCN) modeling attempts to identify probable causal…

Max M Owens, Matthew D Albaugh, Nicholas Allgaier, Dekang Yuan, Gabriel Robert, Renata Basso Cupertino, Philip A. Spechler, Anthony Juliano, Sage Hahn, Tobias Banaschewski, Arun L.W. Bokde, Sylvane Desrivières, Herta Flor, Antoine Grigis, Penny A Gowland, Andreas Heinzel, Rüdiger Brühl, Jean-Luc Martinot, Marie-Laure Paillere-Martinot, Eric Artiges, Frauke Nees, Dimitri Papadopoulos-Orfanos, Herve Lemaitre, Tomas Paus, Luise Poustka, Sabina Millenet, Juliane H Fröhner, Michael N Smolka, Henrik Walter, Robert Whelan, Scott Mackey, Gunter Schumann, Hugh Garavan

Translational Psychiatry -

Statistics

Forgery Detection by Internal Positional Learning of Demosaicing Traces

We propose 4Point (Forensics with Positional Internal Training), an unsupervised neural network trained to assess the consistency of the image colour mosaic to find forgeries. Positional learning trains the model to learn the modulo-2 position of…

Quentin Bammey, Rafael Grompone von Gioi, Jean-Michel Morel

2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) -

Image Processing

The Impact of JPEG Compression on Prior Image Noise

JPEG compression is widely used to store digital images and extensive studies analysed its impact on the image quality; in particular the quantization noise and artefacts created by JPEG. Nevertheless, there is little work on the impact of JPEG…

Marina Gardella, Tina Nikoukhah, Yanhao Li, Quentin Bammey

2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2022) -

Machine Learning

Robust Kernel Density Estimation with Median-of-Means principle

In this paper, we introduce a robust nonparametric density estimator combining the popular Kernel Density Estimation method and the Median-of-Means principle (MoM-KDE). This estimator is shown to achieve robustness to any kind of anomalous data,…

Pierre Humbert, Batiste Le Bars, Ludovic Minvielle

ICML 2022 - The 39th International Conference on Machine Learning (ICML) -

Signal and Image processing

Supervised change-point detection with dimension reduction, applied to physiological signals

This paper proposes an automatic method to calibrate change point detection algorithms for high-dimensional time series. Our procedure builds on the ability of an expert (e.g. a medical researcher) to produce approximate segmentation estimates,…

Charles Truong, Laurent Oudre

NeurIPS 2022 Workshop on Learning from Time Series for Health -

Mathematics

Looking for invariance in Locally Linear Embedding

In this poster, we review the Locally Linear Embedding method and look for new invariance patterns with the hope to explain better the properties of the embeddings constructed.

Elodie Maignant, Xavier Pennec, Alain Trouvé

Curves and Surfaces 2022 -