Intellectual Property Invention ID2326WW00 registered by Intellectual Property Board, Amadeus S.A.S., Sophia Antipolis, France. Amadeus IP Invention licensed by Defensive Publications in the CIKM 2020 and DATA 2020 International Conferences: [1] Tianshu Yang, Nicolas Pasquier, Antoine Hom, Laurent Dolle, Frédéric Precioso. "Semi-supervised...
-
July 7, 2020 (v1)PatentUploaded on: December 4, 2022
-
May 31, 2013 (v1)Publication
Résumé non disponible
Uploaded on: October 11, 2023 -
May 31, 2013 (v1)Publication
Résumé non disponible
Uploaded on: December 2, 2022 -
September 24, 2004 (v1)Publication
Active contour modeling represents the main framework of this thesis. Active contours are dynamicmethods applied to segmentation of still images and video. The goal is to extract image regionscorresponding to semantic objects. Image and Video segmentation can be cast in a minimizationframework by choosing a criterion which includes region and...
Uploaded on: December 4, 2022 -
2002 (v1)Journal article
International audience
Uploaded on: February 28, 2023 -
2021 (v1)Book section
International audience
Uploaded on: December 4, 2022 -
July 7, 2020 (v1)Conference paper
We present a semi-supervised ensemble clustering framework for identifying relevant multi-level clusters, regarding application objectives, in large datasets and mapping them to application classes for predicting the class of new instances. This framework extends the MultiCons closed sets based multiple consensus clustering approach but can...
Uploaded on: December 4, 2022 -
July 21, 2017 (v1)Conference paper
The burst of video production appeals for new browsing frameworks. Chiefly in sports, TV companies have years of recorded match archives to exploit and sports fans are looking for replay, summary or collection of events. In this work, we design a new multi-resolution motion feature for video abstraction. This descriptor is based on optical flow...
Uploaded on: December 4, 2022 -
September 12, 2012 (v1)Report
Cet article présente une méthode de segmentation par contours actifs basés histogramme intégrant comme mesure de similarité la famille particulière des alpha-divergences. L'intérêt principal de cette méthode réside (i) dans la flexibilité des alpha-divergences dont la métrique intrinsèque peut-être paramétrisée via la valeur de alpha et donc...
Uploaded on: December 4, 2022 -
March 25, 2012 (v1)Conference paper
In this article, a complete original framework for non supervised statistical region based active contour segmentation is proposed. More precisely, the method is based on the maximization of alphadivergences between non paramterically estimated probability density functions (PDF) of the inner and outer regions defined by the evolving curve. In...
Uploaded on: December 3, 2022 -
June 25, 2020 (v1)Book section
Convolutional Neural Network (CNN) demonstrated impressive classification performance on ElectroCardioGram (ECG) analysis and has a great potential to extract salient patterns from signal. Visualizing local contributions of ECG input to a CNN classification model can both help us understand why CNN can reach such high-level performances and...
Uploaded on: December 4, 2022 -
January 10, 2021 (v1)Conference paper
The way people consume sports on TV has drastically evolved in the last years, particularly under the combined effects of the legalization of sport betting and the huge increase of sport analytics. Several companies are nowadays sending observers in the stadiums to collect live data of all the events happening on the field during the match....
Uploaded on: December 4, 2022 -
March 21, 2023 (v1)Publication
In many scenarios, the interpretability of machine learning models is a highly required but difficult task. To explain the individual predictions of such models, local model-agnostic approaches have been proposed. However, the process generating the explanations can be, for a user, as mysterious as the prediction to be explained. Furthermore,...
Uploaded on: March 25, 2023 -
April 27, 2020 (v1)Publication
International audience
Uploaded on: December 4, 2022 -
November 7, 2014 (v1)Conference paper
To build a detailed knowledge of the biodiversity, the geo-graphical distribution and the evolution of the alive speciesis essential for a sustainable development and the preser-vation of this biodiversity. Massive databases of underwa-ter video surveillance have been recently made available forsupporting designing algorithms targeting the...
Uploaded on: February 28, 2023 -
June 15, 2022 (v1)Publication
Anchors [Ribeiro et al. (2018)] is a post-hoc, rule-based interpretability method. For text data, it proposes to explain a decision by highlighting a small set of words (an anchor) such that the model to explain has similar outputs when they are present in a document. In this paper, we present the first theoretical analysis of Anchors,...
Uploaded on: December 3, 2022 -
July 2023 (v1)Journal article
Videos and images from camera traps are more and more used by ecologists to estimate the population of species on a territory. It is a laborious work since experts have to analyse massive data sets manually. This takes also a lot of time to filter these videos when many of them do not contain animals or are with human presence. Fortunately,...
Uploaded on: April 29, 2023 -
2015 (v1)Conference paper
In this paper, we propose a new framework hybridizing a Support Vector Machine (SVM), a Multi-Objective Genetic Algorithm (MOGA) and a Locality Sensitive Hashing (LSH). The goal is to tackle fine-grained classification challenges which means classifying many classes with high similarities between classes and poor similarities inside one class....
Uploaded on: February 28, 2023 -
2012 (v1)Conference paper
The amount of images contained in repositories or available on Internet has exploded over the last years. In order to retrieve efficiently one or several images in a database, the development of Content-Based Image Retrieval (CBIR) systems has become an intensively active research area. However, most proposed systems are keyword-based and few...
Uploaded on: February 28, 2023 -
January 10, 2022 (v1)Journal article
Semi-supervised consensus clustering, also called semi-supervised ensemble clustering, is a recently emerged technique that integrates prior knowledge into consensus clustering in order to improve the quality of the clustering result. In this article, we propose a novel semi-supervised consensus clustering algorithm extending the previous work...
Uploaded on: December 4, 2022 -
2015 (v1)Conference paper
Multimodal Optimization (MMO) aims at identifying several best solutions to a problem whereas classical optimization converge oftenly to only one good solution. MMO has been an active research area in the past years and several new evolutionary algorithms have been developed to tackle multimodal problems. In this work, we compare extensively...
Uploaded on: February 28, 2023 -
2015 (v1)Conference paper
No description
Uploaded on: February 28, 2023