Zobrazeno 1 - 10
of 14
pro vyhledávání: '"Frederic, Precioso"'
Autor:
Mateo Espinosa Zarlenga, Pietro, Barbiero, Gabriele, Ciravegna, Giuseppe, Marra, Giannini, Francesco, Diligenti, Michelangelo, Zohreh, Shams, Frederic, Precioso, Melacci, Stefano, Adrian, Weller, Pietro, Lió, Mateja, Jamnik
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______1820::fd1717b6eedb56474028cc76d20bbf60
https://hdl.handle.net/11365/1231237
https://hdl.handle.net/11365/1231237
Autor:
Frederic Precioso, Michel Barlaud
Publikováno v:
EURASIP Journal on Advances in Signal Processing, Vol 2002, Iss 6, Pp 555-560 (2002)
This paper deals with video segmentation for MPEG-4 and MPEG-7 applications. Region-based active contour is a powerful technique for segmentation. However most of these methods are implemented using level sets. Although level-set methods provide accu
Externí odkaz:
https://doaj.org/article/165f013e3e7b4b349c22a9d221ad4e4c
Publikováno v:
Journal on Computing and Cultural Heritage
This work combines semantic reasoning and machine learning to create tools that allow curators of the visual art collections to identify and correct the annotations of the artwork as well as to improve the relevance of the content-based search result
Publikováno v:
CMLF 2020-7ème Congrès mondiale de linguistique française
CMLF 2020-7ème Congrès mondiale de linguistique française, Jul 2020, Montpellier / Online, France
HAL
CMLF 2020-7ème Congrès mondiale de linguistique française, Jul 2020, Montpellier / Online, France
HAL
International audience; L'intertexte est la condition de l'interprétation de tout texte. Cependant, sa matérialisation, son explicitation, son implémentation ont toujours paru difficile pour la linguistique textuelle. Cette contribution propose un
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::9f45bb0e82e5716f38c9ed7799dc6e5a
https://hal.archives-ouvertes.fr/hal-02520224
https://hal.archives-ouvertes.fr/hal-02520224
Publikováno v:
JADT 2020-15èmes Journées Internationales d'Analyse statistique des Données Textuelles
JADT 2020-15èmes Journées Internationales d'Analyse statistique des Données Textuelles, Jun 2020, Toulouse, France
HAL
JADT 2020-15èmes Journées Internationales d'Analyse statistique des Données Textuelles, Jun 2020, Toulouse, France
HAL
International audience; Since few years, some tools that are helping us to interpret results of deep learning have appeared (LIME, LSTMVIS, TDS). In this paper, we propose to go further by searching hidden information encoded in intermediate layers o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::df304b5c09b7251c50b0c66f6b97ee79
https://hal.archives-ouvertes.fr/hal-02926880/document
https://hal.archives-ouvertes.fr/hal-02926880/document
Autor:
Laurent Vanni, Mélanie Ducoffe, Damon Mayaffre, Frederic Precioso, Dominique Longrée, Veeresh Elango, Nazly Santos Buitrago, Juan Gonzales Huesca, Luis Galdo, Carlos Aguilar
Publikováno v:
56th Annual Meeting of the Association for Computational Linguistics
56th Annual Meeting of the Association for Computational Linguistics, Jul 2018, Melbourne, France
HAL
56th Annual Meeting of the Association for Computational Linguistics, Jul 2018, Melbourne, France
HAL
International audience; In this paper, we propose a new strategy , called Text Deconvolution Saliency (TDS), to visualize linguistic information detected by a CNN for text classification. We extend Deconvolution Networks to text in order to present a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::e2de25df6fdeb6e1eadbb5cc55f84f8d
https://hal.archives-ouvertes.fr/hal-01804310
https://hal.archives-ouvertes.fr/hal-01804310
Publikováno v:
NLP Challenges for Detecting Medication and Adverse Drug Events from Electronic Health Records (MADE1.0)
NLP Challenges for Detecting Medication and Adverse Drug Events from Electronic Health Records (MADE1.0), University of Massachusetts Lowell, Worcester, Amherst, May 2018, Massachusetts, United States
HAL
NLP Challenges for Detecting Medication and Adverse Drug Events from Electronic Health Records (MADE1.0), University of Massachusetts Lowell, Worcester, Amherst, May 2018, Massachusetts, United States
HAL
International audience; Currently, the best performance for Named Entity Recognition in medical notes is obtained by systems based on neural networks. These supervised systems require precise features in order to learn well fitted models from trainin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::431e2c1ef777a0f890f7bc024853c4fc
https://hal.archives-ouvertes.fr/hal-01786995/file/UCA-I3S_2.pdf
https://hal.archives-ouvertes.fr/hal-01786995/file/UCA-I3S_2.pdf
Autor:
Mélanie Ducoffe, Damon Mayaffre, Frederic Precioso, Frédéric Lavigne, Laurent Vanni, Tre-Hardy, A.
Publikováno v:
JADT-Statistical Analysis of Textual Data
JADT 2016-Statistical Analysis of Textual Data
JADT 2016-Statistical Analysis of Textual Data, Damon Mayaffre; Céline Poudat; Laurent Vanni; Véronique Magri; Peter Follette; Caroline Daire, Jun 2016, Nice, France. pp.157-168
HAL
JADT 2016-Statistical Analysis of Textual Data
JADT 2016-Statistical Analysis of Textual Data, Damon Mayaffre; Céline Poudat; Laurent Vanni; Véronique Magri; Peter Follette; Caroline Daire, Jun 2016, Nice, France. pp.157-168
HAL
International audience; Author identification and text genesis have always been a hot topic for the statistical analysis of textual data community. Recent advances in machine learning have seen the emergence of machines competing state-of-the-art com
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::c877bca23990bce5051ff62f6312eea1
https://hal.archives-ouvertes.fr/hal-01343209v2/file/JADT2016_Ducoffe_et_al.pdf
https://hal.archives-ouvertes.fr/hal-01343209v2/file/JADT2016_Ducoffe_et_al.pdf
Autor:
Frederic Precioso
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783319419190
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::02383225e0401d8979deb685c48149fd
https://doi.org/10.1007/978-3-319-41920-6
https://doi.org/10.1007/978-3-319-41920-6
The research in content-based indexing and retrieval of visual information such as images and video has become one of the most populated directions in the vast area of information technologies. Social networks such as YouTube, Facebook, FileMobile, a