Zobrazeno 1 - 10
of 143
pro vyhledávání: '"Laviale, Martin"'
Most of the research in content-based image retrieval (CBIR) focus on developing robust feature representations that can effectively retrieve instances from a database of images that are visually similar to a query. However, the retrieved images some
Externí odkaz:
http://arxiv.org/abs/2308.08431
Recent works show that the data distribution in a network's latent space is useful for estimating classification uncertainty and detecting Out-of-distribution (OOD) samples. To obtain a well-regularized latent space that is conducive for uncertainty
Externí odkaz:
http://arxiv.org/abs/2305.13849
Autor:
Venkataramanan, Aishwarya, Laviale, Martin, Figus, Cécile, Usseglio-Polatera, Philippe, Pradalier, Cédric
Automatic classification of aquatic microorganisms is based on the morphological features extracted from individual images. The current works on their classification do not consider the inter-class similarity and intra-class variance that causes misc
Externí odkaz:
http://arxiv.org/abs/2109.11891
Autor:
Vijayaraj, Vinita, Laviale, Martin, Allen, Joey, Amoussou, Nellya, Hilt, Sabine, Hölker, Franz, Kipferler, Nora, Leflaive, Joséphine, López Moreira M, Gregorio A., Polst, Bastian H., Schmitt-Jansen, Mechthild, Stibor, Herwig, Gross, Elisabeth M.
Publikováno v:
In Water Research 1 June 2022 216
Autor:
Allen, Joey, Gross, Elisabeth M., Courcoul, Camille, Bouletreau, Stéphanie, Compin, Arthur, Elger, Arnaud, Ferriol, Jessica, Hilt, Sabine, Jassey, Vincent E.J., Laviale, Martin, Polst, Bastian H., Schmitt-Jansen, Mechthild, Stibor, Herwig, Vijayaraj, Vinita, Leflaive, Joséphine
Publikováno v:
In Water Research 15 February 2021 190
Autor:
Laviale, Martin
Dans le cadre de l'application de la Directive Cadre sur l'Eau il serait intéressant de mettre au point de nouveaux outils de surveillance de la qualité des cours d'eau. Dans le cas d'une pollution ponctuelle, certains d'entre eux pourraient être
Externí odkaz:
http://www.theses.fr/2008LIL10055
Publikováno v:
Botany Letters; Mar2024, Vol. 171 Issue 1, p50-53, 4p
Autor:
Martini, Séverine, Larras, Floriane, Boyé, Aurélien, Faure, Emile, Aberle, Nicole, Archambault, Philippe, Bacouillard, Lise, Beisner, Beatrix, Bittner, Lucie, Castella, Emmanuel, Danger, Michael, Gauthier, Olivier, Karp-Boss, Lee, Lombard, Fabien, Maps, Frédéric, Stemmann, Lars, Thiébaut, Éric, Usseglio-Polatera, Philippe, Vogt, Meike, Laviale, Martin, Ayata, Sakina‐dorothée
Publikováno v:
ALSO Aquatic Sciences Meeting
ALSO Aquatic Sciences Meeting, Association for the Sciences of Limnology and Oceanography (ASLO), Jun 2023, Palma de Mallorca, Balearic Islands, Spain. pp.965-994, ⟨10.1002/lno.11655⟩
ALSO Aquatic Sciences Meeting, Association for the Sciences of Limnology and Oceanography (ASLO), Jun 2023, Palma de Mallorca, Balearic Islands, Spain. pp.965-994, ⟨10.1002/lno.11655⟩
International audience; Aquatic ecologists face challenges in identifying the general rules of the functioning of ecosystems. A common framework, including freshwater, marine, benthic, and pelagic ecologists, is needed to bridge communication gaps an
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::e27304b6197dc4d781814e9d4bd7a529
https://hal.univ-lorraine.fr/hal-04117032
https://hal.univ-lorraine.fr/hal-04117032
Recent works show that the data distribution in a network's latent space is useful for estimating classification uncertainty and detecting Out-of-distribution (OOD) samples. To obtain a well-regularized latent space that is conducive for uncertainty
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5546de41ba4b58ec9606b90cea1bb592
http://arxiv.org/abs/2305.13849
http://arxiv.org/abs/2305.13849
Publikováno v:
14th European Diatom Meeting (EDM 14)
14th European Diatom Meeting (EDM 14), May 2023, Meise, Belgium
14th European Diatom Meeting (EDM 14), May 2023, Meise, Belgium
International audience
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______3379::ce6521d26f956501740a7d56da3115de
https://hal.univ-lorraine.fr/hal-04092991
https://hal.univ-lorraine.fr/hal-04092991