Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Serr��, Joan"'
Autor:
Pons, Jordi, Serr��, Joan, Pascual, Santiago, Cengarle, Giulio, Arteaga, Daniel, Scaini, Davide
Upsampling artifacts are caused by problematic upsampling layers and due to spectral replicas that emerge while upsampling. Also, depending on the used upsampling layer, such artifacts can either be tonal artifacts (additive high-frequency noise) or
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::95dd683bbbb8c755688334337ba5b2a8
http://arxiv.org/abs/2111.11773
http://arxiv.org/abs/2111.11773
Score-based generative models provide state-of-the-art quality for image and audio synthesis. Sampling from these models is performed iteratively, typically employing a discretized series of noise levels and a predefined scheme. In this note, we firs
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d7a8b2de5bb0e8457f42bade7a4cf497
http://arxiv.org/abs/2104.03725
http://arxiv.org/abs/2104.03725
Autor:
G��mez, Emilia, Castillo, Carlos, Charisi, Vicky, Dahl, Ver��nica, Deco, Gustavo, Delipetrev, Blagoj, Dewandre, Nicole, Gonz��lez-Ballester, Miguel ��ngel, Gouyon, Fabien, Hern��ndez-Orallo, Jos��, Herrera, Perfecto, Jonsson, Anders, Koene, Ansgar, Larson, Martha, de M��ntaras, Ram��n L��pez, Martens, Bertin, Miron, Marius, Moreno-Bote, Rub��n, Oliver, Nuria, Gallardo, Antonio Puertas, Schweitzer, Heike, Sebastian, Nuria, Serra, Xavier, Serr��, Joan, Tolan, Song��l, Vold, Karina
This document contains the outcome of the first Human behaviour and machine intelligence (HUMAINT) workshop that took place 5-6 March 2018 in Barcelona, Spain. The workshop was organized in the context of a new research programme at the Centre for Ad
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5f1e87093b089fcaa3d560d89a96ee48
http://arxiv.org/abs/1806.03192
http://arxiv.org/abs/1806.03192
We study the use of a time series encoder to learn representations that are useful on data set types with which it has not been trained on. The encoder is formed of a convolutional neural network whose temporal output is summarized by a convolutional
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::175ce27e1046b35ccf6ce255cc527327
http://arxiv.org/abs/1805.03908
http://arxiv.org/abs/1805.03908