Zobrazeno 1 - 10
of 23
pro vyhledávání: '"Sandro Schönborn"'
Publikováno v:
PLoS ONE, Vol 13, Iss 3, p e0193190 (2018)
Upon a first encounter, individuals spontaneously associate faces with certain personality dimensions. Such first impressions can strongly impact judgments and decisions and may prove highly consequential. Researchers investigating the impact of faci
Externí odkaz:
https://doaj.org/article/03a0b612b31942c9968d26fd73a9dbf1
Publikováno v:
IFAC-PapersOnLine. 53:11614-11619
We demonstrate the application of automated machine learning to the problem of identifying dynamic process models using recurrent neural networks (RNNs). The general concept relies on continuous monitoring of input-output data from a plant and the pr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2aff484d372a5fed91ee8818c463210e
https://doi.org/10.1016/j.ifacol.2020.12.642
https://doi.org/10.1016/j.ifacol.2020.12.642
Autor:
Giuliano Albanese, Sandro Schönborn, Robert Birke, Georgia Giannopoulou, Thanikesavan Sivanthi
Publikováno v:
2021 26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA ).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::eaaf11eecbaa41681f29b22921a88b6e
https://doi.org/10.1109/etfa45728.2021.9613320
https://doi.org/10.1109/etfa45728.2021.9613320
Publikováno v:
ICASSP
In this work, we propose a VAE-LSTM hybrid model as an unsupervised approach for anomaly detection in time series. Our model utilizes both a VAE module for forming robust local features over short windows and a LSTM module for estimating the long ter
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0398ad1641c2fa4d63a15efaa50e873b
https://doi.org/10.1109/icassp40776.2020.9053558
https://doi.org/10.1109/icassp40776.2020.9053558
Publikováno v:
Journal of Mathematical Imaging and Vision
We present a generalization of the convolution-based variational image registration approach, in which different regularizers can be implemented by conveniently exchanging the convolution kernel, even if it is nonseparable or nonstationary. Nonsepara
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d22c2552229989fb4cdd2abb282a6ef2
http://doc.rero.ch/record/325389/files/10851_2014_Article_497.pdf
http://doc.rero.ch/record/325389/files/10851_2014_Article_497.pdf
Autor:
Thomas Vetter, Ghazi Bouabene, Ayet Shaiek, Virginie Rubert, Frederic Flament, Andreas Schneider, Ghislain Francois, Sandro Schönborn
Publikováno v:
FG
We propose a photo-realistic method for artificially ageing facial photographs by combining learned shape deformations with skin detail transfer between a donor and a receiver face. Facial ageing is a complicated process that most existing face model
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::577cf06832bcee05f36700371ba12f9e
Publikováno v:
INFOCOM Workshops
IEEE INFOCOM 2019-IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)
IEEE INFOCOM 2019-IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)
Deep reinforcement learning (DRL) has recently received increasing attention due to unprecedented ability achieved in playing games. Since then DRL has been successfully applied across different domains. Here we explore the potential of DRL in autono
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::24e78e80bdcb05ac3b226026dfaec8dc
https://hdl.handle.net/2318/1888973
https://hdl.handle.net/2318/1888973
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783319920573
IEA/AIE
IEA/AIE
Currently, engineers at substation service providers match customer data with the corresponding internally used signal names manually. This paper proposes a machine learning method to automate this process based on substation signal mapping data from
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b1f12b68b52770975636a7c33cef5169
https://doi.org/10.1007/978-3-319-92058-0_36
https://doi.org/10.1007/978-3-319-92058-0_36
Publikováno v:
Computer Vision and Image Understanding. 136:117-127
Discussion of the implicit but unavoidable background model in generative image models.Analysis of common practical strategies to deal with the problem and their drawbacks.Explicit background models are proposed as a fundamental solution.The backgrou
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::95addaf4648d2b11ebc3ba1221c8eb47
https://doi.org/10.1016/j.cviu.2015.01.008
https://doi.org/10.1016/j.cviu.2015.01.008
3D Morphable Face Models have been introduced for the analysis of 2D face photographs. The analysis is performed by actively reconstructing the three-dimensional face from the image in an Analysis-by-Synthesis loop, exploring statistical models for s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::acba66ca6f4b3dc35324d36fad05013d
https://doi.org/10.1016/b978-0-12-810493-4.00006-7
https://doi.org/10.1016/b978-0-12-810493-4.00006-7