Zobrazeno 1 - 10
of 36
pro vyhledávání: '"Franz-Josef Pfreundt"'
Autor:
Dominik Bendle, Janko Böhm, Wolfram Decker, Alessandro Georgoudis, Franz-Josef Pfreundt, Mirko Rahn, Pascal Wasser, Yang Zhang
Publikováno v:
Journal of High Energy Physics, Vol 2020, Iss 2, Pp 1-34 (2020)
Abstract We introduce an algebro-geometrically motived integration-by-parts (IBP) re- duction method for multi-loop and multi-scale Feynman integrals, using a framework for massively parallel computations in computer algebra. This framework combines
Externí odkaz:
https://doaj.org/article/07b5fcf860874e169d919a6f640dced2
Autor:
Janko Böhm, Franz-Josef Pfreundt, Mirko Rahn, Lukas Ristau, Wolfram Decker, Anne Frühbis-Krüger
Publikováno v:
Foundations of Computational Mathematics. 21:767-806
Introducing parallelism and exploring its use is still a fundamental challenge for the computer algebra community. In high-performance numerical simulation, on the other hand, transparent environments for distributed computing which follow the princi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::562c68746c45b8d7a991256bba724882
https://doi.org/10.1007/s10208-020-09464-x
https://doi.org/10.1007/s10208-020-09464-x
Autor:
Frank Hannig, Yevgen Grynko, Thomas Steinke, Jürgen Teich, Franz-Josef Pfreundt, Florian Wende, Stefan Groth, Tobias Kenter, Daniel Grünewald, Jens Förstner, Christian Plessl, Merlind Schotte, Martin Weiser, Samer Alhaddad
Summary Solving partial differential equations (PDEs) on unstructured grids is a cornerstone of engineering and scientific computing. Heterogeneous parallel platforms, including CPUs, GPUs, and FPGAs, enable energy‐efficient and computationally dem
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ebfa2dd2e405f7cd887f5bbda964d484
https://publica.fraunhofer.de/handle/publica/270560
https://publica.fraunhofer.de/handle/publica/270560
Publikováno v:
ICPR
The term “attribute transfer” refers to the tasks of altering images in such a way, that the semantic interpretation of a given input image is shifted towards an intended direction, which is quantified by semantic attributes. Prominent example ap
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d09a8175e37c3615253c87169988ae31
https://doi.org/10.1109/icpr48806.2021.9412878
https://doi.org/10.1109/icpr48806.2021.9412878
Publikováno v:
ICPR
In this work, we evaluate two different image clustering objectives, k-means clustering and correlation clustering, in the context of Triplet Loss induced feature space embeddings. Specifically, we train a convolutional neural network to learn discri
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a9b9924b6cb915a78f667b7e9a64e8ff
https://doi.org/10.1109/icpr48806.2021.9412602
https://doi.org/10.1109/icpr48806.2021.9412602
Publikováno v:
Computer Vision – ACCV 2020 ISBN: 9783030695316
ACCV (2)
ACCV (2)
Multiple Object Tracking (MOT) is a long-standing task in computer vision. Current approaches based on the tracking by detection paradigm either require some sort of domain knowledge or supervision to associate data correctly into tracks. In this wor
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2750f1a651273b0ed283b4b7c26397b1
https://doi.org/10.1007/978-3-030-69532-3_33
https://doi.org/10.1007/978-3-030-69532-3_33
Publikováno v:
IJCNN
Despite the success of convolutional neural networks (CNNs) in many computer vision and image analysis tasks, they remain vulnerable against so-called adversarial attacks: Small, crafted perturbations in the input images can lead to false predictions
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cbc5c31eed8440449b1e2c1b32f42919
Autor:
Frank Hannig, Merlind Schotte, Samer Alhaddad, Stefan Groth, Thomas Steinke, Florian Wende, Martin Weiser, Franz-Josef Pfreundt, Yevgen Grynko, Daniel Grünewald, Jürgen Teich, Jens Förstner, Christian Plessl, Tobias Kenter
Publikováno v:
Euro-Par 2020: Parallel Processing Workshops ISBN: 9783030715922
Euro-Par Workshops
Euro-Par Workshops
Solving partial differential equations on unstructured grids is a cornerstone of engineering and scientific computing. Nowadays, heterogeneous parallel platforms with CPUs, GPUs, and FPGAs enable energy-efficient and computationally demanding simulat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fbf8754c80529c3151f007e33145a35b
https://doi.org/10.1007/978-3-030-71593-9_15
https://doi.org/10.1007/978-3-030-71593-9_15
Autor:
Ricard Durall, Janis Keuper, Stanislav Frolov, Andreas Dengel, Franz-Josef Pfreundt, Federico Raue, Jörn Hees
Publikováno v:
KI 2021: Advances in Artificial Intelligence ISBN: 9783030876258
KI
KI
Transformer models have recently attracted much interest from computer vision researchers and have since been successfully employed for several problems traditionally addressed with convolutional neural networks. At the same time, image synthesis usi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::499679258b22b034fb6c855fcdc22b02
https://doi.org/10.1007/978-3-030-87626-5_6
https://doi.org/10.1007/978-3-030-87626-5_6
Publikováno v:
VISIGRAPP (4: VISAPP)
Generative adversarial networks are the state of the art approach towards learned synthetic image generation. Although early successes were mostly unsupervised, bit by bit, this trend has been superseded by approaches based on labelled data. These su
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fcdd665a475db7f57a6b3d16ddf86b8b
http://arxiv.org/abs/2012.08803
http://arxiv.org/abs/2012.08803