Search Results

Documents authored by Cremers, Daniel

Document
DOI: 10.4230/DagRep.7.9.109
Deep Learning for Computer Vision (Dagstuhl Seminar 17391)

Authors: Daniel Cremers, Laura Leal-Taixé, and René Vidal

Published in: Dagstuhl Reports, Volume 7, Issue 9 (2018)

Abstract
The field of computer vision engages in the goal to enable and enhance a machine’s ability to infer knowledge and information from spatial and visual input data. Recent advances in data-driven learning approaches, accelerated by increasing parallel computing power and a ubiquitous availability of large amounts of data, pushed the boundaries of almost every vision related subdomain. The most prominent example of these machine learning approaches is a so called deep neural network (DNN), which works as a general function approximator and can be trained to learn a mapping between given input and target output data. Research on and with these DNN is generally referred to as Deep Learning. Despite its high dimensional and complex input space, research in the field of computer vision was and still is one of the main driving forces for new development in machine and deep learning, and vice versa. This seminar aims to discuss recent works on theoretical and practical advances in the field of deep learning itself as well as state-of-the-art results achieved by applying learning based approaches to various vision problems. Our diverse spectrum of topics includes theoretical and mathematical insights focusing on a better understanding of the fundamental concepts behind deep learning and a multitude of specific research topics facilitating an exchange of knowledge between peers of the research community.
Cite as

Daniel Cremers, Laura Leal-Taixé, and René Vidal. Deep Learning for Computer Vision (Dagstuhl Seminar 17391). In Dagstuhl Reports, Volume 7, Issue 9, pp. 109-125, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2018)

Copy BibTex To Clipboard

@Article{cremers_et_al:DagRep.7.9.109,
  author =	{Cremers, Daniel and Leal-Taix\'{e}, Laura and Vidal, Ren\'{e}},
  title =	{{Deep Learning for Computer Vision (Dagstuhl Seminar 17391)}},
  pages =	{109--125},
  journal =	{Dagstuhl Reports},
  ISSN =	{2192-5283},
  year =	{2018},
  volume =	{7},
  number =	{9},
  editor =	{Cremers, Daniel and Leal-Taix\'{e}, Laura and Vidal, Ren\'{e}},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagRep.7.9.109},
  URN =		{urn:nbn:de:0030-drops-85912},
  doi =		{10.4230/DagRep.7.9.109},
  annote =	{Keywords: computer vision, convolutional networks, deep learning, machine learning}
}
Document
DOI: 10.4230/DagSemProc.10411.1
10411 Abstracts Collection – Computational Video

Authors: Daniel Cremers, Marcus A. Magnor, and Lihi Zelnik-Manor

Published in: Dagstuhl Seminar Proceedings, Volume 10411, Computational Video (2011)

Abstract
From 10.10.2010 to 15.10.2010, the Dagstuhl Seminar 10411 ``Computational Video '' was held in Schloss Dagstuhl~--~Leibniz Center for Informatics. During the seminar, several participants presented their current research, and ongoing work and open problems were discussed. Abstracts of the presentations given during the seminar as well as abstracts of seminar results and ideas are put together in this paper. The first section describes the seminar topics and goals in general. Links to extended abstracts or full papers are provided, if available.
Cite as

Daniel Cremers, Marcus A. Magnor, and Lihi Zelnik-Manor. 10411 Abstracts Collection – Computational Video. In Computational Video. Dagstuhl Seminar Proceedings, Volume 10411, pp. 1-22, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2011)

Copy BibTex To Clipboard

@InProceedings{cremers_et_al:DagSemProc.10411.1,
  author =	{Cremers, Daniel and Magnor, Marcus A. and Zelnik-Manor, Lihi},
  title =	{{10411 Abstracts Collection – Computational Video }},
  booktitle =	{Computational Video},
  pages =	{1--22},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2011},
  volume =	{10411},
  editor =	{Daniel Cremers and Marcus A. Magnor and Lihi Zelnik-Manor},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.10411.1},
  URN =		{urn:nbn:de:0030-drops-29195},
  doi =		{10.4230/DagSemProc.10411.1},
  annote =	{Keywords: Video Processing, Image Processing, Computer Vision}
}
Document
DOI: 10.4230/DagSemProc.10411.2
10411 Executive Summary – Computational Video

Authors: Daniel Cremers, Marcus A. Magnor, and Lihi Zelnik-Manor

Published in: Dagstuhl Seminar Proceedings, Volume 10411, Computational Video (2011)

Abstract
Dagstuhl seminar 10411 "Computational Video" took place October 10-15, 2010. 43 researchers from North America, Asia, and Europe discussed the state- of-the-art, contemporary challenges and future research in imaging, processing, analyzing, modeling, and rendering of real-world, dynamic scenes. The seminar was organized into 11 sessions of presentations, discussions, and special-topic meetings. The seminar brought together junior and senior researchers from computer vision, computer graphics, and image communication, both from academia and industry to address the challenges in computational video. Participants included international experts from Kyoto University, Stanford University, University of British Columbia, University of New Mexico, University of Toronto, MIT, Hebrew University of Jerusalem, Technion - Haifa, ETH Zrich, Heriot-Watt Uni- versity - Edinburgh, University of Surrey, and University College London as well as professionals from Adobe Systems, BBC Research & Development, Disney Research and Microsoft Research.
Cite as

Daniel Cremers, Marcus A. Magnor, and Lihi Zelnik-Manor. 10411 Executive Summary – Computational Video. In Computational Video. Dagstuhl Seminar Proceedings, Volume 10411, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2011)

Copy BibTex To Clipboard

@InProceedings{cremers_et_al:DagSemProc.10411.2,
  author =	{Cremers, Daniel and Magnor, Marcus A. and Zelnik-Manor, Lihi},
  title =	{{10411 Executive Summary – Computational Video}},
  booktitle =	{Computational Video},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2011},
  volume =	{10411},
  editor =	{Daniel Cremers and Marcus A. Magnor and Lihi Zelnik-Manor},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.10411.2},
  URN =		{urn:nbn:de:0030-drops-29208},
  doi =		{10.4230/DagSemProc.10411.2},
  annote =	{Keywords: Video Processing, Image Processing, Computer Vision}
}
Document
DOI: 10.4230/DagSemProc.08291.1
08291 Abstracts Collection – Statistical and Geometrical Approaches to Visual Motion Analysis

Authors: Daniel Cremers, Bodo Rosenhahn, and Alan L. Yuille

Published in: Dagstuhl Seminar Proceedings, Volume 8291, Statistical and Geometrical Approaches to Visual Motion Analysis (2008)

Abstract
From 13.07.2008 to 18.07.2008, the Dagstuhl Seminar 08291 ``Statistical and Geometrical Approaches to Visual Motion Analysis'' was held in the International Conference and Research Center (IBFI), Schloss Dagstuhl. During the seminar, several participants presented their current research, and ongoing work and open problems were discussed. Abstracts of the presentations given during the seminar as well as abstracts of seminar results and ideas are put together in this paper. The first section describes the seminar topics and goals in general.
Cite as

Daniel Cremers, Bodo Rosenhahn, and Alan L. Yuille. 08291 Abstracts Collection – Statistical and Geometrical Approaches to Visual Motion Analysis. In Statistical and Geometrical Approaches to Visual Motion Analysis. Dagstuhl Seminar Proceedings, Volume 8291, pp. 1-19, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2008)

Copy BibTex To Clipboard

@InProceedings{cremers_et_al:DagSemProc.08291.1,
  author =	{Cremers, Daniel and Rosenhahn, Bodo and Yuille, Alan L.},
  title =	{{08291 Abstracts Collection – Statistical and Geometrical Approaches to Visual Motion Analysis}},
  booktitle =	{Statistical and Geometrical Approaches to Visual Motion Analysis},
  pages =	{1--19},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2008},
  volume =	{8291},
  editor =	{Daniel Cremers and Bodo Rosenhahn and Alan L. Yuille},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.08291.1},
  URN =		{urn:nbn:de:0030-drops-16206},
  doi =		{10.4230/DagSemProc.08291.1},
  annote =	{Keywords: Motion Segmentation, Statistical Methods, Computational Geometry}
}
Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail
© 2023-2024 Schloss Dagstuhl – LZI GmbH About DROPS Imprint Privacy Contact