default search action
Thomas Deselaers
Person information
- affiliation: Google Switzerland
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
Books and Theses
- 2008
- [b1]Thomas Deselaers:
Image retrieval, object recognition, and discriminative models. RWTH Aachen University, Germany, 2008, pp. I-X, 1-205
Journal Articles
- 2020
- [j14]Victor Carbune, Pedro Gonnet, Thomas Deselaers, Henry A. Rowley, Alexander N. Daryin, Marcos Calvo, Li-Lun Wang, Daniel Keysers, Sandro Feuz, Philippe Gervais:
Fast multi-language LSTM-based online handwriting recognition. Int. J. Document Anal. Recognit. 23(2): 89-102 (2020) - 2017
- [j13]Daniel Keysers, Thomas Deselaers, Henry A. Rowley, Li-Lun Wang, Victor Carbune:
Multi-Language Online Handwriting Recognition. IEEE Trans. Pattern Anal. Mach. Intell. 39(6): 1180-1194 (2017) - 2015
- [j12]Thomas Deselaers, Daniel Keysers, Jan Hendrik Hosang, Henry A. Rowley:
GyroPen: Gyroscopes for Pen-Input With Mobile Phones. IEEE Trans. Hum. Mach. Syst. 45(2): 263-271 (2015) - 2012
- [j11]Thomas Deselaers, Bogdan Alexe, Vittorio Ferrari:
Weakly Supervised Localization and Learning with Generic Knowledge. Int. J. Comput. Vis. 100(3): 275-293 (2012) - [j10]Thomas Deselaers, Tobias Gass, Georg Heigold, Hermann Ney:
Latent Log-Linear Models for Handwritten Digit Classification. IEEE Trans. Pattern Anal. Mach. Intell. 34(6): 1105-1117 (2012) - [j9]Bogdan Alexe, Thomas Deselaers, Vittorio Ferrari:
Measuring the Objectness of Image Windows. IEEE Trans. Pattern Anal. Mach. Intell. 34(11): 2189-2202 (2012) - 2010
- [j8]Thomas Deselaers, Georg Heigold, Hermann Ney:
Object classification by fusing SVMs and Gaussian mixtures. Pattern Recognit. 43(7): 2476-2484 (2010) - 2008
- [j7]Thomas Deselaers, Daniel Keysers, Hermann Ney:
Features for image retrieval: an experimental comparison. Inf. Retr. 11(2): 77-107 (2008) - [j6]Abebe Rorissa, Paul D. Clough, Thomas Deselaers:
Exploring the relationship between feature and perceptual visual spaces. J. Assoc. Inf. Sci. Technol. 59(5): 770-784 (2008) - [j5]Thomas Deselaers, Henning Müller, Thomas Martin Deserno:
Editorial to the Special Issue on Medical Image Annotation in ImageCLEF 2007. Pattern Recognit. Lett. 29(15): 1987 (2008) - [j4]Thomas Deselaers, Thomas Martin Deserno, Henning Müller:
Automatic medical image annotation in ImageCLEF 2007: Overview, results, and discussion. Pattern Recognit. Lett. 29(15): 1988-1995 (2008) - [j3]Thomas Deselaers, Hermann Ney:
Deformations, patches, and discriminative models for automatic annotation of medical radiographs. Pattern Recognit. Lett. 29(15): 2003-2010 (2008) - 2007
- [j2]Thomas Deselaers, Henning Müller, Paul D. Clough, Hermann Ney, Thomas Martin Lehmann:
The CLEF 2005 Automatic Medical Image Annotation Task. Int. J. Comput. Vis. 74(1): 51-58 (2007) - [j1]Daniel Keysers, Thomas Deselaers, Christian Gollan, Hermann Ney:
Deformation Models for Image Recognition. IEEE Trans. Pattern Anal. Mach. Intell. 29(8): 1422-1435 (2007)
Conference and Workshop Papers
- 2022
- [c68]Jen-Hao Rick Chang, Martin Bresler, Youssouf Chherawala, Adrien Delaye, Thomas Deselaers, Ryan S. Dixon, Oncel Tuzel:
Data Incubation - Synthesizing Missing Data for Handwriting Recognition. ICASSP 2022: 4188-4192 - 2020
- [c67]Pedro Gonnet, Thomas Deselaers:
Indylstms: Independently Recurrent LSTMS. ICASSP 2020: 3352-3356 - [c66]Emre Aksan, Thomas Deselaers, Andrea Tagliasacchi, Otmar Hilliges:
CoSE: Compositional Stroke Embeddings. NeurIPS 2020 - 2019
- [c65]R. Reeve Ingle, Yasuhisa Fujii, Thomas Deselaers, Jonathan Baccash, Ashok C. Popat:
A Scalable Handwritten Text Recognition System. ICDAR 2019: 17-24 - 2011
- [c64]Thomas Deselaers, Vittorio Ferrari:
Visual and semantic similarity in ImageNet. CVPR 2011: 1777-1784 - 2010
- [c63]Bogdan Alexe, Thomas Deselaers, Vittorio Ferrari:
What is an object? CVPR 2010: 73-80 - [c62]Thomas Deselaers, Vittorio Ferrari:
Global and efficient self-similarity for object classification and detection. CVPR 2010: 1633-1640 - [c61]Bogdan Alexe, Thomas Deselaers, Vittorio Ferrari:
ClassCut for Unsupervised Class Segmentation. ECCV (5) 2010: 380-393 - [c60]Thomas Deselaers, Bogdan Alexe, Vittorio Ferrari:
Localizing Objects While Learning Their Appearance. ECCV (4) 2010: 452-466 - [c59]Thomas Deselaers, Vittorio Ferrari:
A Conditional Random Field for Multiple-Instance Learning. ICML 2010: 287-294 - 2009
- [c58]Tobias Weyand, Thomas Deselaers, Hermann Ney:
Log-Linear Mixtures for Object Class Recognition. BMVC 2009: 1-11 - [c57]Thomas Deselaers, Tobias Gass, Philippe Dreuw, Hermann Ney:
Jointly optimising relevance and diversity in image retrieval. CIVR 2009 - [c56]Tobias Gass, Thomas Deselaers, Hermann Ney:
Deformation-Aware Log-Linear Models. DAGM-Symposium 2009: 201-210 - [c55]Philippe Dreuw, Pascal Steingrube, Thomas Deselaers, Hermann Ney:
Smoothed Disparity Maps for Continuous American Sign Language Recognition. IbPRIA 2009: 24-31 - [c54]Heiko Roßnagel, Jan Zibuschka, Lexi Pimenidis, Thomas Deselaers:
Facilitating the Adoption of Tor by Focusing on a Promising Target Group. NordSec 2009: 15-27 - [c53]Thomas Deselaers, Sasa Hasan, Oliver Bender, Hermann Ney:
A Deep Learning Approach to Machine Transliteration. WMT@EACL 2009: 233-241 - 2008
- [c52]Thomas Deselaers, Thomas Martin Deserno:
Medical Image Annotation in ImageCLEF 2008. CLEF 2008: 523-530 - [c51]Thomas Deselaers, Thomas Martin Deserno:
Medical Image Annotation in ImageCLEF 2008. CLEF (Working Notes) 2008 - [c50]Thomas Deselaers, Allan Hanbury:
The Visual Concept Detection Task in ImageCLEF 2008. CLEF 2008: 531-538 - [c49]Thomas Deselaers, Allan Hanbury:
The Visual Concept Detection Task in ImageCLEF 2008. CLEF (Working Notes) 2008 - [c48]Thomas Deselaers, Philippe Dreuw, Hermann Ney:
Pan, zoom, scan - Time-coherent, trained automatic video cropping. CVPR 2008 - [c47]Philippe Dreuw, Jens Forster, Thomas Deselaers, Hermann Ney:
Efficient approximations to model-based joint tracking and recognition of continuous sign language. FG 2008: 1-6 - [c46]Georg Heigold, Thomas Deselaers, Ralf Schlüter, Hermann Ney:
A GIS-like training algorithm for log-linear models with hidden variables. ICASSP 2008: 4045-4048 - [c45]Georg Heigold, Thomas Deselaers, Ralf Schlüter, Hermann Ney:
Modified MMI/MPE: a direct evaluation of the margin in speech recognition. ICML 2008: 384-391 - [c44]Vaishak Belle, Thomas Deselaers, Stefan Schiffer:
Randomized trees for real-time one-step face detection and recognition. ICPR 2008: 1-4 - [c43]Thomas Deselaers, Georg Heigold, Hermann Ney:
SVMs, Gaussian mixtures, and their generative/discriminative fusion. ICPR 2008: 1-4 - [c42]Thomas Deselaers, Lexi Pimenidis, Hermann Ney:
Bag-of-visual-words models for adult image classification and filtering. ICPR 2008: 1-4 - [c41]Thomas Deselaers, Roberto Paredes, Enrique Vidal, Hermann Ney:
Learning weighted distances for relevance feedback in image retrieval. ICPR 2008: 1-4 - [c40]Roberto Paredes, Thomas Deselaers, Enrique Vidal:
A Probabilistic Model for User Relevance Feedback on Image Retrieval. MLMI 2008: 260-271 - 2007
- [c39]Thomas Deselaers, Tobias Gass, Tobias Weyand, Hermann Ney:
FIRE in ImageCLEF 2007. CLEF (Working Notes) 2007 - [c38]Thomas Deselaers, Allan Hanbury, Ville Viitaniemi, András A. Benczúr, Mátyás Brendel, Bálint Daróczy, Hugo Jair Escalante Balderas, Theo Gevers, Carlos Arturo Hernández-Gracidas, Steven C. H. Hoi, Jorma Laaksonen, Mingjing Li, Heidy Marisol Marín-Castro, Hermann Ney, Xiaoguang Rui, Nicu Sebe, Julian Stöttinger, Lei Wu:
Overview of the ImageCLEF 2007 Object Retrieval Task. CLEF 2007: 445-471 - [c37]Thomas Deselaers, Allan Hanbury, Ville Viitaniemi, András A. Benczúr, Mátyás Brendel, Bálint Daróczy, Hugo Jair Escalante Balderas, Theo Gevers, Carlos Arturo Hernández-Gracidas, Steven C. H. Hoi, Jorma Laaksonen, Mingjing Li, Heidy Marisol Marín-Castro, Hermann Ney, Xiaoguang Rui, Nicu Sebe, Julian Stöttinger, Lei Wu:
Overview of the ImageCLEF 2007 Object Retrieval Task. CLEF (Working Notes) 2007 - [c36]Henning Müller, Thomas Deselaers, Thomas Martin Deserno, Jayashree Kalpathy-Cramer, Eugene Kim, William R. Hersh:
Overview of the ImageCLEFmed 2007 Medical Retrieval and Medical Annotation Tasks. CLEF 2007: 472-491 - [c35]Tobias Gass, Tobias Weyand, Thomas Deselaers, Hermann Ney:
FIRE in ImageCLEF 2007: Support Vector Machines and Logistic Models to Fuse Image Descriptors for Photo Retrieval. CLEF 2007: 492-499 - [c34]Henning Müller, Thomas Deselaers, Eugene Kim, Jayashree Kalpathy-Cramer, Thomas Martin Deserno, William R. Hersh:
Overview of the ImageCLEF 2007 Medical Retrieval and Annotation Tasks. CLEF (Working Notes) 2007 - [c33]Thomas Deselaers, Antonio Criminisi, John M. Winn, Ankur Agarwal:
Incorporating On-demand Stereo for Real Time Recognition. CVPR 2007 - [c32]Thomas Deselaers, Georg Heigold, Hermann Ney:
Speech recognition with state-based nearest neighbour classifiers. INTERSPEECH 2007: 2093-2096 - [c31]Philippe Dreuw, David Rybach, Thomas Deselaers, Morteza Zahedi, Hermann Ney:
Speech recognition techniques for a sign language recognition system. INTERSPEECH 2007: 2513-2516 - 2006
- [c30]Andre Hegerath, Thomas Deselaers, Hermann Ney:
Patch-based Object Recognition Using Discriminatively Trained Gaussian Mixtures. BMVC 2006: 519-528 - [c29]Morteza Zahedi, Philippe Dreuw, David Rybach, Thomas Deselaers, Hermann Ney:
Geometric Features for Improving Continuous Appearance-based Sign Language Recognition. BMVC 2006: 1019-1028 - [c28]Paul D. Clough, Michael Grubinger, Thomas Deselaers, Allan Hanbury, Henning Müller:
Overview of the ImageCLEF 2006 Photographic Retrieval and Object Annotation Tasks. CLEF 2006: 579-594 - [c27]Paul D. Clough, Michael Grubinger, Thomas Deselaers, Allan Hanbury, Henning Müller:
Overview of the ImageCLEF 2006 Photographic Retrieval and Object Annotation Tasks. CLEF (Working Notes) 2006 - [c26]Henning Müller, Thomas Deselaers, Thomas Martin Deserno, Paul D. Clough, Eugene Kim, William R. Hersh:
Overview of the ImageCLEFmed 2006 Medical Retrieval and Medical Annotation Tasks. CLEF 2006: 595-608 - [c25]Thomas Deselaers, Tobias Weyand, Hermann Ney:
Image Retrieval and Annotation Using Maximum Entropy. CLEF 2006: 725-734 - [c24]Thomas Deselaers, Tobias Weyand, Hermann Ney:
Image Retrieval and Annotation Using Maximum Entropy. CLEF (Working Notes) 2006 - [c23]Henning Müller, Thomas Deselaers, Thomas Martin Lehmann, Paul D. Clough, Eugene Kim, William R. Hersh:
Overview of the ImageCLEFmed 2006 Medical Retrieval and Annotation Tasks. CLEF (Working Notes) 2006 - [c22]Thomas Deselaers, Andre Hegerath, Daniel Keysers, Hermann Ney:
Sparse Patch-Histograms for Object Classification in Cluttered Images. DAGM-Symposium 2006: 202-211 - [c21]Philippe Dreuw, Thomas Deselaers, David Rybach, Daniel Keysers, Hermann Ney:
Tracking Using Dynamic Programming for Appearance-Based Sign Language Recognition. FGR 2006: 293-298 - 2005
- [c20]Paul D. Clough, Henning Müller, Thomas Deselaers, Michael Grubinger, Thomas Martin Lehmann, Jeffery R. Jensen, William R. Hersh:
The CLEF 2005 Cross-Language Image Retrieval Track. CLEF 2005: 535-557 - [c19]Paul D. Clough, Henning Müller, Thomas Deselaers, Michael Grubinger, Thomas Martin Lehmann, Jeffery R. Jensen, William R. Hersh:
The CLEF 2005 Cross-Language Image Retrieval Track. CLEF (Working Notes) 2005 - [c18]Thomas Deselaers, Tobias Weyand, Daniel Keysers, Wolfgang Macherey, Hermann Ney:
FIRE in ImageCLEF 2005: Combining Content-Based Image Retrieval with Textual Information Retrieval. CLEF 2005: 652-661 - [c17]Thomas Deselaers, Tobias Weyand, Daniel Keysers, Wolfgang Macherey, Hermann Ney:
FIRE in ImageCLEF 2005: Combining Content-based Image Retrieval with Textual Information Retrieval. CLEF (Working Notes) 2005 - [c16]Thomas Deselaers, Daniel Keysers, Hermann Ney:
Discriminative Training for Object Recognition Using Image Patches. CVPR (2) 2005: 157-162 - [c15]Thomas Deselaers, Daniel Keysers, Hermann Ney:
Improving a Discriminative Approach to Object Recognition Using Image Patches. DAGM-Symposium 2005: 326-333 - [c14]Morteza Zahedi, Daniel Keysers, Thomas Deselaers, Hermann Ney:
Combination of Tangent Distance and an Image Distortion Model for Appearance-Based Sign Language Recognition. DAGM-Symposium 2005: 401-408 - [c13]Jens Strackeljan, Roland Jonscher, Sigurd Prieur, David Vogel, Thomas Deselaers, Daniel Keysers, Arne Mauser, Ilja Bezrukov, Andre Hegerath:
GfKl Data Mining Competition 2005: Predicting Liquidity Crises of Companies. GfKl 2005: 748-758 - [c12]Philippe Dreuw, Daniel Keysers, Thomas Deselaers, Hermann Ney:
Gesture Recognition Using Image Comparison Methods. Gesture Workshop 2005: 124-128 - [c11]Arne Mauser, Ilja Bezrukov, Thomas Deselaers, Daniel Keysers:
Predicting Customer Behavior using Naive Bayes and Maximum Entrop. Informatiktage 2005: 143-146 - [c10]Mark Everingham, Andrew Zisserman, Christopher K. I. Williams, Luc Van Gool, Moray Allan, Christopher M. Bishop, Olivier Chapelle, Navneet Dalal, Thomas Deselaers, Gyuri Dorkó, Stefan Duffner, Jan Eichhorn, Jason D. R. Farquhar, Mario Fritz, Christophe Garcia, Tom Griffiths, Frédéric Jurie, Daniel Keysers, Markus Koskela, Jorma Laaksonen, Diane Larlus, Bastian Leibe, Hongying Meng, Hermann Ney, Bernt Schiele, Cordelia Schmid, Edgar Seemann, John Shawe-Taylor, Amos J. Storkey, Sándor Szedmák, Bill Triggs, Ilkay Ulusoy, Ville Viitaniemi, Jianguo Zhang:
The 2005 PASCAL Visual Object Classes Challenge. MLCW 2005: 117-176 - [c9]Henning Müller, Paul D. Clough, William R. Hersh, Thomas Deselaers, Thomas Martin Lehmann, Antoine Geissbühler:
Evaluation axes for medical image retrieval systems: the imageCLEF experience. ACM Multimedia 2005: 1014-1022 - 2004
- [c8]Thomas Deselaers, Daniel Keysers, Hermann Ney:
FIRE - Flexible Image Retrieval Engine: ImageCLEF 2004 Evaluation. CLEF (Working Notes) 2004 - [c7]Thomas Deselaers, Daniel Keysers, Hermann Ney:
FIRE - Flexible Image Retrieval Engine: ImageCLEF 2004 Evaluation. CLEF 2004: 688-698 - [c6]Daniel Keysers, Thomas Deselaers, Hermann Ney:
Pixel-to-Pixel Matching for Image Recognition Using Hungarian Graph Matching. DAGM-Symposium 2004: 154-162 - [c5]Thomas Deselaers, Daniel Keysers, Hermann Ney:
Features for Image Retrieval: A Quantitative Comparison. DAGM-Symposium 2004: 228-236 - [c4]Thomas Deselaers, Daniel Keysers, Hermann Ney:
Classification Error Rate for Quantitative Evaluation of Content-based Image Retrieval Systems. ICPR (2) 2004: 505-508 - [c3]Thomas Martin Lehmann, Mark Oliver Güld, Daniel Keysers, Thomas Deselaers, Henning Schubert, Berthold B. Wein, Klaus Spitzer:
Similarity of Medical Images Computed from Global Feature Vectors for Content-Based Retrieval. KES 2004: 989-995 - 2003
- [c2]Daniel Keysers, Michael Motter, Thomas Deselaers, Hermann Ney:
Training and Recognition of Complex Scenes Using a Holistic Statistical Model. DAGM-Symposium 2003: 52-59 - [c1]Thomas Deselaers, Daniel Keysers, Roberto Paredes, Enrique Vidal, Hermann Ney:
Local Representations for Multi-object Recognition. DAGM-Symposium 2003: 305-312
Parts in Books or Collections
- 2010
- [p3]Stefanie Nowak, Allan Hanbury, Thomas Deselaers:
Object and Concept Recognition for Image Retrieval. ImageCLEF 2010: 199-219 - [p2]Tatiana Tommasi, Thomas Deselaers:
The Medical Image Classification Task. ImageCLEF 2010: 221-238 - 2008
- [p1]Thomas Deselaers:
Bildsuche, Objekterkennung und Diskriminative Modelle [Image Retrieval, Object Recognition, and Discriminative Models]. Ausgezeichnete Informatikdissertationen 2008: 51-60
Editorship
- 2010
- [e2]Henning Müller, Paul D. Clough, Thomas Deselaers, Barbara Caputo:
ImageCLEF, Experimental Evaluation in Visual Information Retrieval. Springer 2010, ISBN 978-3-642-15180-4 [contents] - 2009
- [e1]Carol Peters, Thomas Deselaers, Nicola Ferro, Julio Gonzalo, Gareth J. F. Jones, Mikko Kurimo, Thomas Mandl, Anselmo Peñas, Vivien Petras:
Evaluating Systems for Multilingual and Multimodal Information Access, 9th Workshop of the Cross-Language Evaluation Forum, CLEF 2008, Aarhus, Denmark, September 17-19, 2008, Revised Selected Papers. Lecture Notes in Computer Science 5706, Springer 2009, ISBN 978-3-642-04446-5 [contents]
Informal and Other Publications
- 2021
- [i7]Jen-Hao Rick Chang, Martin Bresler, Youssouf Chherawala, Adrien Delaye, Thomas Deselaers, Ryan S. Dixon, Oncel Tuzel:
Data Incubation - Synthesizing Missing Data for Handwriting Recognition. CoRR abs/2110.07040 (2021) - 2020
- [i6]Philippe Gervais, Thomas Deselaers, Emre Aksan, Otmar Hilliges:
The DIDI dataset: Digital Ink Diagram data. CoRR abs/2002.09303 (2020) - [i5]Emre Aksan, Thomas Deselaers, Andrea Tagliasacchi, Otmar Hilliges:
CoSE: Compositional Stroke Embeddings. CoRR abs/2006.09930 (2020) - 2019
- [i4]Victor Carbune, Pedro Gonnet, Thomas Deselaers, Henry A. Rowley, Alexander N. Daryin, Marcos Calvo, Li-Lun Wang, Daniel Keysers, Sandro Feuz, Philippe Gervais:
Fast Multi-language LSTM-based Online Handwriting Recognition. CoRR abs/1902.10525 (2019) - [i3]Pedro Gonnet, Thomas Deselaers:
IndyLSTMs: Independently Recurrent LSTMs. CoRR abs/1903.08023 (2019) - [i2]R. Reeve Ingle, Yasuhisa Fujii, Thomas Deselaers, Jonathan Baccash, Ashok C. Popat:
A Scalable Handwritten Text Recognition System. CoRR abs/1904.09150 (2019) - 2018
- [i1]Victor Carbune, Thierry Coppey, Alexander N. Daryin, Thomas Deselaers, Nikhil Sarda, Jay Yagnik:
Predicted Variables in Programming. CoRR abs/1810.00619 (2018)
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from , , and to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from .
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-10-30 21:30 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint