Thomas Deselaers

Before joining Google in October 2010, Thomas Deselaers was a postdoctoral researcher in the Computer Vision Laboratory of ETH Zurich. He received his diploma and PhD degrees from RWTH Aachen University in 2004 and 2008. He is interested in machine learning and computer vision problems.

Google Publications

Previous Publications

  •  

    Latent Log-Linear Models for Handwritten Digit Classification

    Thomas Deselaers, Tobias Gass, Georg Heigold

    IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 34/6 (2012), pp. 1105-1117

  •   

    Weakly Supervised Localization and Learning with Generic Knowledge

    Thomas Deselaers, Bogdan Alexe, Vittorio Ferrari

    International Journal of Computer Vision, vol. 100, no. 3 (2012), pp. 257-293

  •  

    A conditional random field for multiple-instance learning

    Thomas Deselaers, Vittorio Ferrari

    International Conference on Machine Learning (2010)

  •  

    ClassCut for Unsupervised Class Segmentation

    Bogdan Alexe, Thomas Deselaers, Vittorio Ferrari

    European Conference on Computer Vision (ECCV) (2010), pp. 380-393

  •  

    Global and Efficient Self-Similarity for Object Classification and Detection

    Thomas Deselaers, Vittorio Ferrari

    IEEE Computer Vision and Pattern Recognition (CVPR) (2010)

  •  

    Localizing Objects while Learning Their Appearance

    Thomas Deselaers, Bogdan Alexe, Vittorio Ferrari

    European Conference on Computer Vision (ECCV) (2010), pp. 452-466

  •  

    What is an object

    Bogdan Alexe, Thomas Deselaers, Vittorio Ferrari

    IEEE Computer Vision and Pattern Recognition (CVPR) (2010)

  •  

    Features for image retrieval: an experimental comparison

    Thomas Deselaers, Daniel Keysers, Hermann Ney

    Information Retrieval, vol. 11 (2008), pp. 77-107

  •  

    Pan, Zoom, Scan - Time-coherent, Trained Automatic Video Cropping

    Thomas Deselaers, Philippe Dreuw, Hermann Ney

    IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2008)

  •  

    Spoken Language Processing Techniques for Sign Language Recognition and Translation.

    Philippe Dreuw, Daniel Stein, Thomas Deselaers, David Rybach, Morteza Zahedi, Jan Bungeroth, Hermann Ney

    Technology and Dissability, vol. 20 (2008), pp. 121-133

  •   

    Deformation models for image recognition

    Daniel Keysers, Thomas Deselaers, Christian Gollan, Hermann Ney

    Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 29 (2007), pp. 1422-1435

  •  

    Incorporating on-demand stereo for real time recognition

    Thomas Deselaers, Antonio Criminisi, John Winn, Ankur Agarwal

    International Conference on Computer Vision and Pattern Recognition (CVPR), IEEE (2007)

  •  

    Speech Recognition with State-based Nearest Neighbour Classifiers.

    Thomas Deselaers, Georg Heigold, Hermann Ney

    Interspeech (2007), pp. 2093-2096

  •  

    Discriminative Training for Object Recognition using Image Patches

    Thomas Deselaers, Daniel Keysers, Hermann Ney

    IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2005)

  •  

    Improving a Discriminative Approach to Object Recognition using Image Patches.

    Thomas Deselaers, Daniel Keysers, Hermann Ney

    Pattern Recognition (DAGM) (2005)