• English
  • Deutsch
  • Log In
    Password Login
    Research Outputs
    Fundings & Projects
    Researchers
    Institutes
    Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Konferenzschrift
  4. Discriminative structure learning of hierarchical representations for object detection
 
  • Details
  • Full
Options
2009
Conference Paper
Title

Discriminative structure learning of hierarchical representations for object detection

Abstract
A variety of flexible models have been proposed to detect objects in challenging real world scenes. Motivated by some of the most successful techniques, we propose a hierarchical multi-feature representation and automatically learn flexible hierarchical object models for a wide variety of object classes. To that end we not only rely on automatic selection of relevant individual features, but go beyond previous work by automatically selecting and modeling complex, long-range feature couplings within this model. To achieve this generality and flexibility our work combines structure learning in conditional random fields and discriminative parameter learning of classifiers using hierarchical features. We adopt an efficient gradient based heuristic for model selection and carry it forward to discriminative, multidimensional selection of features and their couplings for improved detection performance. Experimentally we consistently outperform the currently leading method on all 20 classes of the PASCAL VOC 2007 challenge and achieve the best published results on 16 of 20 classes.
Author(s)
Schnitzspan, Paul
TU Darmstadt
Fritz, Mario
UC Berkeley
Roth, Stefan
TU Darmstadt GRIS
Schiele, Bernt
TU Darmstadt
Mainwork
IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009. DVD-ROM  
Conference
Conference on Computer Vision and Pattern Recognition (CVPR) 2009  
DOI
10.1109/CVPR.2009.5206544
Language
English
Fraunhofer-Institut für Graphische Datenverarbeitung IGD  
Keyword(s)
  • computer vision

  • object recognition

  • graphical modelling

  • structure learning

  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Contact
© 2024