Header logo is

Object Localization with Global and Local Context Kernels


Conference Paper


Recent research has shown that the use of contextual cues significantly improves performance in sliding window type localization systems. In this work, we propose a method that incorporates both global and local context information through appropriately defined kernel functions. In particular, we make use of a weighted combination of kernels defined over local spatial regions, as well as a global context kernel. The relative importance of the context contributions is learned automatically, and the resulting discriminant function is of a form such that localization at test time can be solved efficiently using a branch and bound optimization scheme. By specifying context directly with a kernel learning approach, we achieve high localization accuracy with a simple and efficient representation. This is in contrast to other systems that incorporate context for which expensive inference needs to be done at test time. We show experimentally on the PASCAL VOC datasets that the inclusion of context can significantly improve localization performance, provided the relative contributions of context cues are learned appropriately.

Author(s): Blaschko, M. and Lampert, CH.
Book Title: British Machine Vision Conference 2009
Journal: Proceedings of the British Machine Vision Conference 2009 (BMVC 2009)
Pages: 1-11
Year: 2009
Month: September
Day: 0

Department(s): Empirical Inference
Bibtex Type: Conference Paper (inproceedings)

Event Name: BMVC 2009
Event Place: London, UK

Language: en
Organization: Max-Planck-Gesellschaft
School: Biologische Kybernetik

Links: PDF


  title = {Object Localization with Global and Local Context Kernels},
  author = {Blaschko, M. and Lampert, CH.},
  journal = {Proceedings of the British Machine Vision Conference 2009 (BMVC 2009)},
  booktitle = {British Machine Vision Conference 2009},
  pages = {1-11},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  month = sep,
  year = {2009},
  month_numeric = {9}