Object localization with global and local context kernels Conference Paper


Author(s): Blaschko, Matthew B; Lampert, Christoph
Title: Object localization with global and local context kernels
Title Series: Proceedings of the BMVC
Affiliation
Abstract: 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.
Conference Title: BMVC: British Machine Vision Conference
Conference Dates: September 7-10, 2009
Conference Location: London, UK
ISBN: 1-901725-39-1
Publisher: BMVA Press  
Date Published: 2009-09-10
Start Page: 1
End Page: 11
Copyright Statement: CC BY ⓒ 2009. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms.
URL:
DOI: 10.5244/C.23.63
Notes: The research leading to these results has received funding from the European Research Council under the European Community’s Seventh Framework Programme (FP7/2007- 2013) / ERC grant agreement no. 228180. This work was funded in part by the EC project CLASS, IST 027978, and the PASCAL2 network of excellence. The first author is supported by the Royal Academy of Engineering through a Newton International Fellowship.
Open access: no
IST Austria Authors
  1. Christoph Lampert
    88 Lampert
Related IST Austria Work