Convex Optimization for Scene Understanding

TitleConvex Optimization for Scene Understanding
Publication TypeConference Paper
Year of Publication2013
AuthorsSouiai, M., Nieuwenhuis C., Strekalovskiy E., & Cremers D.
Other Numbers3625

In this paper we give a convex optimization approach forscene understanding. Since segmentation, object recognition and scene labeling strongly benefit from each other wepropose to solve these tasks within a single convex optimization problem. In contrast to previous approaches we do notrely on pre-processing techniques such as object detectorsor superpixels. The central idea is to integrate a hierarchical label prior and a set of convex constraints into thesegmentation approach, which combine the three tasks byintroducing high-level scene information. Instead of learning label co-occurrences from limited benchmark trainingdata, the hierarchical prior comes naturally with the wayhumans see their surroundings.


This work was partially funded by the Deutscher Akademischer Austausch Dienst (DAAD) through a postdoctoral fellowship.

Bibliographic Notes

Proceedings of the Workshop on Graphical Models for Scene Understanding at the International Conference on Computer Vision 2013 (ICCV 2013), Sydney, Australia

Abbreviated Authors

M. Souiai, C. Nieuwenhuis, E. Strekalovskiy, and D. Cremers

ICSI Research Group


ICSI Publication Type

Article in conference proceedings