Convex Optimization for Scene Understanding

Abstract

In this paper we give a convex optimization approach for scene understanding. Since segmentation, object recognition and scene labeling strongly benefit from each other we propose to solve these tasks within a single convex optimization problem. In contrast to previous approaches we do not rely on pre-processing techniques such as object detectors or super pixels. The central idea is to integrate a hierarchical label prior and a set of convex constraints into the segmentation approach, which combine the three tasks by introducing high-level scene information. Instead of learning label co-occurrences from limited benchmark training data, the hierarchical prior comes naturally with the way humans see their surroundings.

Cite

Text

Souiai et al. "Convex Optimization for Scene Understanding." IEEE/CVF International Conference on Computer Vision Workshops, 2013. doi:10.1109/ICCVW.2013.131

Markdown

[Souiai et al. "Convex Optimization for Scene Understanding." IEEE/CVF International Conference on Computer Vision Workshops, 2013.](https://mlanthology.org/iccvw/2013/souiai2013iccvw-convex/) doi:10.1109/ICCVW.2013.131

BibTeX

@inproceedings{souiai2013iccvw-convex,
  title     = {{Convex Optimization for Scene Understanding}},
  author    = {Souiai, Mohamed and Nieuwenhuis, Claudia and Strekalovskiy, Evgeny and Cremers, Daniel},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2013},
  pages     = {9-14},
  doi       = {10.1109/ICCVW.2013.131},
  url       = {https://mlanthology.org/iccvw/2013/souiai2013iccvw-convex/}
}