Object Detection and Segmentation from Joint Embedding of Parts and Pixels

Abstract

We present a new framework in which image segmentation, figure/ground organization, and object detection all appear as the result of solving a single grouping problem. This framework serves as a perceptual organization stage that integrates information from low-level image cues with that of high-level part detectors. Pixels and parts each appear as nodes in a graph whose edges encode both affinity and ordering relationships. We derive a generalized eigen-problem from this graph and read off an interpretation of the image from the solution eigenvectors. Combining an off-the-shelf top-down part-based person detector with our low-level cues and grouping formulation, we demonstrate improvements to object detection and segmentation.

Cite

Text

Maire et al. "Object Detection and Segmentation from Joint Embedding of Parts and Pixels." IEEE/CVF International Conference on Computer Vision, 2011. doi:10.1109/ICCV.2011.6126490

Markdown

[Maire et al. "Object Detection and Segmentation from Joint Embedding of Parts and Pixels." IEEE/CVF International Conference on Computer Vision, 2011.](https://mlanthology.org/iccv/2011/maire2011iccv-object/) doi:10.1109/ICCV.2011.6126490

BibTeX

@inproceedings{maire2011iccv-object,
  title     = {{Object Detection and Segmentation from Joint Embedding of Parts and Pixels}},
  author    = {Maire, Michael and Yu, Stella X. and Perona, Pietro},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2011},
  pages     = {2142-2149},
  doi       = {10.1109/ICCV.2011.6126490},
  url       = {https://mlanthology.org/iccv/2011/maire2011iccv-object/}
}