ML Anthology

Factorizing Appearance Using Epitomic Flobject Analysis

Patrick S. Li, Brendan J. Frey
CVPR 2012 pp. 2839-2846
doi:10.1109/CVPR.2012.6248009 /cvpr/2012/li2012cvpr-factorizing/

Abstract

Previously, `flobject analysis' was introduced as a method for using motion or stereo disparity information to train better models of static images. During training, but not during testing, optic flow is used as a cue for factorizing appearance-based image features into those belonging to different flow-defined objects, or flobjects. Here, we describe how the image epitome can be extended to model flobjects and introduce a suitable learning algorithm. Using the CityCars and City F'edestrians datasets, we study the tasks of object classification and localization. Our method performs significantly better than the original LDA-based flobject analysis technique, SIFT-based methods with and without spatial pyramid matching, and gist descriptors.

CVPR Semantic Scholar

Cite

Text

Li and Frey. "Factorizing Appearance Using Epitomic Flobject Analysis." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2012. doi:10.1109/CVPR.2012.6248009

Markdown

[Li and Frey. "Factorizing Appearance Using Epitomic Flobject Analysis." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2012.](https://mlanthology.org/cvpr/2012/li2012cvpr-factorizing/) doi:10.1109/CVPR.2012.6248009

BibTeX

@inproceedings{li2012cvpr-factorizing,
  title     = {{Factorizing Appearance Using Epitomic Flobject Analysis}},
  author    = {Li, Patrick S. and Frey, Brendan J.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2012},
  pages     = {2839-2846},
  doi       = {10.1109/CVPR.2012.6248009},
  url       = {https://mlanthology.org/cvpr/2012/li2012cvpr-factorizing/}
}