ML Anthology

Controlling Model Complexity in Flow Estimation

Zoran Duric, Fayin Li, Harry Wechsler, Vladimir Cherkassky
ICCV 2003 pp. 908-914
doi:10.1109/ICCV.2003.1238445 /iccv/2003/duric2003iccv-controlling/

Abstract

This paper describes a novel application of Statistical Learning Theory (SLT) to control model complexity in flow estimation. SLT provides analytical generalization bounds suitable for practical model selection from small and noisy data sets of image measurements (normal flow). The method addresses the aperture problem by using the penalized risk (ridge regression). We demonstrate an application of this method on both synthetic and real image sequences and use it for motion interpolation and extrapolation. Our experimental results show that our approach compares favorably against alternative model selection methods such as the Akaike’s final prediction error, Schwartz’s criterion, Generalized cross-validation, and Shibata’s model selector. 1.

PDF ICCV Semantic Scholar

Cite

Text

Duric et al. "Controlling Model Complexity in Flow Estimation." IEEE/CVF International Conference on Computer Vision, 2003. doi:10.1109/ICCV.2003.1238445

Markdown

[Duric et al. "Controlling Model Complexity in Flow Estimation." IEEE/CVF International Conference on Computer Vision, 2003.](https://mlanthology.org/iccv/2003/duric2003iccv-controlling/) doi:10.1109/ICCV.2003.1238445

BibTeX

@inproceedings{duric2003iccv-controlling,
  title     = {{Controlling Model Complexity in Flow Estimation}},
  author    = {Duric, Zoran and Li, Fayin and Wechsler, Harry and Cherkassky, Vladimir},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2003},
  pages     = {908-914},
  doi       = {10.1109/ICCV.2003.1238445},
  url       = {https://mlanthology.org/iccv/2003/duric2003iccv-controlling/}
}