Modeling dynamic scenes with active appearance

Doretto, G.
Modeling dynamic scenes with active appearance. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 66–73, San Diego, CA, USA, June 2005.
Oral Presentation

Download

PDF (310.9kB )  

Abstract

In this work we propose a model for video scenes that contain temporal variability in shape and appearance. We propose a conditionally linear model akin to a dynamic extension of active appearance models. We formulate the problem variationally, and propose a framework where a model complexity cost dictates the “modeling responsibility” of each of the factors: appearance, shape and motion. We render the learning problem well-posed by reverting to a physical and a dynamic prior, and use the finite element method to compute a numerical solution. We illustrate our model to learn and simulate the shape, appearance, and motion of scenes that exhibit some form of temporal regularity, intended in a statistical sense.

@INPROCEEDINGS{doretto05cvpr,
  author = {Doretto, G.},
  title = {Modeling dynamic scenes with active appearance},
  booktitle = cvpr,
  year = {2005},
  volume = {1},
  pages = {66--73},
  address = {San Diego, CA, USA},
  month = jun,
  note = {\btohremove{\textsf{\textbf{GSCC: 1, ARO: 6.5\%}}}},
  bib2html_pubtype = {Refereed Conferences},
  bib2html_rescat = {Dynamic Textures, Visual Motion Analysis, Shape and Appearance Modeling},
  abstract = {In this work we propose a model for video scenes that contain temporal
	variability in shape and appearance. We propose a conditionally linear
	model akin to a dynamic extension of active appearance models. We
	formulate the problem variationally, and propose a framework where
	a model complexity cost dictates the “modeling responsibility” of
	each of the factors: appearance, shape and motion. We render the
	learning problem well-posed by reverting to a physical and a dynamic
	prior, and use the finite element method to compute a numerical solution.
	We illustrate our model to learn and simulate the shape, appearance,
	and motion of scenes that exhibit some form of temporal regularity,
	intended in a statistical sense.},
  file = {doretto05cvpr.pdf:doretto\\conference\\doretto05cvpr.pdf:PDF},
  owner = {doretto},
  pdf = {doretto\conference\doretto05cvpr.pdf},
  wwwnote = {<span class="wwwnote">Oral Presentation</span>}
}

Generated by bib2html.pl (written by Patrick Riley )