Using Co-Occurrence and Segmentation to Learn Feature-Based Object Models from Video

Abstract

A number of recent systems for unsupervised feature- based learning of object models take advantage of cooccurrence: broadly, they search for clusters of discriminative features that tend to coincide across multiple still images or video frames. An intuition behind these efforts is that regularly co-occurring image features are likely to refer to physical… (More)
DOI: 10.1109/ACVMOT.2005.119

Topics

4 Figures and Tables

Cite this paper

@article{Stepleton2005UsingCA, title={Using Co-Occurrence and Segmentation to Learn Feature-Based Object Models from Video}, author={Thomas S. Stepleton and Tai Sing Lee}, journal={2005 Seventh IEEE Workshops on Applications of Computer Vision (WACV/MOTION'05) - Volume 1}, year={2005}, volume={1}, pages={129-134} }