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

Thomas S. Stepleton, Tai Sing LeeWACV 2005 · OpenReview

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 traits of the same object, while features that do not often co-occur are more likely to belong to different objects. In this paper we discuss a refinement to these techniques in which multiple segmentations establish meaningful contexts for co-occurrence, or limit the spatial regions in which two features are deemed to co-occur. This approach can reduce the variety of image data necessary for model learning and simplify the incorporation of less discriminative features into the model.
BibTeX
@inproceedings{stepleton2005using,
  author = {Thomas S. Stepleton and Tai Sing Lee},
  title = {{Using Co-Occurrence and Segmentation to Learn Feature-Based Object Models from Video}},
  booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision},
  year = {2005},
  url = {https://openreview.net/forum?id=FUBaRECLskF},
}

Loading related content...

Figure