file.pdf (311.54 kB)

Using Co-occurrence and Segmentation to Learn Feature-based Object Models from Video

Download (311.54 kB)
journal contribution
posted on 01.01.1981, 00:00 by Thomas Stepleton, Tai Sing Lee
A number of recent systems for unsupervised feature-based learning of object models take advantage of co-occurrence: 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.

History

Publisher Statement

All Rights Reserved

Date

01/01/1981

Exports

Exports