Sciweavers

Share
WACV
2005
IEEE

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

10 years 10 months ago
Using Co-Occurrence and Segmentation to Learn Feature-Based Object Models from Video
A number of recent systems for unsupervised featurebased 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.
Thomas S. Stepleton, Tai Sing Lee
Added 25 Jun 2010
Updated 25 Jun 2010
Type Conference
Year 2005
Where WACV
Authors Thomas S. Stepleton, Tai Sing Lee
Comments (0)
books