Fast unsupervised greedy learning of multiple objects and parts from video

Michalis K Titsias, Christopher K.I. Williams

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Williams and Titsias (2004) have shown how to carry out unsupervised greedy learning of multiple objects from images (GLOMO), building on the work of Jojic and Frey (2001). In this paper we show that the earlier work on GLOMO can be greatly speeded up for video sequence data by carrying out approximate tracking of the multiple objects in the scene. Our method is applied to raw image sequence data and extracts the objects one at a time. First, the moving background is learned, and moving objects are found at later stages. The algorithm recursively updates an appearance model of the tracked object so that possible occlusion of the object is taken into account which makes tracking stable. We apply this method to learn multiple objects in image sequences as well as articulated parts of the human body.
Original languageEnglish
Title of host publicationComputer Vision and Pattern Recognition Workshop, 2004. CVPRW'04. Conference on
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages1
Publication statusPublished - 2004

Fingerprint Dive into the research topics of 'Fast unsupervised greedy learning of multiple objects and parts from video'. Together they form a unique fingerprint.

Cite this