Unsupervised learning of multiple aspects of moving objects from video

Authors:
Michalis K. Titsias;Christopher K. I. Williams
Affiliations:
School of Informatics, University of Edinburgh, Edinburgh, UK;School of Informatics, University of Edinburgh, Edinburgh, UK
Venue:
PCI'05 Proceedings of the 10th Panhellenic conference on Advances in Informatics
Year:
2005

Citing 5
Cited 0

Computing occluding and transparent motions

International Journal of Computer Vision
Statistical background modelling for tracking with a virtual camera

BMVC '95 Proceedings of the 6th British conference on Machine vision (Vol. 2)
Transformation-Invariant Clustering Using the EM Algorithm

IEEE Transactions on Pattern Analysis and Machine Intelligence
Greedy learning of multiple objects in images using robust statistics and factorial learning

Neural Computation
Fast Unsupervised Greedy Learning of Multiple Objects and Parts from Video

CVPRW '04 Proceedings of the 2004 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'04) Volume 12 - Volume 12

Quantified Score

Hi-index	0.00

Visualization

Abstract

A popular framework for the interpretation of image sequences is based on the layered model; see e.g. Wang and Adelson [8], Irani et al. [2]. Jojic and Frey [3] provide a generative probabilistic model framework for this task. However, this layered models do not explicitly account for variation due to changes in the pose and self occlusion. In this paper we show that if the motion of the object is large so that different aspects (or views) of the object are visible at different times in the sequence, we can learn appearance models of the different aspects using a mixture modelling approach.