Show simple item record

dc.contributor.authorTitsias, M.en
dc.contributor.authorWilliams, Christopheren
dc.date.accessioned2009-09-08T13:55:42Z
dc.date.available2009-09-08T13:55:42Z
dc.date.issued2004/05en
dc.date.issued2004-05-01en
dc.identifier.citationTitsias, M., Williams, C K I. (2004-05-01) Greedy Learning of Multiple Objects in Images using Robust Statistics and Factorial Learning, Neural Computation 16 (5) 1039-1062en
dc.identifier.issn0899-7667en
dc.identifier.urihttp://www.mitpressjournals.org/doi/pdf/10.1162/089976604773135096?cookieSet=1en
dc.identifier.urihttp://dx.doi.org/10.1162/089976604773135096en
dc.identifier.urihttp://hdl.handle.net/1842/3055
dc.description.abstractWe consider data that are images containing views of multiple objects. Our task is to learn about each of the objects present in the images. This task can be approached as a factorial learning problem, where each image must be explained by instantiating a model for each of the objects present with the correct instantiation parameters. A major problem with learning a factorial model is that as the number of objects increases, there is a combinatorial explosion of the number of configurations that need to be considered. We develop a method to extract object models sequentially from the data by making use of a robust statistical method, thus avoiding the combinatorial explosion, and present results showing successful extraction of objects from real images.en
dc.format.extent985479 bytes
dc.format.mimetypeapplication/pdf
dc.language.isoen
dc.publisherMIT Pressen
dc.subjectInstitute for Adaptive and Neural Computation
dc.titleGreedy Learning of Multiple Objects in Images using Robust Statistics and Factorial Learningen
dc.typeArticleen


Files in this item

This item appears in the following Collection(s)

Show simple item record