Please use this identifier to cite or link to this item:
|Title:||Spatialized epitome and its applications||Authors:||Chu, X.
|Issue Date:||2010||Citation:||Chu, X., Yan, S., Li, Y., Chan, K.L., Huang, T.S. (2010). Spatialized epitome and its applications. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition : 311-318. ScholarBank@NUS Repository. https://doi.org/10.1109/CVPR.2010.5540196||Abstract:||Due to the lack of explicit spatial consideration, existing epitome model may fail for image recognition and target detection, which directly motivates us to propose the so-called spatialized epitome in this paper. Extended from the original graphical model of epitome, the spatialized epitome provides a general framework to integrate both appearance and spatial arrangement of patches in the image to achieve a more precise likelihood representation for image(s) and eliminate ambiguities in image reconstruction and recognition. From the extended graphical model of epitome, an EM learning procedure is derived under the framework of variational approximation. The learning procedure can generate an optimized summary of the image appearance with spatial distribution of the similar patches. From the spatialized epitome, we present a principled way of inferring the probability of a new input image under the learnt model and thereby enabling image recognition and target detection. We show how the incorporation of spatial information enhances the epitome's ability for discrimination on several vision tasks, e.g., misalignment/cross-pose face recognition and vehicle detection with a few training samples. ©2010 IEEE.||Source Title:||Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition||URI:||http://scholarbank.nus.edu.sg/handle/10635/71835||ISBN:||9781424469840||ISSN:||10636919||DOI:||10.1109/CVPR.2010.5540196|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.