CaltechAUTHORS
  A Caltech Library Service

The rate adapting poisson model for information retrieval and object recognition

Gehler, Peter V. and Holub, Alex D. and Welling, Max (2006) The rate adapting poisson model for information retrieval and object recognition. In: ICML '06 Proceedings of the 23rd international conference on Machine learning. ACM , New York, NY, pp. 337-344. ISBN 1-59593-383-2. http://resolver.caltech.edu/CaltechAUTHORS:20161026-160525724

[img] PDF - Published Version
See Usage Policy.

288Kb

Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20161026-160525724

Abstract

Probabilistic modelling of text data in the bag-of-words representation has been dominated by directed graphical models such as pLSI, LDA, NMF, and discrete PCA. Recently, state of the art performance on visual object recognition has also been reported using variants of these models. We introduce an alternative undirected graphical model suitable for modelling count data. This "Rate Adapting Poisson" (RAP) model is shown to generate superior dimensionally reduced representations for subsequent retrieval or classification. Models are trained using contrastive divergence while inference of latent topical representations is efficiently achieved through a simple matrix multiplication.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
http://dx.doi.org/10.1145/1143844.1143887DOIPaper
http://dl.acm.org/citation.cfm?doid=1143844.1143887PublisherPaper
Additional Information:Copyright 2006 by the author(s)/owner(s). This material is based upon work supported by the National Science Foundation under Grant No. 0447903.
Funders:
Funding AgencyGrant Number
NSFIIS-0447903
Record Number:CaltechAUTHORS:20161026-160525724
Persistent URL:http://resolver.caltech.edu/CaltechAUTHORS:20161026-160525724
Official Citation:Peter V. Gehler, Alex D. Holub, and Max Welling. 2006. The rate adapting poisson model for information retrieval and object recognition. In Proceedings of the 23rd international conference on Machine learning (ICML '06). ACM, New York, NY, USA, 337-344. DOI=http://dx.doi.org/10.1145/1143844.1143887
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:71515
Collection:CaltechAUTHORS
Deposited By: Kristin Buxton
Deposited On:27 Oct 2016 16:48
Last Modified:27 Oct 2016 16:48

Repository Staff Only: item control page