PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

A BOVW Based Query Generative Model
Reede Ren, Joemon Jose and John Collomosse
In: 17th Intl. Conf. on Multimedia Modelling (MMM), Taiwan(2011).

Abstract

Bag-of-visual words (BOVW) is a local feature based frame work for content-based image and video retrieval. Its performance relies on the discriminative power of visual vocabulary, i.e. the cluster set on local features. However, the optimisation of visual vocabulary is of a high complexity in a large collection. This paper aims to relax such a dependence by adapting the query generative model to BOVW based retrieval. Local features are directly projected onto latent content topics to create effective visual queries; visual word distributions are learnt around local features to estimate the contribution of a visual word to a query topic the relevance is justified by considering concept distributions on visual words as well as on local features. Massive experiments are carried out the TRECVid 2009 collection. The notable improvement on retrieval performance shows that this probabilistic framework alleviates the problem of visual ambiguity and is able to afford visual vocabulary with relatively low discriminative power.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Oral)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Information Retrieval & Textual Information Access
ID Code:8349
Deposited By:John Collomosse
Deposited On:30 October 2011