A new technique to locate content-representing words for a given document image using representation of character shapes is described. A character shape code representation define...
Users prefer to navigate subjects from organized topics in an abundance resources than to list pages retrieved from search engines. We propose a framework to cluster frequent items...
We present a new method for information retrievalusing hidden Markov models (HMMs). We develop a general framework for incorporating multiple word generation mechanisms within the...
Abstract—The idea of an online visual vocabulary is proposed. In contrast to the accepted strategy of generating vocabularies offline, using the k-means clustering over all the ...
Given a query image of an object, our objective is to retrieve all instances of that object in a large (1M+) image database. We adopt the bag-of-visual-words architecture which ha...
Ondrej Chum, James Philbin, Josef Sivic, Michael I...