We describe an approach to object retrieval which searches for and localizes all the occurrences of an object in a video, given a query image of the object. The object is represent...
Automatic separation of text and symbols from graphics in document image is one of the fundamental aims in graphics recognition. In maps, separation of text and symbols from graphi...
Partha Pratim Roy, Eduard Vazquez, Josep Llad&oacu...
In this paper, we propose a probabilistic model for web image mining, which is based on concept-sensitive salient regions without human intervene. Our goal is to achieve a middle-...
Modeling the beyond-topical aspects of relevance are currently gaining popularity in IR evaluation. For example, the discounted cumulated gain (DCG) measure implicitly models some...
This work is motivated by the need for visual information extraction and management in the growing field of content based image retrieval from medical archives. In particular it f...