A New Ranking Principle for Multimedia Information Retrieval

TL;DR

This paper introduces a new theoretical framework and ranking principle for multimedia information retrieval that extends the probability ranking principle by considering transmission time, inspection time, and aspectual recall to improve retrieval effectiveness.

Contribution

It presents a novel Ranking Principle for Distributed Multimedia-Documents (RPDM) and an algorithm satisfying this principle, generalizing the classic PRP for multimedia contexts.

Findings

RPDM guarantees optimal multimedia retrieval effectiveness

The algorithm effectively implements the RPDM

RPDM extends PRP by incorporating transmission, inspection time, and aspectual recall

Abstract

A theoretic framework for multimedia information retrieval is introduced which guarantees optimal retrieval effectiveness. In particular, a Ranking Principle for Distributed Multimedia-Documents (RPDM) is described together with an algorithm that satisfies this principle. Finally, the RPDM is shown to be a generalization of the Probability Ranking principle (PRP) which guarantees optimal retrieval effectiveness in the case of text document retrieval. The PRP justifies theoretically the relevance ranking adopted by modern search engines. In contrast to the classical PRP, the new RPDM takes into account transmission and inspection time, and most importantly, aspectual recall rather than simple recall.