Multimedia Search with Pseudo-Relevance Feedback

Intelligent Multimedia Knowledge Management

Volume

Papers from the 2003 AAAI Spring Symposium

Contents

We present an algorithm for video retrieval that fuses the decisions of multiple retrieval agents in both text and image modalities. While the normalization and combination of evidence is novel, this paper emphasizes the successful use of negative pseudo-relevance feedback to improve image retrieval performance. While the results are still far from perrfect, pseudo-relevance feedback shows great promise for multimedia retrieval in very noisy data.