In this paper, a kernel-based method for multi-object retrieval in large image database is presented. First, our approach exploits a fuzzy region segmentation approach in order to...
Philippe Henri Gosselin, Matthieu Cord, Sylvie Phi...
We develop a robust technique to find similar matches of human actions in video. Given a query video, Motion History Images (MHI) are constructed for consecutive keyframes. This i...
This paper introduces a composite relevance feedback approach for image retrieval using transaction-based and SVM-based learning. A transaction repository is dynamically constructe...
We have been developing new relevance feedback algorithms for Content-based Image Retrieval (CBIR) that allow the user to achieve more flexible query. In conjunction with the new...
Munehiro Nakazato, Charlie K. Dagli, Thomas S. Hua...
In this paper we will describe Berkeley's approach to the ImageCLEF Wikipedia Retrieval task for 2010. Our approach to this task was primarily to use text-based searches on th...