D. Heesch and S. Ruger. Performance boosting with three mouse clicks - relevance feedback for cbir. In 25th European Conference on Information Retrieval Research (ECIR, Pisa, Italy, 14-16 Apr 2003. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Performance comparison of different similarity models.. - Heesch, Yavlinsky, Rüger (2003) Self-citation (Heesch) (Correct)
....requires the user to label retrieved images according to their relevance. A commonly employed techniques to achieve supervised learning through relevance feedback involves updating weights of a parametrized similarity function over several iterations of user system interac tion (see for example [12, 4]) This paper is concerned with the question of how retrieval performance and the effectiveness of relevance feedback is affected by the choice of the similarity model that underlies the ranking of retrieved images. The first similarity model is associated with support vector machines (SVM) This ....
....the plasticity to be exploited by relevance feedback. 4 Relevance feedback Thumbnails of retrieved images are displayed such that their respective distance from the centre of the screen is proportional to their dissimilarity to the query Q as computed by the system, Ds(i) for the GUI see [4]) By moving images further away or closer towards the center, the user provides a real valued vector of distances, Du(i) which, in general, differ from the distances computed by the system. To update the feature weights, we minimize the sum of squared errors (SSE) between the user distances and ....
[Article contains additional citation context not shown here]
D Heesch and S Rfiger. Performance boosting with three mouse clicks -- relevance feedback for CBIR. In Proceedings of the European Colloquium on IR Research 2003. LNCS, Springer, 2003.
Cortina: A System for Large-scale, Content-based Web - Image Retrieval Till (2004) (Correct)
No context found.
D. Heesch and S. Ruger. Performance boosting with three mouse clicks - relevance feedback for cbir. In 25th European Conference on Information Retrieval Research (ECIR, Pisa, Italy, 14-16 Apr 2003.
Cortina: A System for Large-scale, Content-based Web - Image Retrieval Till (Correct)
No context found.
D. Heesch and S. Ruger. Performance boosting with three mouse clicks - relevance feedback for cbir. In 25th European Conference on Information Retrieval Research (ECIR, Pisa, Italy, 14-16 Apr 2003.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC