Refereed full papers (journals, book chapters, international conferences)

1998

@inproceedings{ISF1998,
	vgclass =	{refpap},
	vgproject =	{cbir},
	author =	{Yoshiharu Ishikawa and Ravishankar Subramanya and Christos
	Faloutsos},
	title =	{MindReader: Querying databases through multiple examples},
	editor =	{Ashish Gupta and Oded Shmueli and Jennifer Widom},
	booktitle =	{Proceedings of 24th International Conference on Very Large Databases (VLDB'98)},
	address =	{New York, NY, USA},
	pages =	{218--227},
	month =	{24--27~August},
	year =	{1998},
	abstract =	{Users often can not easily express their queries. For
	example, in a multimedia/image by content setting, the user might want
	photographs with sunsets; in current systems, like QBIC, the user has
	to give a sample query, and to specify the relative importance of
	color, shape and texture. Even worse, the user might want correlations
	between attributes, like, for example, in a traditional, medical record
	database, a medical researcher might want to find ``mildly overweight
	patients'', where the implied query would be
	``$\mathrm{weight}/\mathrm{height} \approx 4
	\mathrm{lb}/\mathrm{inch}$''.  Our goal is to provide a user�friendly,
	but theoretically solid method, to handle such queries. We allow the
	user to give several examples, and, optionally, their ``goodness''
	scores, and we propose a novel method to ``guess'' which attributes are
	important, which correlations are important, and with what weight.  Our
	contributions are twofold: (a) we formalize the problem as a
	minimization problem and show how to solve for the optimal solution,
	completely avoiding the ad�hoc the heuristics of the past. (b)
	Moreover, we are the \emph{first} that can handle ``diagonal'' queries
	(like the ``overweight'' query above). Experiments on synthetic and
	real datasets show that our method estimates quickly and accurately the
	``hidden'' distance function in the user's mind.},
}