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

1998

@inproceedings{CMM1998,
	vgclass =	{refpap},
	vgproject =	{cbir},
	author =	{Ingemar J. Cox and Matthew L. Miller and Thomas P. Minka
	and Peter N. Yianilos},
	title =	{An Optimized Interaction Strategy for Bayesian Relevance
	Feedback},
	booktitle =	{Proceedings of the 1998 IEEE Conference on Computer Vision and Pattern Recognition (CVPR'98)},
	address =	{Santa Barbara, California, USA},
	pages =	{553--558},
	month =	{June},
	year =	{1998},
	url =	{ftp://vismod.www.media.mit.edu/pub/tpminka/papers/minka-cvpr98.ps.gz},
	abstract =	{A new algorithm and systematic evaluation is presented for
	searching a database via relevance feedback. It represents a new image
	display strategy for the \texttt{PicHunter} system [2, 1]. The
	algorithm takes feedback in the form of relative judgments (``item A is
	more relevant than item B'') as opposed to the stronger assumption of
	categorical relevance judgments (``item A is relevant but item B is
	not''). It also exploits a learned probabilistic model of human
	behavior to make better use of the feedback it obtains. The algorithm
	can be viewed as an extension of indexing schemes like the $k$-d tree
	to a stochastic setting, hence the name ``stochastic-comparison
	search.'' In simulations, the amount of feedback required for the new
	algorithm scales like $\log_2|D|$, where $|D|$ is the size of the
	database, while a simple query-by-example approach scales like $|D|^a$
	, where $a < 1$ depends on the structure of the database. This
	theoretical advantage is reflected by experiments with real users on a
	database of 1500 stock photographs.},
}