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

1998

@inproceedings{VaL1998,
	vgclass =	{refpap},
	vgproject =	{cbir},
	author =	{Nuno Vasconcelos and Andrew Lippman},
	title =	{Embedded Mixture Modeling for Efficient Probabilistic
	Content-based Indexing and Retrieval},
	editor =	{C.-C. Jay Kuo and Shih-Fu Chang and Sethuraman
	Panchanathan},
	booktitle =	{Multimedia Storage and Archiving Systems III (VV02)},
	address =	{Boston, Massachusetts, USA},
	volume =	{3527},
	series =	{SPIE Proceedings},
	pages =	{134--143},
	month =	{November},
	year =	{1998},
	note =	{(SPIE Symposium on Voice, Video and Data Communications)},
	url =	{http://www.media.mit.edu/\~{}nuno/Papers/spie98.ps.gz},
	abstract =	{By formulating content�based retrieval as a problem of
	Bayesian inference we have previously developed a retrieval framework
	with various interesting properties: 1) allows the incorporation of
	prior beliefs about image relevance in the retrieval process, 2) leads
	to simple and intuitive mechanisms for combining information from
	several modalities, such as images, audio, and text during retrieval,
	3) provides support for the development of interfaces that learn from
	user interaction, 4) allows retrieval directly from compressed
	bitstreams, and 5) lends itself to the construction of indexing
	structures which can also be computed as a side effect of the
	compression process.

	In this paper, we analyze the relationships between probabilistic
	retrieval using mixture models and two approaches commonly found in the
	retrieval literature, and introduce an alternative criterion, the
	random sample likelihood that is computationally cheaper and more
	robust. By performing all the modeling in the frequency domain, we
	obtain an embedded set of representations that operate on subspaces of
	the feature space. When only the coarsest of these subspaces is
	considered for retrieval, our model becomes a simple histogram leading
	to very efficient retrieval. However, as more subspaces are considered,
	the model is also able to capture higher order dependencies between
	image pixels, allowing for more accurate retrieval. The representation
	is therefore suited to the implementation of multistage filtering
	strategies where low�complexity and low�accuracy methods are used in
	the early stages to eliminate clearly inappropriate matches and higher
	accuracy methods are employed in subsequent stages to select the best
	matches within the set of surviving hypothesis. Simulation results show
	that the new retrieval criterion beats the standard ones even when the
	former is applied to a generic feature space and the latter ones to a
	feature space highly specialized to the type of imagery in the
	database.},
}