NIPS
2004
13 years 11 months ago
2004
We present a discriminative part-based approach for the recognition of object classes from unsegmented cluttered scenes. Objects are modeled as flexible constellations of parts co...
NIPS
2004
13 years 11 months ago
2004
We propose a new set of criteria for learning algorithms in multi-agent systems, one that is more stringent and (we argue) better justified than previous proposed criteria. Our cr...
NIPS
2004
13 years 11 months ago
2004
Existing algorithms for discrete partially observable Markov decision processes can at best solve problems of a few thousand states due to two important sources of intractability:...
NIPS
2004
13 years 11 months ago
2004
We introduce a novel active-learning scenario in which a user wants to work with a learning algorithm to identify useful anomalies. These are distinguished from the traditional st...
NIPS
2004
13 years 11 months ago
2004
Dominant sets are a new graph-theoretic concept that has proven to be relevant in pairwise data clustering problems, such as image segmentation. They generalize the notion of a ma...
NIPS
2004
13 years 11 months ago
2004
Online mechanism design (OMD) addresses the problem of sequential decision making in a stochastic environment with multiple self-interested agents. The goal in OMD is to make valu...
NIPS
2004
13 years 11 months ago
2004
Capturing dependencies in images in an unsupervised manner is important for many image processing applications. We propose a new method for capturing nonlinear dependencies in ima...
NIPS
2004
13 years 11 months ago
2004
We discuss an identification framework for noisy speech mixtures. A block-based generative model is formulated that explicitly incorporates the time-varying harmonic plus noise (H...
NIPS
2004
13 years 11 months ago
2004
We develop a family of upper and lower bounds on the worst-case expected KL loss for estimating a discrete distribution on a finite number m of points, given N i.i.d. samples. Our...
NIPS
2004
13 years 11 months ago
2004
Log-concavity is an important property in the context of optimization, Laplace approximation, and sampling; Bayesian methods based on Gaussian process priors have become quite pop...