CVPR
2011
IEEE
13 years 24 days ago
2011
IEEE
We deal with an image jigsaw puzzle problem, which is defined as reconstructing an image from a set of square and non-overlapping image patches. It is known that a general instan...
EMNLP
2010
13 years 2 months ago
2010
We present a unified view of two state-of-theart non-projective dependency parsers, both approximate: the loopy belief propagation parser of Smith and Eisner (2008) and the relaxe...
PAMI
2010
13 years 3 months ago
2010
— Time-of-flight range sensors and passive stereo have complimentary characteristics in nature. To fuse them to get high accuracy depth maps varying over time, we extend traditi...
CORR
2010
Springer
13 years 4 months ago
2010
Springer
We propose a new approach to the analysis of Loopy Belief Propagation (LBP) by establishing a formula that connects the Hessian of the Bethe free energy with the edge zeta functio...
UAI
2003
13 years 5 months ago
2003
In non-ergodic belief networks the posterior belief of many queries given evidence may become zero. The paper shows that when belief propagation is applied iteratively over arbitr...
UAI
2001
13 years 6 months ago
2001
This paper presents a new deterministic approximation technique in Bayesian networks. This method, "Expectation Propagation," unifies two previous techniques: assumed-de...
NIPS
2001
13 years 6 months ago
2001
In this paper we will show that a restricted class of constrained minimum divergence problems, named generalized inference problems, can be solved by approximating the KL divergen...
ICCV
2007
IEEE
13 years 6 months ago
2007
IEEE
Development of multiple camera based vision systems for analysis of dynamic objects such as humans is challenging due to occlusions and similarity in the appearance of a person wi...
AAAI
2008
13 years 6 months ago
2008
Loop Calculus, introduced by Chertkov and Chernyak, is a new technique to incrementally improve approximations computed by Loopy Belief Propagation (LBP), with the ability to even...
CVPR
2008
IEEE
13 years 11 months ago
2008
IEEE
Background estimation, i.e. automatic recovery of the background image from a sequence of images containing moving foreground objects, is an important module in many applications,...