Description: This paper introduces the Located Hidden Random Field
(LHRF), a conditional model for simultaneous part-based detection and
segmentation of objects of a given class. Given a training set of images
with segmentation masks for the object of interest, the LHRF automati-
cally learns a set of parts that are both discriminative in terms of appear-
ance and informative about the location of the object. By introducing
the global position of the object as a latent variable, the LHRF models
the long-range spatial conguration of these parts, as well as their local
interactions. Experiments on benchmark datasets show that the use of
discriminative parts leads to state-of-the-art detection and segmentation
performance, with the additional benet of obtaining a labeling of the
object s component parts.
To Search:
File list (Check if you may need any files):
Kapoor_Winn.pdf