A “Shape Aware” Model for semi-supervised Learning of Objects and its Context

TitleA “Shape Aware” Model for semi-supervised Learning of Objects and its Context
Publication TypeJournal Articles
Year of Publication2008
AuthorsGupta A, Shi J, Davis LS
JournalProc. of NIPS
Date Published2008///
Abstract

We present an approach that combines bag-of-words and spatial models to performsemantic and syntactic analysis for recognition of an object based on its internal
appearance and its context. We argue that while object recognition requires mod-
eling relative spatial locations of image features within the object, a bag-of-word
is sufficient for representing context. Learning such a model from weakly labeled
data involves labeling of features into two classes: foreground(object) or “infor-
mative” background(context). We present a “shape-aware” model which utilizes
contour information for efficient and accurate labeling of features in the image.
Our approach iterates between an MCMC-based labeling and contour based la-
beling of features to integrate co-occurrence of features and shape similarity.