Date of Original Version

2008

Type

Book Chapter

Abstract or Description

Learning visual classifiers for object recognition from weakly labeled data requires determining correspondence between image regions and semantic object classes. Most approaches use co-occurrence of “nouns” and image features over large datasets to determine the correspondence, but many correspondence ambiguities remain. We further constrain the correspondence problem by exploiting additional language constructs to improve the learning process from weakly labeled data. We consider both “prepositions” and “comparative adjectives” which are used to express relationships between objects. If the models of such relationships can be determined, they help resolve correspondence ambiguities. However, learning models of these relationships requires solving the correspondence problem. We simultaneously learn the visual features defining “nouns” and the differential visual features defining such “binary-relationships” using an EM-based approach.

Included in

Robotics Commons

Share

COinS
 

Published In

D. Forsyth, P. Torr, and A. Zisserman (Eds.): ECCV 2008, Part I, LNCS 5302, 16-29.