Carnegie Mellon University
Browse
file.pdf (388.46 kB)

Beyond Nouns: Exploiting Prepositions and Comparative Adjectives for Learning Visual Classifiers

Download (388.46 kB)
journal contribution
posted on 2008-01-01, 00:00 authored by Abhinav GuptaAbhinav Gupta, Larry S. Davis

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.

History

Date

2008-01-01

Usage metrics

    Keywords

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC