Computer Vision – ECCV 2008

Volume 5302 of the series Lecture Notes in Computer Science pp 16-29

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

  • Abhinav GuptaAffiliated withDepartment of Computer Science, University of Maryland
  • , Larry S. DavisAffiliated withDepartment of Computer Science, University of Maryland

* Final gross prices may vary according to local VAT.

Get Access


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.