Quantitative Characterization of Semantic Gaps for Learning Complexity Estimation and Inference Model Selection | IEEE Journals & Magazine | IEEE Xplore

Quantitative Characterization of Semantic Gaps for Learning Complexity Estimation and Inference Model Selection


Abstract:

In this paper, a novel data-driven algorithm is developed for achieving quantitative characterization of the semantic gaps directly in the visual feature space, where the...Show More

Abstract:

In this paper, a novel data-driven algorithm is developed for achieving quantitative characterization of the semantic gaps directly in the visual feature space, where the visual feature space is the common space for concept classifier training and automatic concept detection. By supporting quantitative characterization of the semantic gaps, more effective inference models can automatically be selected for concept classifier training by: (1) identifying the image concepts with small semantic gaps (i.e., the isolated image concepts with high inner-concept visual consistency) and training their one-against-all SVM concept classifiers independently; (2) determining the image concepts with large semantic gaps (i.e., the visually-related image concepts with low inner-concept visual consistency) and training their inter-related SVM concept classifiers jointly; and (3) using more image instances to achieve more reliable training of the concept classifiers for the image concepts with large semantic gaps. Our experimental results on NUS-WIDE and ImageNet image sets have obtained very promising results.
Published in: IEEE Transactions on Multimedia ( Volume: 14, Issue: 5, October 2012)
Page(s): 1414 - 1428
Date of Publication: 02 May 2012

ISSN Information:


References

References is not available for this document.