摘要
To solve the unbalanced data problems of learning models for semantic concepts, an optimized modeling method based on the posterior probability support vector machine (PPSVM) is presented. A neighborbased posterior probability estimator for visual concepts is provided. The proposed method has been applied in a high-level visual semantic concept classification system and the experiment results show that it results in enhanced performance over the baseline SVM models, as well as in improved robustness with respect to high-level visual semantic concept classification.
To solve the unbalanced data problems of learning models for semantic concepts, an optimized modeling method based on the posterior probability support vector machine (PPSVM) is presented. A neighborbased posterior probability estimator for visual concepts is provided. The proposed method has been applied in a high-level visual semantic concept classification system and the experiment results show that it results in enhanced performance over the baseline SVM models, as well as in improved robustness with respect to high-level visual semantic concept classification.
基金
Sponsored by the Beijing Municipal Natural Science Foundation(4082027)