Sciweavers

ECCV
2008
Springer

Learning to Localize Objects with Structured Output Regression

14 years 5 months ago
Learning to Localize Objects with Structured Output Regression
Sliding window classifiers are among the most successful and widely applied techniques for object localization. However, training is typically done in a way that is not specific to the localization task. First a binary classifier is trained using a sample of positive and negative examples, and this classifier is subsequently applied to multiple regions within test images. We propose instead to treat object localization in a principled way by posing it as a problem of predicting structured data: we model the problem not as binary classification, but as the prediction of the bounding box of objects located in images. The use of a joint-kernel framework allows us to formulate the training procedure as a generalization of an SVM, which can be solved efficiently. We further improve computational efficiency by using a branch-and-bound strategy for localization during both training and testing. Experimental evaluation on the PASCAL VOC and TU Darmstadt datasets show that the structured traini...
Matthew B. Blaschko, Christoph H. Lampert
Added 15 Oct 2009
Updated 15 Oct 2009
Type Conference
Year 2008
Where ECCV
Authors Matthew B. Blaschko, Christoph H. Lampert
Comments (0)