conference paper published Matthew Blaschko author Christoph Lampert author 40C20FD2-F248-11E8-B48F-1D18A9856A870000-0001-8622-7887 ECCV: European Conference on Computer Vision 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 training procedure improves pe rformance over binary training as well as the best previously published scores. Springer Nature2008Marseille, France eng 978354088681510.1007/978-3-540-88682-2_2 53022 - 15 yes Blaschko, Matthew, and Christoph Lampert. “Learning to Localize Objects with Structured Output Regression.” In <i>10th European Conference on Computer Vision</i>, 5302:2–15. Springer Nature, 2008. <a href="https://doi.org/10.1007/978-3-540-88682-2_2">https://doi.org/10.1007/978-3-540-88682-2_2</a>. Blaschko, Matthew, and Christoph Lampert. “Learning to Localize Objects with Structured Output Regression.” <i>10th European Conference on Computer Vision</i>, vol. 5302, Springer Nature, 2008, pp. 2–15, doi:<a href="https://doi.org/10.1007/978-3-540-88682-2_2">10.1007/978-3-540-88682-2_2</a>. Blaschko M, Lampert C. Learning to localize objects with structured output regression. In: <i>10th European Conference on Computer Vision</i>. Vol 5302. Springer Nature; 2008:2-15. doi:<a href="https://doi.org/10.1007/978-3-540-88682-2_2">10.1007/978-3-540-88682-2_2</a> Blaschko, M., &#38; Lampert, C. (2008). Learning to localize objects with structured output regression. In <i>10th European Conference on Computer Vision</i> (Vol. 5302, pp. 2–15). Marseille, France: Springer Nature. <a href="https://doi.org/10.1007/978-3-540-88682-2_2">https://doi.org/10.1007/978-3-540-88682-2_2</a> M. Blaschko and C. Lampert, “Learning to localize objects with structured output regression,” in <i>10th European Conference on Computer Vision</i>, Marseille, France, 2008, vol. 5302, pp. 2–15. Blaschko M, Lampert C. 2008. Learning to localize objects with structured output regression. 10th European Conference on Computer Vision. ECCV: European Conference on Computer Vision, LNCS, vol. 5302, 2–15. M. Blaschko, C. Lampert, in:, 10th European Conference on Computer Vision, Springer Nature, 2008, pp. 2–15. 37052018-12-11T12:04:43Z2026-06-12T11:38:01Z