{"type":"report","day":"01","publication":"Unknown","author":[{"first_name":"Matthew","last_name":"Blaschko","full_name":"Blaschko,Matthew B"},{"full_name":"Hofmann,Thomas","first_name":"Thomas","last_name":"Hofmann"},{"id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","full_name":"Christoph Lampert","first_name":"Christoph","last_name":"Lampert","orcid":"0000-0001-8622-7887"}],"month":"08","date_updated":"2019-04-26T07:22:33Z","citation":{"ista":"Blaschko M, Hofmann T, Lampert C. 2007. Efficient subwindow search for object localization, Max-Planck-Institute for Biological Cybernetics,p.","chicago":"Blaschko, Matthew, Thomas Hofmann, and Christoph Lampert. <i>Efficient Subwindow Search for Object Localization</i>. <i>Unknown</i>. Max-Planck-Institute for Biological Cybernetics, 2007.","apa":"Blaschko, M., Hofmann, T., &#38; Lampert, C. (2007). <i>Efficient subwindow search for object localization</i>. <i>Unknown</i>. Max-Planck-Institute for Biological Cybernetics.","ama":"Blaschko M, Hofmann T, Lampert C. <i>Efficient Subwindow Search for Object Localization</i>. Max-Planck-Institute for Biological Cybernetics; 2007.","short":"M. Blaschko, T. Hofmann, C. Lampert, Efficient Subwindow Search for Object Localization, Max-Planck-Institute for Biological Cybernetics, 2007.","mla":"Blaschko, Matthew, et al. “Efficient Subwindow Search for Object Localization.” <i>Unknown</i>, no. 164, Max-Planck-Institute for Biological Cybernetics, 2007.","ieee":"M. Blaschko, T. Hofmann, and C. Lampert, <i>Efficient subwindow search for object localization</i>, no. 164. Max-Planck-Institute for Biological Cybernetics, 2007."},"date_published":"2007-08-01T00:00:00Z","publication_status":"published","extern":1,"issue":"164","_id":"3687","abstract":[{"text":"Recent years have seen huge advances in object recognition from images. Recognition rates beyond 95% are the rule rather than the exception on many datasets. However, most state-of-the-art methods can only decide if an object is present or not. They are not able to provide information on the object location or extent within in the image.\n\nWe report on a simple yet powerful scheme that extends many existing recognition methods to also perform localization of object bounding boxes. This is achieved by maximizing the classification score over all possible subrectangles in the image. Despite the impression that this would be computationally intractable, we show that in many situations efficient algorithms exist which solve a generalized maximum subrectangle problem.\n\nWe show how our method is applicable to a variety object detection frameworks and demonstrate its performance by applying it to the popular bag of visual words model, achieving competitive results on the PASCAL VOC 2006 dataset.","lang":"eng"}],"main_file_link":[{"url":"http://www.kyb.tuebingen.mpg.de/fileadmin/user_upload/files/publications/TR-164_[0].pdf","open_access":"0"}],"publist_id":"2681","date_created":"2018-12-11T12:04:37Z","year":"2007","publisher":"Max-Planck-Institute for Biological Cybernetics","title":"Efficient subwindow search for object localization","quality_controlled":0,"status":"public"}