Seeking the Strongest Rigid Detector


The current state of the art solutions for object detection describe each class by a set of models trained on discovered sub-classes (so called "components"), with each model itself composed of collections of interrelated parts (deformable models). These detectors build upon the now classic Histogram of Oriented Gradients+linear SVM combo. In this paper we… (More)
DOI: 10.1109/CVPR.2013.470

8 Figures and Tables



Citations per Year

338 Citations

Semantic Scholar estimates that this publication has 338 citations based on the available data.

See our FAQ for additional information.

  • Presentations referencing similar topics