@conference {Nguyen2009a, title = {Weakly supervised discriminative localization and classification: A joint learning process}, booktitle = {Proceedings of the IEEE International Conference on Computer Vision}, year = {2009}, pages = {1925{\textendash}1932}, abstract = {Visual categorization problems, such as object classification or action recognition, are increasingly often approached using a detection strategy: a classifier function is first applied to candidate subwindows of the image or the video, and then the maximum classifier score is used for class decision. Traditionally, the subwindow classifiers are trained on a large collection of examples manually annotated with masks or bounding boxes. The reliance on time-consuming human labeling effectively limits the application of these methods to problems involving very few categories. Furthermore, the human selection of the masks introduces arbitrary biases (e.g. in terms of window size and location) which may be suboptimal for classification. In this paper we propose a novel method for learning a discriminative subwindow classifier from examples annotated with binary labels indicating the presence of an object or action of interest, but not its location. During training, our approach simultaneously localizes the instances of the positive class and learns a subwindow SVM to recognize them. We extend our method to classification of time series by presenting an algorithm that localizes the most discriminative set of temporal segments in the signal. We evaluate our approach on several datasets for object and action recognition and show that it achieves results similar and in many cases superior to those obtained with full supervision. {\textcopyright}2009 IEEE.}, isbn = {9781424444205}, doi = {10.1109/ICCV.2009.5459426}, author = {Nguyen, Minh Hoai and Torresani, Lorenzo and De La Torre, Fernando and Carsten Rother} }