We present a novel algorithm for image classification that is targeted to capture class variability. A single model is often not sufficient to represent a category since categories can vary from large semantic classes to fine-grained sub-categories. Instead, we develop a representation based on discovering visually similar sub-categories within a given class. We introduce a novel Clustered Exemplar SVM classifier which incorporates data-driven and exemplar focused discovery. Semi-supervised learning is employed for training each C-eSVM classifier. We evaluate our approach on two datasets and demonstrate the efficacy of our method over standard Exemplar SVM.

We propose a new weakly-supervised structured learning approach for recognition and spatio-temporal localization of actions in video. As part of the proposed approach we develop a generalization of the Max-Path search algorithm, which allows us to efficiently search over a structured space of multiple spatio-temporal paths, while also allowing to incorporate context information into the model. Instead of using spatial annotations, in the form of bounding boxes, to guide the latent model during training, we utilize human gaze data in the form of a weak supervisory signal. This is achieved by incorporating gaze, along with the classification, into the structured loss within the latent SVM learning framework. Experiments on a challenging benchmark dataset, UCF-Sports, show that our model is more accurate, in terms of classification, and achieves state-of-the-art results in localization. In addition, we show how our model can produce top-down saliency maps conditioned on the classification label and localized latent paths.