Learn More
Our objective is to obtain a state-of-the art object category detector by employing a state-of-the-art image classifier to search for the object in all possible image sub-windows. We use multiple kernel learning of Varma and Ray (ICCV 2007) to learn an optimal combination of exponential &#x03C7;<sup>2</sup> kernels, each of which captures a different(More)
In this paper we introduce a new shape constraint for interactive image segmentation. It is an extension of Veksler's [25] star-convexity prior, in two ways: from a single star to multiple stars and from Euclidean rays to Geodesic paths. Global minima of the energy function are obtained subject to these new constraints. We also introduce Geodesic Forests,(More)
Importance Deep learning is a family of computational methods that allow an algorithm to program itself by learning from a large set of examples that demonstrate the desired behavior, removing the need to specify rules explicitly. Application of these methods to medical imaging requires further assessment and validation. Objective To apply deep learning(More)
The Kinect provides an opportunity to collect large quantities of training data for visual learning algorithms relatively effortlessly. To this end we investigate learning to automatically segment humans from cluttered images (without depth information) given a bounding box. For this algorithm, obtaining a large dataset of images with segmented humans is(More)
Data are ooen labeled by many diierent experts with each expert only labeling a small fraction of the data and each data point being labeled by several experts. is reduces the workload on individual experts and also gives a beeer estimate of the unobserved ground truth. When experts disagree, the standard approaches are to treat the majority opinion as the(More)
  • 1