Learn More
Our objective is to obtain a state-of-the art object category detector by employing a state-of-the-art image clas-sifier 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 χ 2 kernels, each of which captures a different feature channel. Our(More)
(a) No Shape Constraint (b) Geodesic Star Convexity Constraint Figure 1. Shape constraints for Interactive Segmentation. The blue and pink strokes represent foreground(FG) and background (BG) brushes respectively. The output segmentations are overlaid as a two-colored boundary, with the red boundary towards the FG side and green towards the BG. The(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)
  • 1