6 Matching Annotations
  1. Dec 2018
    1. in our case, with a per-pixelsigmoidand abinaryloss, they do not. We show by experiments that this formu-lation is key for good instance segmentation results




    1. visible and unoccluded in the image. Varolet al. ex-plore predicting a voxel representation of human body [45].In this work we go beyond these approaches by proposing amethod that can predict shape and pose from a single image,as well as how


    1. ficult: perspective ambiguities make theloss function noisy and training data is scarce. In thispaper, we propose a novel approach (Neural Body Fitting(NBF)). It integrates a statistical body model within a CNN,leveraging reliabl


  2. Nov 2018
    1. Deep convolutional neural networks [21, 23] revolution-ized computer vision arguably due to the discovery that fea-ture representations learned on apre-trainingtask can trans-fer useful info