• Human Pose Estimation with CNNs and LSTMs 

      Coskun, Huseyin (Universitat Politècnica de Catalunya, 2016-08-15)
      Projecte Final de Màster Oficial
      Accés obert
      Realitzat a/amb:   Technische Universität München
      In this thesis, we present an end-to-end approach to human pose estimation task that based on a deep hybrid architecture that combines convolutional neural network (CNNs) and recurrent neural networks (RNNs).
    • Image Segmentation using Dictionary Learning 

      Sarasúa Cañedo-Arguelles, Ignacio (Universitat Politècnica de Catalunya, 2014-12-22)
      Projecte/Treball Final de Carrera
      Accés obert
      Realitzat a/amb:   Technische Universität München
      [ANGLÈS] In image segmentation, we are often interested in capturing certain characteristics of objects of interests, and perform the classification based on criteria such as mean intensity, gradient magnitude, and responses ...