Now showing items 1-4 of 392

    • On the Reduction of Computational Complexity of Deep Convolutional Neural Networks 

      Maji, Partha; Mullins, Robert David (MDPI AG, 2018-04)
      Deep convolutional neural networks (ConvNets), which are at the heart of many new emerging applications, achieve remarkable performance in audio and visual recognition tasks. Unfortunately, achieving accuracy often requires ...
    • Dataset and metrics for predicting local visible differences 

      Wolski, Krzysztof; Giunchi, Daniele; Ye, Nanyang; Didyk, Piotr; Myszkowski, Karol; Mantiuk, Radosław; Seidel, Hans-Peter et al.
      A large number of imaging and computer graphics applications require localized information on the visibility of image distortions. Existing image quality metrics are not suitable for this task as they provide a single ...
    • High Dynamic Range Imaging Technology. 

      Artusi, Alessandro; Richter, Thomas; Ebrahimi, Touradj; Mantiuk, Rafal Konrad (IEEE, 2017)
      Abstract: In this lecture note, we describe high dynamic range (HDR) imaging systems. Such systems are able to represent luminances of much larger brightness and, typically, a larger range of colors than conventional ...
    • Langevin Dynamics with Continuous Tempering for High-dimensional Non-convex Optimization. 

      Ye, Nanyang; Zhu, Zhanxing; Mantiuk, Rafal Konrad (2017)
      Minimizing non-convex and high-dimensional objective functions is challenging, especially when training modern deep neural networks. In this paper, a novel approach is proposed which divides the training process into two ...