Now showing items 1-7 of 7

    • Adaptive temporal compressive sensing for video 

      Brady, David J; Carin, Lawrence; Liao, X; Llull, P; Sapiro, Guillermo; Yang, J; Yuan, X (2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings, 2013-12-01)
      This paper introduces the concept of adaptive temporal compressive sensing (CS) for video. We propose a CS algorithm to adapt the compression ratio based on the scene's temporal complexity, computed from the compressed data, ...
    • Coded aperture compressive temporal imaging. 

      Brady, David J; Carin, Lawrence; Kittle, D; Liao, X; Llull, P; Sapiro, Guillermo; Yang, J; ... (8 authors) (Opt Express, 2013-05-06)
      We use mechanical translation of a coded aperture for code division multiple access compression of video. We discuss the compressed video's temporal resolution and present experimental results for reconstructions of > 10 ...
    • Computer vision tools for low-cost and noninvasive measurement of autism-related behaviors in infants. 

      Dawson, Geraldine; Egger, Helen; Esler, A; Hashemi, J; Morellas, V; Papanikolopoulos, N; Sapiro, Guillermo; ... (9 authors) (Autism Res Treat, 2014)
      The early detection of developmental disorders is key to child outcome, allowing interventions to be initiated which promote development and improve prognosis. Research on autism spectrum disorder (ASD) suggests that behavioral ...
    • Computer vision tools for the non-invasive assessment of autism-related behavioral markers 

      Esler, A; Hashemi, J; Morellas, V; Papanikolopoulos, N; Sapiro, Guillermo; Spina, TV; Tepper, M
      The early detection of developmental disorders is key to child outcome, allowing interventions to be initiated that promote development and improve prognosis. Research on autism spectrum disorder (ASD) suggests behavioral ...
    • DCFNet: Deep Neural Network with Decomposed Convolutional Filters 

      Cheng, Xiuyuan; Sapiro, Guillermo; Qiu, Q; Calderbank, R (35th International Conference on Machine Learning, ICML 2018, 2018-01-01)
      ©35th International Conference on Machine Learning, ICML 2018.All Rights Reserved. Filters in a Convolutional Neural Network (CNN) contain model parameters learned from enormous amounts of data. In this paper, we suggest ...
    • Stop memorizing: A data-dependent regularization framework for intrinsic pattern learning 

      Daubechies, Ingrid; Lu, Jianfeng; Qiu, Qiang; Sapiro, Guillermo; Wang, Bao; Zhu, Wei
      Deep neural networks (DNNs) typically have enough capacity to fit random data by brute force even when conventional data-dependent regularizations focusing on the geometry of the features are imposed. We find out that the ...
    • Task-driven adaptive statistical compressive sensing of gaussian mixture models 

      Carin, Lawrence; Duarte-Carvajalino, JM; Sapiro, Guillermo; Yu, G (IEEE Transactions on Signal Processing, 2013-01-21)
      A framework for adaptive and non-adaptive statistical compressive sensing is developed, where a statistical model replaces the standard sparsity model of classical compressive sensing. We propose within this framework optimal ...