• A Framework For TV Logos Learning Using Linear Inverse Diffusion Filters For Noise Removal 

      Ramos-Cozar, Julian; Zeljković, Vesna; Gonzalez-Linares, Jose Maria; Guil-Mata, Nicolas; Tameze, Claude; [et al.] (IEEE, 2013)
      Different logotypes represent significant cues for video annotations. A combination of temporal and spatial segmentation methods can be used for logo extraction from various video contents. To achieve this segmentation, ...
    • CUVLE: Variable-Length Encoding on CUDA 

      Fuentes-Alventosa, Antonio; Gómez-Luna, Juan; Gonzalez-Linares, Jose Maria; Guil-Mata, Nicolas (2014-10-14)
      Data compression is the process of representing information in a compact form, in order to reduce the storage requirements and, hence, communication bandwidth. It has been one of the critical enabling technologies for ...
    • Efficient OpenCL-based concurrent tasks offloading on accelerators 

      Lázaro-Muñoz, Antonio J.; Gonzalez-Linares, Jose Maria; Gómez-Luna, Juan; Guil-Mata, Nicolas (Procedia Computer Science, 2017)
      Current heterogeneous platforms with CPUs and accelerators have the ability to launch several independent tasks simultaneously, in order to exploit concurrency among them. These tasks typically consist of data transfer ...
    • Evaluation of CNN architectures for gait recognition based on optical flow maps 

      Castro, F. M.; Marín-Jiménez, M.J.; Guil-Mata, Nicolas; López-Tapia, S.; Pérez de la Blanca, N. (2017)
      This work targets people identification in video based on the way they walk (\ie gait) by using deep learning architectures. We explore the use of convolutional neural networks (CNN) for learning high-level descriptors ...
    • Gait recognition and fall detection with inertial sensors 

      Delgado-Escaño, Rubén; Castro, Francisco M.; Marín-Jiménez, Manuel J.; Guil-Mata, Nicolas (2019-11-26)
      In contrast to visual information that is recorded by cameras placed somewhere, inertial information can be obtained from mobile phones that are commonly used in daily life. We present in this talk a general deep learning ...
    • Gait recognition applying Incremental learning 

      Castro, Francisco M.; Marín-Jiménez, Manuel J.; Guil-Mata, Nicolas; Schmid, Cordelia; Alahari, Karteek (2019-11-25)
      when new knowledge needs to be included in a classifier, the model is retrained from scratch using a huge training set that contains all available information of both old and new knowledge. However, in this talk, we present ...
    • Gait recognition from multiple view-points 

      Castro Payan, Francisco Manuel (UMA Editorial, 2018-11-15)
      Arquitectura de Computadores Resumen tesis: La identificación automática de personas está ganando mucha importancia en los últimos años ya que se puede aplicar en entornos que deben ser seguros (aeropuertos, centrales ...
    • Low-textured regions detection for improving stereoscopy algorithms 

      Ibarra-Delgado, Salvador; Ramos-Cozar, Julian; Gonzalez-Linares, Jose Maria; Gómez Luna, Juan; Guil-Mata, Nicolas (2014-07-29)
      The main goal of stereoscopy algorithms is the calculation of the disparity map between two frames corresponding to the same scene, and captured simultaneously by two different cameras. The different position (disparity) ...
    • Planificación Dinámica de Tareas en Aceleradores 

      Lazaro Muñoz, Antonio Jose (Uma Editorial, 2019-10)
      Las arquitecturas de computación de alto rendimiento (HPC) se han convertido en una herramienta clave para la investigación y desarrollo de aplicaciones en diversos campos científicos y técnicos. La incorporación de unidades ...
    • Pre-Ictal Phase Detection with SVMs 

      Ramos-Cozar, Julian; Zeljković, Vesna; Gonzalez-Linares, Jose Maria; Guil-Mata, Nicolas; Bojic, Milena; [et al.] (2014-07-29)
      Over 50 million persons worldwide are affected by epilepsy. Epilepsy is a brain disorder known for sudden, unexpected transitions from normal to pathological behavioral states called epileptic seizures. Epilepsy poses a ...
    • Robust tracking for augmented reality 

      Gonzalez-Linares, Jose Maria; Guil-Mata, Nicolas; Ramos-Cozar, Julian (2015-06-17)
      In this paper a method for improving a tracking algorithm in an augmented reality application is presented. This method addresses several issues to this particular application, like marker-less tracking and color constancy ...
    • A scheduling theory framework for GPU tasks efficient execution 

      Lázaro Muñoz, Antonio José; López Albelda, Bernabé; Gonzalez-Linares, Jose Maria; Guil-Mata, Nicolas (2018-07-16)
      Concurrent execution of tasks in GPUs can reduce the computation time of a workload by overlapping data transfer and execution commands. However it is difficult to implement an efficient run- time scheduler ...
    • Tasks Fairness Scheduler for GPU 

      López Albelda, Bernabé; Gonzalez-Linares, Jose Maria; Guil-Mata, Nicolas (2019-09-24)
      Nowadays GPU clusters are available in almost every data processing center. Their GPUs are typically shared by different applications that might have different processing needs and/or different levels of priority. As current ...
    • A weakly-supervised approach for discovering common objects in airport video surveillance footage 

      Castro Payan, Francisco Manuel; Delgado-Escaño, Rubén; Guil-Mata, Nicolas; Marín-Jiménez, Manuel J. (2019-07-22)
      Object detection in video is a relevant task in computer vision. Standard and current detectors are typically trained in a strongly supervised way, what requires a huge amount of labelled data. In contrast, in this paper ...