Enviaments recents

  • Seabed mapping in coastal shallow waters using high resolution multispectral and hyperspectral imagery 

    Marcello, Javier; Eugenio, Francisco; Martín Abasolo, Javier; Marqués Acosta, Fernando (Multidisciplinary Digital Publishing Institute (MDPI), 2018-08-01)
    Article
    Accés obert
    Coastal ecosystems experience multiple anthropogenic and climate change pressures. To monitor the variability of the benthic habitats in shallow waters, the implementation of effective strategies is required to support ...
  • Temporally coherent 3D point cloud video segmentation in generic scenes 

    Lin, Xiao; Casas Pla, Josep Ramon; Pardàs Feliu, Montse (2018-03-02)
    Article
    Accés obert
    Video segmentation is an important building block for high level applications, such as scene understanding and interaction analysis. While outstanding results are achieved in this field by the state-of-the-art learning and ...
  • Scanpath and saliency prediction on 360 degree images 

    Assens Reina, Marc; Giró Nieto, Xavier; McGuinness, Kevin; O'Connor, Noel (2018-06-23)
    Article
    Accés restringit per política de l'editorial
    We introduce deep neural networks for scanpath and saliency prediction trained on 360-degree images. The scanpath prediction model called SaltiNet is based on a temporal-aware novel representation of saliency information ...
  • Introduction to the special issue: egocentric vision and lifelogging 

    Dimiccoli, Mariella; Gurrin, Cathal; Crandall, David; Giró Nieto, Xavier; Radeva, Petia (2018-06-15)
    Article
    Accés restringit per política de l'editorial
  • Magnetic resonance imaging and machine learning make a valuable combined tool for the screening of preclinical AD 

    Petrone, Paula; Vilaplana Besler, Verónica; Casamitjana Díaz, Adrià; Domingo Gispert, Juan; Molinuevo, Jose Luis; Sánchez Escobedo, Dalila (2017-07)
    Article
    Accés restringit per política de l'editorial
  • Hierarchical stack filtering: a bitplane-based algorithm for massively parallel processors 

    Frías Velazquez, Andres; Morros Rubió, Josep Ramon; García Molina, Mario; Philips, Wilfried (2017-03-15)
    Article
    Accés obert
    With the development of novel parallel architectures for image processing, the implementation of well-known image operators needs to be reformulated to take advantage of the so-called massive parallelism. In this work, we ...
  • 3D hierarchical optimization for multi-view depth map coding 

    Maceira, Marc; Varas, David; Morros Rubió, Josep Ramon; Ruiz Hidalgo, Javier; Marqués Acosta, Fernando (2017-11-28)
    Article
    Accés restringit per política de l'editorial
    Depth data has a widespread use since the popularity of high resolution 3D sensors. In multi-view sequences, depth information is used to supplement the color data of each view. This article proposes a joint encoding of ...
  • A closed-loop approach for tracking a humanoid robot using particle filtering and depth data 

    Martínez González, Pablo Arturo; Lin, Xiao; Castelan, Mario; Casas Pla, Josep Ramon; Arechavaleta, Gustavo (Springer, 2017-05-24)
    Article
    Accés obert
    Humanoid robots introduce instabilities during biped march that complicate the process of estimating their position and orientation along time. Tracking humanoid robots may be useful not only in typical applications such ...
  • Distributed training strategies for a computer vision deep learning algorithm on a distributed GPU cluster 

    Campos, Victor; Sastre, Francesc; Yagües, Maurici; Bellver, Míriam; Giró Nieto, Xavier; Torres Viñals, Jordi (Elsevier, 2017)
    Article
    Accés obert
    Deep learning algorithms base their success on building high learning capacity models with millions of parameters that are tuned in a data-driven fashion. These models are trained by processing millions of examples, so ...
  • Multiscale combinatorial grouping for image segmentation and object proposal generation 

    Pont Tuset, Jordi; Arbelaez, Pablo Andrés; Barron, Jonathan; Marqués Acosta, Fernando; Malik, Jitendra (2017-01-01)
    Article
    Accés obert
    We propose a unified approach for bottom-up hierarchical image segmentation and object proposal generation for recognition, called Multiscale Combinatorial Grouping (MCG). For this purpose, we first develop a fast normalized ...
  • From pixels to sentiment: fine-tuning CNNs for visual sentiment prediction 

    Campos Camunez, Victor; Jou, Brendan; Giró Nieto, Xavier (2017-02-05)
    Article
    Accés restringit per política de l'editorial
    Visual multimedia have become an inseparable part of our digital social lives, and they often capture moments tied with deep affections. Automated visual sentiment analysis tools can provide a means of extracting the rich ...
  • Optimum graph cuts for pruning binary partition trees of polarimetric SAR images 

    Salembier Clairon, Philippe Jean; Foucher, Samuel (Institute of Electrical and Electronics Engineers (IEEE), 2016-09-01)
    Article
    Accés obert
    This paper investigates several optimum graph-cut techniques for pruning binary partition trees (BPTs) and their usefulness for the low-level processing of polarimetric synthetic aperture radar (PolSAR) images. BPTs group ...

Mostra'n més