Enviaments recents

  • Hierarchical object detection with deep reinforcement learning 

    Bellver, Míriam; Giró Nieto, Xavier; Marqués Acosta, Fernando; Torres, Jordi (2016)
    Comunicació de congrés
    Accés obert
    We present a method for performing hierarchical object detection in images guided by a deep reinforcement learning agent. The key idea is to focus on those parts of the image that contain richer information and zoom on ...
  • Is a “happy dog” more “happy” than “dog”? - Adjective and Noun Contributions for Adjective-Noun Pair prediction 

    Fernàndez, Dèlia; Campos Camúñez, Victor; Jou, Brendan; Giró Nieto, Xavier; Chang, Shih-Fu (2016)
    Comunicació de congrés
    Accés obert
  • Hierarchical visual description schemes for still images and video sequences 

    Salembier Clairon, Philippe Jean; O'Connor, N; Correia Fernandez-Pereira, Paulo; Pereira, F (Institute of Electrical and Electronics Engineers (IEEE), 1999)
    Text en actes de congrés
    Accés obert
    This paper proposes two description schemes (DSs) to describe the visual information of an audio-visual (AV) document. The first one, is devoted to still images. It describes the image visual appearance and its structure ...
  • Optimum watermark detection in color images 

    Sayrol Clols, Elisa; Vidal Manzano, José; Cabanillas, Silvia; Santamaria, Sonia (Institute of Electrical and Electronics Engineers (IEEE), 1999)
    Text en actes de congrés
    Accés obert
    This work concentrates on the problem of watermarking embedding and optimum detection in color images through the use of spread spectrum techniques both in space (Direct Sequence Spread Spectrum or DSSS) and frequency ...
  • Human face segmentation and tracking using connected components and partition projection 

    Marqués Acosta, Fernando; Vilaplana Besler, Verónica; Buxes, A (Institute of Electrical and Electronics Engineers (IEEE), 1999)
    Text en actes de congrés
    Accés obert
    A new technique for segmenting and tracking human faces in video sequences is presented. The algorithm uses a connected operator to extract the connected component that more likely belongs to a face. Such a connected ...
  • Accurate and automatic NOAA-AVHRR image navigation using a global contour matching approach 

    Eugenio, F; Marqués Acosta, Fernando; Gómez, L; Suarez, E; Rovaris, E (2000)
    Text en actes de congrés
    Accés obert
    The problem of precise and automatic AVHRR image navigation is tractable in theory, but has proved to be somewhat difficult in practice. The authors' work has been motivated by the need for a fully automatic and operational ...
  • Perceptual masks in the wavelet domain for color image watermarking 

    Sayrol Clols, Elisa; Martínez Serra, Elena (Institute of Electrical and Electronics Engineers (IEEE), 2015)
    Text en actes de congrés
    Accés restringit per política de l'editorial
    In this paper, three different perceptual masks in the wavelet domain are investigated for image watermarking systems. Along with an already existing method, we present two alternative perceptual masks based on visual ...
  • Shallow and deep convolutional networks for saliency prediction 

    Pan, Junting; Sayrol Clols, Elisa; Giró Nieto, Xavier; McGuinness, Kevin; O'Connor, Noel (Institute of Electrical and Electronics Engineers (IEEE), 2016)
    Comunicació de congrés
    Accés restringit per política de l'editorial
    The prediction of salient areas in images has been traditionally addressed with hand-crafted features based on neuroscience principles. This paper, however, addresses the problem with a completely data-driven approach by ...
  • PSyCo: manifold span reduction for super resolution 

    Pérez Pellitero, Eduardo; Salvador, Jordi; Ruiz Hidalgo, Javier; Rosenhahn, Bodo (Institute of Electrical and Electronics Engineers (IEEE), 2016)
    Text en actes de congrés
    Accés restringit per política de l'editorial
    The main challenge in Super Resolution (SR) is to discover the mapping between the low- and highresolution manifolds of image patches, a complex ill-posed problem which has recently been addressed through piecewise linear ...
  • Matehematic morphology approach for renal biopsy analysis 

    Marqués Acosta, Fernando; Cuberas, Gemma; Gasull Llampallas, Antoni; Seron, Daniel; Moreso, Francesc; Joshi, Nayana (Institute of Electrical and Electronics Engineers (IEEE), 2004)
    Text en actes de congrés
    Accés restringit per política de l'editorial
    This paper proposes a new technique for the analysis of renal biopsies stained with Sirius red and digitized under non-polarized light. The renal interstitial space, the cortex area and the tubules should be segmented to ...

Mostra'n més