Enviaments recents

  • Machine and deep learning approaches to localization and range estimation of underwater acoustic sources 

    Houégnigan, Ludwig; Safari, Pooyan; Nadeu Camprubí, Climent; André, Michel; Van der Schaar, Mike Connor Roger Malcolm (Institute of Electrical and Electronics Engineers (IEEE), 2017)
    Comunicació de congrés
    Accés restringit per política de l'editorial
    This paper introduces ongoing experiments and early results for the underwater localization and range estimation of acoustic sources. Beyond classical results obtained for direction of arrival estimation, results concerning ...
  • Skip RNN: learning to skip state updates in recurrent neural networks 

    Campos Camunez, Victor; Jou, Brendan; Giró Nieto, Xavier; Torres Viñals, Jordi; Chang, Shih-Fu (2018)
    Comunicació de congrés
    Accés obert
    Recurrent Neural Networks (RNNs) continue to show outstanding performance in sequence modeling tasks. However, training RNNs on long sequences often face challenges like slow inference, vanishing gradients and difficulty ...
  • Dimension spreading for coherent opportunistic communications 

    Borràs Pino, Jordi; Font Segura, Josep; Riba Sagarra, Jaume; Vázquez Grau, Gregorio (Institute of Electrical and Electronics Engineers (IEEE), 2018)
    Text en actes de congrés
    Accés restringit per política de l'editorial
    The waveform optimization problem for opportunistic communications is addressed, based on sensing the second-order statistics of the existing transmissions. We propose a minimum-norm waveform optimization that exhibits ...
  • Learning from unequally reliable blind ensembles of classifiers 

    Traganitis, Panagiotis; Pagès Zamora, Alba Maria; Giannakis, Georgios B. (Institute of Electrical and Electronics Engineers (IEEE), 2017)
    Text en actes de congrés
    Accés obert
    The rising interest in pattern recognition and data analytics has spurred the development of a plethora of machine learning algorithms and tools. However, as each algorithm has its strengths and weaknesses, one is motivated ...
  • Entropy-based covariance determinant estimation 

    Cabrera Estanyol, Ferran de; Riba Sagarra, Jaume; Vázquez Grau, Gregorio (Institute of Electrical and Electronics Engineers (IEEE), 2017)
    Comunicació de congrés
    Accés restringit per política de l'editorial
    An information-theoretic approach is described to estimate the determinant of the covariance matrix of a random vector sequence (a common task in a wide range of estimation and detection problems in signal processing for ...
  • The importance of color information in face recognition 

    Torres Urgell, Lluís; Reutter, Jean-Yves; Lorente, Luis (Institute of Electrical and Electronics Engineers (IEEE), 1999)
    Text en actes de congrés
    Accés obert
    A common feature found in practically all technical approaches proposed for face recognition is the use of only the luminance information associated to the face image. One may wonder if this is due to the low importance ...
  • All-Optical Intra-PON Data Routing Between ONUs with a MG-Y Tunable Laser as 2.5 Gbps Burst-Mode Transmitter 

    Bonada Bó, Francesc Xavier; Schrenk, Bernhard; Fabrega Sanchez, Josep Maria; Lázaro Villa, José Antonio; Forzati, Marco; Jean Rigole,, Pierre; Prat Gomà, Josep Joan (Institute of Electrical and Electronics Engineers (IEEE), 2011)
    Text en actes de congrés
    Accés restringit per política de l'editorial
    Direct communication between ONUs is experimentally demonstrated with a tunable MG-Y laser in a ring+tree PON for 640 users, without passing electrically powered equipment.
  • Foreground objects segmentation for moving camera scenarios based on SCGMM 

    Gallego Vila, Jaime; Pardàs Feliu, Montse; Solano, Montse (2011)
    Text en actes de congrés
    Accés restringit per política de l'editorial
    In this paper we present a new system for segmenting non-rigid objects in moving camera sequences for indoor and outdoor scenarios that achieves a correct object segmentation via global MAP-MRF framework formulation for ...
  • Diversity techniques for blind equalization in mobile communications 

    Lamarca Orozco, M. Meritxell; Vázquez Grau, Gregorio (1997)
    Text en actes de congrés
    Accés obert
    This paper deals with blind equalization of mobile channels, which are either frequency-selective or multiplicative. The proposed algorithm can be used for channel distortion compensation in diversity systems subject ...
  • Balancing egoistic and altruistic transmit beamforming in femtocell networks 

    Husso, Mika; Dowhuszko, Alexis; Hamalainen, K.; Pastore, Adriano; Rodríguez Fonollosa, Javier (Institute of Electrical and Electronics Engineers (IEEE), 2011)
    Text en actes de congrés
    Accés restringit per política de l'editorial
    In this paper, we study the balancing of egoistic (maximum-ratio, MR) and altruistic (zero-forcing, ZF) beamforming (BF) in femtocells through simulations. To investigate the achievable gains from operating between the ...
  • On a mutual information and a capacity bound gap of pilot-aided MIMO channels 

    Pastore, Adriano; Joham, Michael; Rodríguez Fonollosa, Javier (Institute of Electrical and Electronics Engineers (IEEE), 2011)
    Text en actes de congrés
    Accés restringit per política de l'editorial
    For single-user MIMO channels with partial re ceiver CSI, we study the difference between a lower bound and two alternative upper bounds of the mutual information achieved with Gaussian codebooks. These differences are ...
  • Svq: a proposal for still image coding in mpeg 4 - snhc 

    Torres Urgell, Lluís; Gimeno, D; García Luque, David (European Commission. EU Publications, 1997)
    Text en actes de congrés
    Accés obert
    A technique for efficient coding of homogeneous textures is presented here. The technique is based on the use of Stochastic Vector Quantization and provides very high compression with graceful degradation. To encode the ...

Mostra'n més