Ara es mostren els items 20-39 de 43

    • Graph matching using SIFT descriptors: an application to pose recovery of a mobile robot 

      Sanromà Güell, Gerard; Alquézar Mancho, René; Serratosa Casanelles, Francesc (2010)
      Text en actes de congrés
      Accés obert
      Image-feature matching based on Local Invariant Feature Extraction (LIFE) methods has proven to be successful, and SIFT is one of the most effective. SIFT matching uses only local texture information to compute the ...
    • Group-wise sparse correspondences between images based on a common labelling approach 

      Solé Ribalta, Albert; Sanromà Güell, Gerard; Serratosa Casanelles, Francesc; Alquézar Mancho, René (SciTePress, 2012)
      Text en actes de congrés
      Accés restringit per política de l'editorial
      Finding sparse correspondences between two images is a usual process needed for several higher-level computer vision tasks. For instance, in robot positioning, it is frequent to make use of images that the robot captures ...
    • Heuri: a Scrabble© playing engine using a probability-based heuristic 

      González Romero, Alejandro; Alquézar Mancho, René; Ramírez Flores, Arturo; González Acuña, Francisco; García Olmedo, Ian (2022-02-16)
      Article
      Accés obert
      The game of Scrabble has been successfully tackled by two engines: Quackle and Maven. They attain the state-of-the-art in Computer Scrabble. These engines use simulation techniques and precalculated values to achieve ...
    • Incremental construction of LSTM recurrent neural network 

      Ribeiro, Evandsa Sabrine Lopes-Lima; Alquézar Mancho, René (2002-12)
      Report de recerca
      Accés obert
      Long Short--Term Memory (LSTM) is a recurrent neural network that uses structures called memory blocks to allow the net remember significant events distant in the past input sequence in order to solve long time lag ...
    • Informàtica bàsica II, ETSEIB. Memòria del curs 1994-1995 

      Vila Marta, Sebastià; Pla García, Núria; Soto Riera, Antoni; Pérez Vidal, Lluís; Roura Ferret, Salvador; Franquesa Niubó, Marta; Cotrina Navau, Josep; Alquézar Mancho, René; Martínez Parra, Conrado (1995-02-06)
      Report de recerca
      Accés obert
      Memòria de l'assignatura d'Infomàtica bàsica II del curs 94-95.
    • Label noise in subtype discrimination of class C G protein-coupled receptors: A systematic approach to the analysis of classification errors 

      Koenig, Caroline; Cárdenas Domíınguez, Martha Ivón; Giraldo Arjonilla, Jesús; Alquézar Mancho, René; Vellido Alcacena, Alfredo (2015-09-29)
      Article
      Accés obert
      Background: The characterization of proteins in families and subfamilies, at different levels, entails the definition and use of class labels. When the adscription of a protein to a family is uncertain, or even wrong, this ...
    • Misclassification of class C G-protein-coupled receptors as a label noise problem 

      König, Caroline; Vellido Alcacena, Alfredo; Alquézar Mancho, René; Giraldo Arjonilla, Jesús (2014)
      Comunicació de congrés
      Accés obert
      G-Protein-Coupled Receptors (GPCRs) are cell membrane proteins of relevance to biology and pharmacology. Their supervised classification in subtypes is hampered by label noise, which stems from a combination of expert ...
    • MSClique: Multiple structure discovery through the maximum weighted clique problem 

      Sanromà Güell, Gerard; Peñate Sánchez, Adrián; Alquézar Mancho, René; Serratosa Casanelles, Francesc; Moreno-Noguer, Francesc; Andrade-Cetto, Juan; González Ballester, Miguel Ángel (2016-01-01)
      Article
      Accés obert
      We present a novel approach for feature correspondence and multiple structure discovery in computer vision. In contrast to existing methods, we exploit the fact that point-sets on the same structure usually lie close to ...
    • Neural networks with periodic and monotonic activation functions: a comparative study in classification problems 

      Romero Merino, Enrique; Sopena, Josep Maria; Alquézar Mancho, René; Moliner, Joan L. (2000-02)
      Report de recerca
      Accés obert
      This article discusses a number of reasons why the use of non-monotonic functions as activation functions can lead to a marked improvement in the performance of a neural network. Using a wide range of benchmarks we show ...
    • Object recognition and tracking in video sequences: a new integrated methodology 

      Amézquita Gómez, Nicolás; Alquézar Mancho, René; Serratosa, Francesc (2006-06)
      Report de recerca
      Accés obert
      This paper describes a methodology that integrates recognition and segmentation, simultaneously with image tracking in a cooperative manner, for recognition of objects (or parts of them) in image sequences. A probabilistic ...
    • Reducing the n-gram feature space of class C GPCRs to subtype-discriminating patterns 

      König, Caroline; Alquézar Mancho, René; Vellido Alcacena, Alfredo; Giraldo Arjonilla, Jesús (2014-10-23)
      Article
      Accés obert
      G protein-coupled receptors (GPCRs) are a large and heterogeneous superfamily of receptors that are key cell players for their role as extracellular signal transmitters. Class C GPCRs, in particular, are of great interest ...
    • Searching and tracking people in urban environments with static and dynamic obstacles 

      Goldhoorn, Alex; Garrell Zulueta, Anais; Alquézar Mancho, René; Sanfeliu Cortés, Alberto (2017-12-01)
      Article
      Accés obert
      Searching and tracking people in crowded urban areas where they can be occluded by static or dynamic obstacles is an important behavior for social robots which assist humans in urban outdoor environments. In this work, we ...
    • Searching and tracking people with cooperative mobile robots 

      Goldhoorn, Alex; Garrell Zulueta, Anais; Alquézar Mancho, René; Sanfeliu Cortés, Alberto (2018)
      Article
      Accés obert
      Social robots should be able to search and track people in order to help them. In this paper we present two different techniques for coordinated multi-robot teams for searching and tracking people. A probability map (belief) ...
    • Smooth simultaneous structural graph matching and point-set registration 

      Sanromà Güell, Gerard; Alquézar Mancho, René; Serratosa Casanelles, Francesc (Springer, 2011)
      Text en actes de congrés
      Accés obert
      We present a graph matching method that encompasses both a model of structural consistency and a model of geometrical deformations. Our method poses the graph matching problem as one of mixture modelling which is solved ...
    • SVM-based classification of class C GPCRs from alignment-free physicochemical transformations of their sequences 

      König, Caroline; Cruz Barbosa, Raúl; Alquézar Mancho, René; Vellido Alcacena, Alfredo (Springer Berlin Heidelberg, 2013)
      Text en actes de congrés
      Accés obert
      G protein-coupled receptors (GPCRs) have a key function in regulating the function of cells due to their ability to transmit extracelullar signals. Given that the 3D structure and the functionality of most GPCRs is unknown, ...
    • Symbolic and connectionist learning techniques for grammatical inference 

      Alquézar Mancho, René (Universitat Politècnica de Catalunya, 1997-05-12)
      Tesi
      Accés obert
      This thesis is structured in four parts for a total of ten chapters. <br/><br/>The first part, introduction and review (Chapters 1 to 4), presents an extensive state-of-the-art review of both symbolic and connectionist GI ...
    • Systematic analysis of primary sequence domain segments for the discrimination between class C GPCR subtypes 

      König, Caroline; Alquézar Mancho, René; Vellido Alcacena, Alfredo; Giraldo Arjonilla, Jesús (2018-03-01)
      Article
      Accés obert
      G-protein-coupled receptors (GPCRs) are a large and diverse super-family of eukaryotic cell membrane proteins that play an important physiological role as transmitters of extracellular signal. In this paper, we investigate ...
    • Teaching a drone to accompany a person from demonstrations using non-linear ASFM 

      Garrell Zulueta, Anais; Coll Gomilla, Carles; Alquézar Mancho, René; Sanfeliu Cortés, Alberto (Institute of Electrical and Electronics Engineers (IEEE), 2019)
      Text en actes de congrés
      Accés restringit per política de l'editorial
      In this paper, we present a new method based on the Aerial Social Force Model (ASFM) to allow human-drone side-by-side social navigation in real environments. To tackle this problem, the present work proposes a new ...
    • The extracellular N-terminal domain suffices to discriminate class C G Protein-Coupled Receptor subtypes from n-grams of their sequences 

      König, Caroline; Alquézar Mancho, René; Vellido Alcacena, Alfredo; Giraldo Arjonilla, Jesús (Institute of Electrical and Electronics Engineers (IEEE), 2015)
      Text en actes de congrés
      Accés obert
      The investigation of protein functionality often relies on the knowledge of crystal 3-D structure. This structure is not always known or easily unravelled, which is the case of eukaryotic cell membrane proteins such as G ...
    • Tracking deformable objects and dealing with same class object occlusion 

      Alquézar Mancho, René; Amézquita Gómez, Nicolás; Serratosa Casanelles, Francesc (INSTICC Press. Institute for Systems and Technologies of Information, Control and Communication, 2009)
      Capítol de llibre
      Accés obert
      This paper presents an extension of a previously reported method for object tracking in video sequences to handle the problems of object crossing and occlusion by other objects in the same class that the one followed. The ...