Home << 1 2 3 4 >>
List View
 | 
Citations
 | 
Details
   web
Records
Author (down) Miguel Angel Bautista; Sergio Escalera; Xavier Baro; Petia Radeva; Jordi Vitria; Oriol Pujol
Title Minimal Design of Error-Correcting Output Codes Type Journal Article
Year 2011 Publication Pattern Recognition Letters Abbreviated Journal PRL
Volume 33 Issue 6 Pages 693-702
Keywords Multi-class classification; Error-correcting output codes; Ensemble of classifiers
Abstract IF JCR CCIA 1.303 2009 54/103
The classification of large number of object categories is a challenging trend in the pattern recognition field. In literature, this is often addressed using an ensemble of classifiers. In this scope, the Error-correcting output codes framework has demonstrated to be a powerful tool for combining classifiers. However, most state-of-the-art ECOC approaches use a linear or exponential number of classifiers, making the discrimination of a large number of classes unfeasible. In this paper, we explore and propose a minimal design of ECOC in terms of the number of classifiers. Evolutionary computation is used for tuning the parameters of the classifiers and looking for the best minimal ECOC code configuration. The results over several public UCI datasets and different multi-class computer vision problems show that the proposed methodology obtains comparable (even better) results than state-of-the-art ECOC methodologies with far less number of dichotomizers.
Address
Corporate Author Thesis
Publisher Elsevier Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 0167-8655 ISBN Medium
Area Expedition Conference
Notes MILAB; OR;HuPBA;MV Approved no
Call Number Admin @ si @ BEB2011a Serial 1800
Permanent link to this record
 
 
Author (down) Meysam Madadi; Sergio Escalera; Jordi Gonzalez; Xavier Roca; Felipe Lumbreras
Title Multi-part body segmentation based on depth maps for soft biometry analysis Type Journal Article
Year 2015 Publication Pattern Recognition Letters Abbreviated Journal PRL
Volume 56 Issue Pages 14-21
Keywords 3D shape context; 3D point cloud alignment; Depth maps; Human body segmentation; Soft biometry analysis
Abstract This paper presents a novel method extracting biometric measures using depth sensors. Given a multi-part labeled training data, a new subject is aligned to the best model of the dataset, and soft biometrics such as lengths or circumference sizes of limbs and body are computed. The process is performed by training relevant pose clusters, defining a representative model, and fitting a 3D shape context descriptor within an iterative matching procedure. We show robust measures by applying orthogonal plates to body hull. We test our approach in a novel full-body RGB-Depth data set, showing accurate estimation of soft biometrics and better segmentation accuracy in comparison with random forest approach without requiring large training data.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes HuPBA; ISE; ADAS; 600.076;600.049; 600.063; 600.054; 302.018;MILAB Approved no
Call Number Admin @ si @ MEG2015 Serial 2588
Permanent link to this record
 
 
Author (down) Marco Pedersoli; Jordi Gonzalez; Andrew Bagdanov; Xavier Roca
Title Efficient Discriminative Multiresolution Cascade for Real-Time Human Detection Applications Type Journal Article
Year 2011 Publication Pattern Recognition Letters Abbreviated Journal PRL
Volume 32 Issue 13 Pages 1581-1587
Keywords
Abstract Human detection is fundamental in many machine vision applications, like video surveillance, driving assistance, action recognition and scene understanding. However in most of these applications real-time performance is necessary and this is not achieved yet by current detection methods.

This paper presents a new method for human detection based on a multiresolution cascade of Histograms of Oriented Gradients (HOG) that can highly reduce the computational cost of detection search without affecting accuracy. The method consists of a cascade of sliding window detectors. Each detector is a linear Support Vector Machine (SVM) composed of HOG features at different resolutions, from coarse at the first level to fine at the last one.

In contrast to previous methods, our approach uses a non-uniform stride of the sliding window that is defined by the feature resolution and allows the detection to be incrementally refined as going from coarse-to-fine resolution. In this way, the speed-up of the cascade is not only due to the fewer number of features computed at the first levels of the cascade, but also to the reduced number of windows that need to be evaluated at the coarse resolution. Experimental results show that our method reaches a detection rate comparable with the state-of-the-art of detectors based on HOG features, while at the same time the detection search is up to 23 times faster.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes ISE Approved no
Call Number Admin @ si @ PGB2011a Serial 1707
Permanent link to this record
 
 
Author (down) Marçal Rusiñol; Agnes Borras; Josep Llados
Title Relational Indexing of Vectorial Primitives for Symbol Spotting in Line-Drawing Images Type Journal Article
Year 2010 Publication Pattern Recognition Letters Abbreviated Journal PRL
Volume 31 Issue 3 Pages 188–201
Keywords Document image analysis and recognition, Graphics recognition, Symbol spotting ,Vectorial representations, Line-drawings
Abstract This paper presents a symbol spotting approach for indexing by content a database of line-drawing images. As line-drawings are digital-born documents designed by vectorial softwares, instead of using a pixel-based approach, we present a spotting method based on vector primitives. Graphical symbols are represented by a set of vectorial primitives which are described by an off-the-shelf shape descriptor. A relational indexing strategy aims to retrieve symbol locations into the target documents by using a combined numerical-relational description of 2D structures. The zones which are likely to contain the queried symbol are validated by a Hough-like voting scheme. In addition, a performance evaluation framework for symbol spotting in graphical documents is proposed. The presented methodology has been evaluated with a benchmarking set of architectural documents achieving good performance results.
Address
Corporate Author Thesis
Publisher Elsevier Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes DAG Approved no
Call Number DAG @ dag @ RBL2010 Serial 1177
Permanent link to this record
 
 
Author (down) Manuel Carbonell; Alicia Fornes; Mauricio Villegas; Josep Llados
Title A Neural Model for Text Localization, Transcription and Named Entity Recognition in Full Pages Type Journal Article
Year 2020 Publication Pattern Recognition Letters Abbreviated Journal PRL
Volume 136 Issue Pages 219-227
Keywords
Abstract In the last years, the consolidation of deep neural network architectures for information extraction in document images has brought big improvements in the performance of each of the tasks involved in this process, consisting of text localization, transcription, and named entity recognition. However, this process is traditionally performed with separate methods for each task. In this work we propose an end-to-end model that combines a one stage object detection network with branches for the recognition of text and named entities respectively in a way that shared features can be learned simultaneously from the training error of each of the tasks. By doing so the model jointly performs handwritten text detection, transcription, and named entity recognition at page level with a single feed forward step. We exhaustively evaluate our approach on different datasets, discussing its advantages and limitations compared to sequential approaches. The results show that the model is capable of benefiting from shared features by simultaneously solving interdependent tasks.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes DAG; 600.140; 601.311; 600.121 Approved no
Call Number Admin @ si @ CFV2020 Serial 3451
Permanent link to this record
 
 
Author (down) M. Bressan; Jordi Vitria
Title Nonparametric Discriminant Analysis and Nearest Neighbor Classification Type Journal Article
Year 2003 Publication Pattern Recognition Letters Abbreviated Journal PRL
Volume 24 Issue 15 Pages 2743–2749
Keywords
Abstract IF: 0.809
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes OR;MV Approved no
Call Number BCNPCL @ bcnpcl @ BrV2003b Serial 367
Permanent link to this record
 
 
Author (down) Lluis Gomez; Ali Furkan Biten; Ruben Tito; Andres Mafla; Marçal Rusiñol; Ernest Valveny; Dimosthenis Karatzas
Title Multimodal grid features and cell pointers for scene text visual question answering Type Journal Article
Year 2021 Publication Pattern Recognition Letters Abbreviated Journal PRL
Volume 150 Issue Pages 242-249
Keywords
Abstract This paper presents a new model for the task of scene text visual question answering. In this task questions about a given image can only be answered by reading and understanding scene text. Current state of the art models for this task make use of a dual attention mechanism in which one attention module attends to visual features while the other attends to textual features. A possible issue with this is that it makes difficult for the model to reason jointly about both modalities. To fix this problem we propose a new model that is based on an single attention mechanism that attends to multi-modal features conditioned to the question. The output weights of this attention module over a grid of multi-modal spatial features are interpreted as the probability that a certain spatial location of the image contains the answer text to the given question. Our experiments demonstrate competitive performance in two standard datasets with a model that is faster than previous methods at inference time. Furthermore, we also provide a novel analysis of the ST-VQA dataset based on a human performance study. Supplementary material, code, and data is made available through this link.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes DAG; 600.084; 600.121 Approved no
Call Number Admin @ si @ GBT2021 Serial 3620
Permanent link to this record
 
 
Author (down) Kai Wang; Joost Van de Weijer; Luis Herranz
Title ACAE-REMIND for online continual learning with compressed feature replay Type Journal Article
Year 2021 Publication Pattern Recognition Letters Abbreviated Journal PRL
Volume 150 Issue Pages 122-129
Keywords online continual learning; autoencoders; vector quantization
Abstract Online continual learning aims to learn from a non-IID stream of data from a number of different tasks, where the learner is only allowed to consider data once. Methods are typically allowed to use a limited buffer to store some of the images in the stream. Recently, it was found that feature replay, where an intermediate layer representation of the image is stored (or generated) leads to superior results than image replay, while requiring less memory. Quantized exemplars can further reduce the memory usage. However, a drawback of these methods is that they use a fixed (or very intransigent) backbone network. This significantly limits the learning of representations that can discriminate between all tasks. To address this problem, we propose an auxiliary classifier auto-encoder (ACAE) module for feature replay at intermediate layers with high compression rates. The reduced memory footprint per image allows us to save more exemplars for replay. In our experiments, we conduct task-agnostic evaluation under online continual learning setting and get state-of-the-art performance on ImageNet-Subset, CIFAR100 and CIFAR10 dataset.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes LAMP; 600.147; 601.379; 600.120; 600.141 Approved no
Call Number Admin @ si @ WWH2021 Serial 3575
Permanent link to this record
 
 
Author (down) Josep Llados; Horst Bunke; Enric Marti
Title Finding rotational symmetries by cyclic string matching Type Journal Article
Year 1997 Publication Pattern recognition letters Abbreviated Journal PRL
Volume 18 Issue 14 Pages 1435-1442
Keywords Rotational symmetry; Reflectional symmetry; String matching
Abstract Symmetry is an important shape feature. In this paper, a simple and fast method to detect perfect and distorted rotational symmetries of 2D objects is described. The boundary of a shape is polygonally approximated and represented as a string. Rotational symmetries are found by cyclic string matching between two identical copies of the shape string. The set of minimum cost edit sequences that transform the shape string to a cyclically shifted version of itself define the rotational symmetry and its order. Finally, a modification of the algorithm is proposed to detect reflectional symmetries. Some experimental results are presented to show the reliability of the proposed algorithm
Address
Corporate Author Thesis
Publisher Elsevier Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes DAG;IAM; Approved no
Call Number IAM @ iam @ LBM1997a Serial 1562
Permanent link to this record
 
 
Author (down) Jose Antonio Rodriguez; Florent Perronnin; Gemma Sanchez; Josep Llados
Title Unsupervised writer adaptation of whole-word HMMs with application to word-spotting Type Journal Article
Year 2010 Publication Pattern Recognition Letters Abbreviated Journal PRL
Volume 31 Issue 8 Pages 742–749
Keywords Word-spotting; Handwriting recognition; Writer adaptation; Hidden Markov model; Document analysis
Abstract In this paper we propose a novel approach for writer adaptation in a handwritten word-spotting task. The method exploits the fact that the semi-continuous hidden Markov model separates the word model parameters into (i) a codebook of shapes and (ii) a set of word-specific parameters.

Our main contribution is to employ this property to derive writer-specific word models by statistically adapting an initial universal codebook to each document. This process is unsupervised and does not even require the appearance of the keyword(s) in the searched document. Experimental results show an increase in performance when this adaptation technique is applied. To the best of our knowledge, this is the first work dealing with adaptation for word-spotting. The preliminary version of this paper obtained an IBM Best Student Paper Award at the 19th International Conference on Pattern Recognition.
Address
Corporate Author Thesis
Publisher Elsevier Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes DAG Approved no
Call Number DAG @ dag @ RPS2010 Serial 1290
Permanent link to this record
 
 
Author (down) Jordi Vitria; J. Llacer
Title Reconstructing 3D light microscopic images using the EM algorithm Type Journal Article
Year 1996 Publication Pattern Recognition Letters Abbreviated Journal
Volume 17 Issue 14 Pages 1491–1498
Keywords
Abstract
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes OR;MV Approved no
Call Number BCNPCL @ bcnpcl @ ViL1996 Serial 74
Permanent link to this record
 
 
Author (down) Jaume Gibert; Ernest Valveny; Horst Bunke
Title Feature Selection on Node Statistics Based Embedding of Graphs Type Journal Article
Year 2012 Publication Pattern Recognition Letters Abbreviated Journal PRL
Volume 33 Issue 15 Pages 1980–1990
Keywords Structural pattern recognition; Graph embedding; Feature ranking; PCA; Graph classification
Abstract Representing a graph with a feature vector is a common way of making statistical machine learning algorithms applicable to the domain of graphs. Such a transition from graphs to vectors is known as graphembedding. A key issue in graphembedding is to select a proper set of features in order to make the vectorial representation of graphs as strong and discriminative as possible. In this article, we propose features that are constructed out of frequencies of node label representatives. We first build a large set of features and then select the most discriminative ones according to different ranking criteria and feature transformation algorithms. On different classification tasks, we experimentally show that only a small significant subset of these features is needed to achieve the same classification rates as competing to state-of-the-art methods.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes DAG Approved no
Call Number Admin @ si @ GVB2012b Serial 1993
Permanent link to this record
 
 
Author (down) Jaume Amores; Petia Radeva
Title Registration and Retrieval of Highly Elastic Bodies using Contextual Information Type Journal Article
Year 2005 Publication Pattern Recognition Letters Abbreviated Journal PRL
Volume 26 Issue 11 Pages 1720–1731
Keywords
Abstract IF: 1.138
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes ADAS;MILAB Approved no
Call Number ADAS @ adas @ AmR2005b Serial 592
Permanent link to this record
 
 
Author (down) Jaume Amores; N. Sebe; Petia Radeva
Title Boosting the distance estimation: Application to the K-Nearest Neighbor Classifier Type Journal Article
Year 2006 Publication Pattern Recognition Letters Abbreviated Journal PRL
Volume 27 Issue 3 Pages 201–209
Keywords
Abstract
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes ADAS;MILAB Approved no
Call Number ADAS @ adas @ ASR2006 Serial 643
Permanent link to this record
 
 
Author (down) Ivet Rafegas; Maria Vanrell; Luis A Alexandre; G. Arias
Title Understanding trained CNNs by indexing neuron selectivity Type Journal Article
Year 2020 Publication Pattern Recognition Letters Abbreviated Journal PRL
Volume 136 Issue Pages 318-325
Keywords
Abstract The impressive performance of Convolutional Neural Networks (CNNs) when solving different vision problems is shadowed by their black-box nature and our consequent lack of understanding of the representations they build and how these representations are organized. To help understanding these issues, we propose to describe the activity of individual neurons by their Neuron Feature visualization and quantify their inherent selectivity with two specific properties. We explore selectivity indexes for: an image feature (color); and an image label (class membership). Our contribution is a framework to seek or classify neurons by indexing on these selectivity properties. It helps to find color selective neurons, such as a red-mushroom neuron in layer Conv4 or class selective neurons such as dog-face neurons in layer Conv5 in VGG-M, and establishes a methodology to derive other selectivity properties. Indexing on neuron selectivity can statistically draw how features and classes are represented through layers in a moment when the size of trained nets is growing and automatic tools to index neurons can be helpful.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes CIC; 600.087; 600.140; 600.118 Approved no
Call Number Admin @ si @ RVL2019 Serial 3310
Permanent link to this record