Home [191–200] << 201 202 203 204 205 206 207 208 209 210 >> [211–220]
List View
 | 
Citations
 | 
Details
   web
Records
Author Lluis Gomez; Marçal Rusiñol; Ali Furkan Biten; Dimosthenis Karatzas
Title Subtitulació automàtica d'imatges. Estat de l'art i limitacions en el context arxivístic Type Conference Article
Year 2018 Publication Jornades Imatge i Recerca Abbreviated Journal
Volume Issue Pages
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 (up) JIR
Notes DAG; 600.084; 600.135; 601.338; 600.121; 600.129 Approved no
Call Number Admin @ si @ GRB2018 Serial 3173
Permanent link to this record
 
 
Author Fernando Vilariño
Title Computer Vision and Performing Arts Type Conference Article
Year 2015 Publication Korean Scholars of Marketing Science Abbreviated Journal
Volume Issue Pages
Keywords
Abstract
Address Seoul; Korea; October 2015
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 (up) KAMS
Notes MV;SIAI Approved no
Call Number Admin @ si @Vil2015 Serial 2799
Permanent link to this record
 
 
Author Carles Fernandez; Pau Baiget; Xavier Roca; Jordi Gonzalez
Title Natural Language Descriptions of Human Behavior from Video Sequences Type Conference Article
Year 2007 Publication Advances in Artificial Intelligence, 30th Annual Conference on Artificial Intelligence Abbreviated Journal
Volume 4667 Issue Pages 279–292
Keywords
Abstract
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title LNCS
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference (up) KI
Notes ISE Approved no
Call Number ISE @ ise @ FBR2007b Serial 921
Permanent link to this record
 
 
Author David Roche; Debora Gil; Jesus Giraldo
Title Assessing agonist efficacy in an uncertain Em world Type Conference Article
Year 2012 Publication 40th Keystone Symposia on mollecular and celular biology Abbreviated Journal
Volume Issue Pages 79
Keywords
Abstract The operational model of agonism has been widely used for the analysis of agonist action since its formulation in 1983. The model includes the Em parameter, which is defined as the maximum response of the system. The methods for Em estimation provide Em values not significantly higher than the maximum responses achieved by full agonists. However, it has been found that that some classes of compounds as, for instance, superagonists and positive allosteric modulators can increase the full agonist maximum response, implying upper limits for Em and thereby posing doubts on the validity of Em estimates. Because of the correlation between Em and operational efficacy, τ, wrong Em estimates will yield wrong τ estimates.
In this presentation, the operational model of agonism and various methods for the simulation of allosteric modulation will be analyzed. Alternatives for curve fitting will be presented and discussed.
Address Fairmont Banff Springs, Banff, Alberta, Canada
Corporate Author Keystone Symposia Thesis
Publisher Keystone Symposia Place of Publication Editor A. Christopoulus and M. Bouvier
Language english Summary Language english Original Title
Series Editor Keystone Symposia Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference (up) KSMCB
Notes IAM Approved no
Call Number IAM @ iam @ RGG2012 Serial 1855
Permanent link to this record
 
 
Author Fernando Vilariño
Title Giving Value to digital collections in the Public Library Type Conference Article
Year 2016 Publication Librarian 2020 Abbreviated Journal
Volume Issue Pages
Keywords
Abstract
Address Brussels; Belgium; October 2016
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 (up) LIB
Notes MV; 600.097;SIAI Approved no
Call Number Admin @ si @Vil2016a Serial 2802
Permanent link to this record
 
 
Author Hassan Ahmed Sial; Ramon Baldrich; Maria Vanrell; Dimitris Samaras
Title Light Direction and Color Estimation from Single Image with Deep Regression Type Conference Article
Year 2020 Publication London Imaging Conference Abbreviated Journal
Volume Issue Pages
Keywords
Abstract We present a method to estimate the direction and color of the scene light source from a single image. Our method is based on two main ideas: (a) we use a new synthetic dataset with strong shadow effects with similar constraints to the SID dataset; (b) we define a deep architecture trained on the mentioned dataset to estimate the direction and color of the scene light source. Apart from showing good performance on synthetic images, we additionally propose a preliminary procedure to obtain light positions of the Multi-Illumination dataset, and, in this way, we also prove that our trained model achieves good performance when it is applied to real scenes.
Address Virtual; September 2020
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 (up) LIM
Notes CIC; 600.118; 600.140; Approved no
Call Number Admin @ si @ SBV2020 Serial 3460
Permanent link to this record
 
 
Author David Vazquez; David Geronimo; Antonio Lopez
Title The effect of the distance in pedestrian detection Type Report
Year 2009 Publication CVC Technical Report Abbreviated Journal
Volume 149 Issue Pages
Keywords Pedestrian Detection
Abstract Pedestrian accidents are one of the leading preventable causes of death. In order to reduce the number of accidents, in the last decade the pedestrian protection systems have been introduced, a special type of advanced driver assistance systems, in witch an on-board camera explores the road ahead for possible collisions with pedestrians in order to warn the driver or perform braking actions. As a result of the variability of the appearance, pose and size, pedestrian detection is a very challenging task. So many techniques, models and features have been proposed to solve the problem. As the appearance of pedestrians varies signi cantly as a function of distance, a system based on multiple classi ers specialized on diferent depths is likely to improve the overall performance with respect to a typical system based on a general detector. Accordingly, the main aim of this work is to explore the e ect of the distance in pedestrian detection. We have evaluated three pedestrian detectors (HOG, HAAR and EOH) in two di erent databases (INRIA and Daimler09) for two di erent sizes (small and big). By a extensive set of experiments we answer to questions like which datasets and evaluation methods are the most adequate, which is the best method for each size of the pedestrians and why or how do the method optimum parameters vary with respect to the distance
Address
Corporate Author Thesis Master's 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 (up) M.Sc.
Notes ADAS Approved no
Call Number ADAS @ adas @ VGL2009 Serial 1669
Permanent link to this record
 
 
Author Javier Rodenas; Bhalaji Nagarajan; Marc Bolaños; Petia Radeva
Title Learning Multi-Subset of Classes for Fine-Grained Food Recognition Type Conference Article
Year 2022 Publication 7th International Workshop on Multimedia Assisted Dietary Management Abbreviated Journal
Volume Issue Pages 17–26
Keywords
Abstract Food image recognition is a complex computer vision task, because of the large number of fine-grained food classes. Fine-grained recognition tasks focus on learning subtle discriminative details to distinguish similar classes. In this paper, we introduce a new method to improve the classification of classes that are more difficult to discriminate based on Multi-Subsets learning. Using a pre-trained network, we organize classes in multiple subsets using a clustering technique. Later, we embed these subsets in a multi-head model structure. This structure has three distinguishable parts. First, we use several shared blocks to learn the generalized representation of the data. Second, we use multiple specialized blocks focusing on specific subsets that are difficult to distinguish. Lastly, we use a fully connected layer to weight the different subsets in an end-to-end manner by combining the neuron outputs. We validated our proposed method using two recent state-of-the-art vision transformers on three public food recognition datasets. Our method was successful in learning the confused classes better and we outperformed the state-of-the-art on the three datasets.
Address Lisboa; Portugal; October 2022
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 (up) MADiMa
Notes MILAB Approved no
Call Number Admin @ si @ RNB2022 Serial 3797
Permanent link to this record
 
 
Author Jose A. Garcia; David Masip; Valerio Sbragaglia; Jacopo Aguzzi
Title Using ORB, BoW and SVM to identificate and track tagged Norway lobster Nephrops Norvegicus (L.) Type Conference Article
Year 2016 Publication 3rd International Conference on Maritime Technology and Engineering Abbreviated Journal
Volume Issue Pages
Keywords
Abstract Sustainable capture policies of many species strongly depend on the understanding of their social behaviour. Nevertheless, the analysis of emergent behaviour in marine species poses several challenges. Usually animals are captured and observed in tanks, and their behaviour is inferred from their dynamics and interactions. Therefore, researchers must deal with thousands of hours of video data. Without loss of generality, this paper proposes a computer
vision approach to identify and track specific species, the Norway lobster, Nephrops norvegicus. We propose an identification scheme were animals are marked using black and white tags with a geometric shape in the center (holed
triangle, filled triangle, holed circle and filled circle). Using a massive labelled dataset; we extract local features based on the ORB descriptor. These features are a posteriori clustered, and we construct a Bag of Visual Words feature vector per animal. This approximation yields us invariance to rotation
and translation. A SVM classifier achieves generalization results above 99%. In a second contribution, we will make the code and training data publically available.
Address Lisboa; Portugal; July 2016
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 (up) MARTECH
Notes OR;MV; Approved no
Call Number Admin @ si @ GMS2016b Serial 2817
Permanent link to this record
 
 
Author Sergio Escalera; Oriol Pujol; Petia Radeva
Title Recoding Error-Correcting Output Codes Type Conference Article
Year 2009 Publication 8th International Workshop of Multiple Classifier Systems Abbreviated Journal
Volume 5519 Issue Pages 11–21
Keywords
Abstract One of the most widely applied techniques to deal with multi- class categorization problems is the pairwise voting procedure. Recently, this classical approach has been embedded in the Error-Correcting Output Codes framework (ECOC). This framework is based on a coding step, where a set of binary problems are learnt and coded in a matrix, and a decoding step, where a new sample is tested and classified according to a comparison with the positions of the coded matrix. In this paper, we present a novel approach to redefine without retraining, in a problem-dependent way, the one-versus-one coding matrix so that the new coded information increases the generalization capability of the system. Moreover, the final classification can be tuned with the inclusion of a weighting matrix in the decoding step. The approach has been validated over several UCI Machine Learning repository data sets and two real multi-class problems: traffic sign and face categorization. The results show that performance improvements are obtained when comparing the new approach to one of the best ECOC designs (one-versus-one). Furthermore, the novel methodology obtains at least the same performance than the one-versus-one ECOC design.
Address Reykjavik (Iceland)
Corporate Author Thesis
Publisher Springer Berlin Heidelberg Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 0302-9743 ISBN 978-3-642-02325-5 Medium
Area Expedition Conference (up) MCS
Notes MILAB;HuPBA Approved no
Call Number BCNPCL @ bcnpcl @ EPR2009d Serial 1190
Permanent link to this record
 
 
Author Oriol Pujol; Eloi Puertas; Carlo Gatta
Title Multi-scale Stacked Sequential Learning Type Conference Article
Year 2009 Publication 8th International Workshop of Multiple Classifier Systems Abbreviated Journal
Volume 5519 Issue Pages 262–271
Keywords
Abstract One of the most widely used assumptions in supervised learning is that data is independent and identically distributed. This assumption does not hold true in many real cases. Sequential learning is the discipline of machine learning that deals with dependent data such that neighboring examples exhibit some kind of relationship. In the literature, there are different approaches that try to capture and exploit this correlation, by means of different methodologies. In this paper we focus on meta-learning strategies and, in particular, the stacked sequential learning approach. The main contribution of this work is two-fold: first, we generalize the stacked sequential learning. This generalization reflects the key role of neighboring interactions modeling. Second, we propose an effective and efficient way of capturing and exploiting sequential correlations that takes into account long-range interactions by means of a multi-scale pyramidal decomposition of the predicted labels. Additionally, this new method subsumes the standard stacked sequential learning approach. We tested the proposed method on two different classification tasks: text lines classification in a FAQ data set and image classification. Results on these tasks clearly show that our approach outperforms the standard stacked sequential learning. Moreover, we show that the proposed method allows to control the trade-off between the detail and the desired range of the interactions.
Address Reykjavik, Iceland
Corporate Author Thesis
Publisher Springer Berlin Heidelberg Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 0302-9743 ISBN 978-3-642-02325-5 Medium
Area Expedition Conference (up) MCS
Notes MILAB;HuPBA Approved no
Call Number BCNPCL @ bcnpcl @ PPG2009 Serial 1260
Permanent link to this record
 
 
Author Santiago Segui; Laura Igual; Jordi Vitria
Title Weighted Bagging for Graph based One-Class Classifiers Type Conference Article
Year 2010 Publication 9th International Workshop on Multiple Classifier Systems Abbreviated Journal
Volume 5997 Issue Pages 1-10
Keywords
Abstract Most conventional learning algorithms require both positive and negative training data for achieving accurate classification results. However, the problem of learning classifiers from only positive data arises in many applications where negative data are too costly, difficult to obtain, or not available at all. Minimum Spanning Tree Class Descriptor (MSTCD) was presented as a method that achieves better accuracies than other one-class classifiers in high dimensional data. However, the presence of outliers in the target class severely harms the performance of this classifier. In this paper we propose two bagging strategies for MSTCD that reduce the influence of outliers in training data. We show the improved performance on both real and artificially contaminated data.
Address Cairo, Egypt
Corporate Author Thesis
Publisher Springer Berlin Heidelberg Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title LNCS
Series Volume Series Issue Edition
ISSN 0302-9743 ISBN 978-3-642-12126-5 Medium
Area Expedition Conference (up) MCS
Notes MILAB;OR;MV Approved no
Call Number BCNPCL @ bcnpcl @ SIV2010 Serial 1284
Permanent link to this record
 
 
Author Jaume Gibert; Ernest Valveny; Oriol Ramos Terrades; Horst Bunke
Title Multiple Classifiers for Graph of Words Embedding Type Conference Article
Year 2011 Publication 10th International Conference on Multiple Classifier Systems Abbreviated Journal
Volume 6713 Issue Pages 36-45
Keywords
Abstract During the last years, there has been an increasing interest in applying the multiple classifier framework to the domain of structural pattern recognition. Constructing base classifiers when the input patterns are graph based representations is not an easy problem. In this work, we make use of the graph embedding methodology in order to construct different feature vector representations for graphs. The graph of words embedding assigns a feature vector to every graph by counting unary and binary relations between node representatives and combining these pieces of information into a single vector. Selecting different node representatives leads to different vectorial representations and therefore to different base classifiers that can be combined. We experimentally show how this methodology significantly improves the classification of graphs with respect to single base classifiers.
Address Napoles, Italy
Corporate Author Thesis
Publisher Place of Publication Editor Carlo Sansone; Josef Kittler; Fabio Roli
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title LNCS
Series Volume Series Issue Edition
ISSN ISBN 978-3-642-21556-8 Medium
Area Expedition Conference (up) MCS
Notes DAG Approved no
Call Number Admin @ si @GVR2011 Serial 1745
Permanent link to this record
 
 
Author Pierluigi Casale; Oriol Pujol; Petia Radeva
Title Approximate Convex Hulls Family for One-Class Cassification Type Conference Article
Year 2011 Publication 10th International Workshop on Multiple Classifier Systems Abbreviated Journal
Volume 6713 Issue Pages 106-115
Keywords
Abstract In this work, a new method for one-class classification based on the Convex Hull geometric structure is proposed. The new method creates a family of convex hulls able to fit the geometrical shape of the training points. The increased computational cost due to the creation of the convex hull in multiple dimensions is circumvented using random projections. This provides an approximation of the original structure with multiple bi-dimensional views. In the projection planes, a mechanism for noisy points rejection has also been elaborated and evaluated. Results show that the approach performs considerably well with respect to the state the art in one-class classification.
Address Napoli, Italy
Corporate Author Thesis
Publisher Springer Berlin Heidelberg Place of Publication Editor Carlo Sansone; Josef Kittler; Fabio Roli
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title LNCS
Series Volume Series Issue Edition
ISSN 0302-9743 ISBN 978-3-642-21556-8 Medium
Area Expedition Conference (up) MCS
Notes MILAB;HuPBA Approved no
Call Number Admin @ si @ CPR2011b Serial 1761
Permanent link to this record
 
 
Author Miguel Angel Bautista; Oriol Pujol; Xavier Baro; Sergio Escalera
Title Introducing the Separability Matrix for Error Correcting Output Codes Coding Type Conference Article
Year 2011 Publication 10th International conference on Multiple Classifier Systems Abbreviated Journal
Volume 6713 Issue Pages 227-236
Keywords
Abstract Error Correcting Output Codes (ECOC) have demonstrate to be a powerful tool for treating multi-class problems. Nevertheless, predefined ECOC designs may not benefit from Error-correcting principles for particular multi-class data. In this paper, we introduce the Separability matrix as a tool to study and enhance designs for ECOC coding. In addition, a novel problem-dependent coding design based on the Separability matrix is tested over a wide set of challenging multi-class problems, obtaining very satisfactory results.
Address Napoles, Italy
Corporate Author Thesis
Publisher Springer-Verlag Berlin Heidelberg Place of Publication Editor Carlo Sansone; Josef Kittler; Fabio Roli
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title LNCS
Series Volume Series Issue Edition
ISSN ISBN 978-3-642-21556-8 Medium
Area Expedition Conference (up) MCS
Notes MILAB; OR;HuPBA;MV Approved no
Call Number Admin @ si @ BPB2011a Serial 1771
Permanent link to this record