Home | [191–200] << 201 202 203 204 205 206 207 208 209 210 >> [211–220] |
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 | 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 | 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 | 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 | 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 | 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 | 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 signicantly as a function of distance, a system based on multiple classiers 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 eect of the distance in pedestrian detection. We have evaluated three pedestrian detectors (HOG, HAAR and EOH) in two dierent databases (INRIA and Daimler09) for two dierent 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 | 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 | 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 | 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 | 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 | 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 | 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 | 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 | 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 | MCS | ||
Notes | MILAB; OR;HuPBA;MV | Approved | no | ||
Call Number | Admin @ si @ BPB2011a | Serial | 1771 | ||
Permanent link to this record |