Home << 1 2 3 4 5 6 7 8 9 10 >> [11–12]
List View
 | 
Citations
 | 
Details
   web
Records
Author Jiaolong Xu; David Vazquez; Sebastian Ramos; Antonio Lopez; Daniel Ponsa
Title Adapting a Pedestrian Detector by Boosting LDA Exemplar Classifiers Type Conference Article
Year 2013 Publication CVPR Workshop on Ground Truth – What is a good dataset? Abbreviated Journal
Volume Issue Pages (down) 688 - 693
Keywords Pedestrian Detection; Domain Adaptation
Abstract Training vision-based pedestrian detectors using synthetic datasets (virtual world) is a useful technique to collect automatically the training examples with their pixel-wise ground truth. However, as it is often the case, these detectors must operate in real-world images, experiencing a significant drop of their performance. In fact, this effect also occurs among different real-world datasets, i.e. detectors' accuracy drops when the training data (source domain) and the application scenario (target domain) have inherent differences. Therefore, in order to avoid this problem, it is required to adapt the detector trained with synthetic data to operate in the real-world scenario. In this paper, we propose a domain adaptation approach based on boosting LDA exemplar classifiers from both virtual and real worlds. We evaluate our proposal on multiple real-world pedestrian detection datasets. The results show that our method can efficiently adapt the exemplar classifiers from virtual to real world, avoiding drops in average precision over the 15%.
Address Portland; oregon; June 2013
Corporate Author Thesis
Publisher Place of Publication Editor
Language English Summary Language English Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference CVPRW
Notes ADAS; 600.054; 600.057; 601.217 Approved yes
Call Number XVR2013; ADAS @ adas @ xvr2013a Serial 2220
Permanent link to this record
 
 
Author Patricia Marquez; Debora Gil; Aura Hernandez-Sabate
Title Evaluation of the Capabilities of Confidence Measures for Assessing Optical Flow Quality Type Conference Article
Year 2013 Publication ICCV Workshop on Computer Vision in Vehicle Technology: From Earth to Mars Abbreviated Journal
Volume Issue Pages (down) 624-631
Keywords
Abstract Assessing Optical Flow (OF) quality is essential for its further use in reliable decision support systems. The absence of ground truth in such situations leads to the computation of OF Confidence Measures (CM) obtained from either input or output data. A fair comparison across the capabilities of the different CM for bounding OF error is required in order to choose the best OF-CM pair for discarding points where OF computation is not reliable. This paper presents a statistical probabilistic framework for assessing the quality of a given CM. Our quality measure is given in terms of the percentage of pixels whose OF error bound can not be determined by CM values. We also provide statistical tools for the computation of CM values that ensures a given accuracy of the flow field.
Address Sydney; Australia; December 2013
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 CVTT:E2M
Notes IAM; ADAS; 600.044; 600.057; 601.145 Approved no
Call Number Admin @ si @ MGH2013b Serial 2351
Permanent link to this record
 
 
Author Albert Gordo; Marçal Rusiñol; Dimosthenis Karatzas; Andrew Bagdanov
Title Document Classification and Page Stream Segmentation for Digital Mailroom Applications Type Conference Article
Year 2013 Publication 12th International Conference on Document Analysis and Recognition Abbreviated Journal
Volume Issue Pages (down) 621-625
Keywords
Abstract In this paper we present a method for the segmentation of continuous page streams into multipage documents and the simultaneous classification of the resulting documents. We first present an approach to combine the multiple pages of a document into a single feature vector that represents the whole document. Despite its simplicity and low computational cost, the proposed representation yields results comparable to more complex methods in multipage document classification tasks. We then exploit this representation in the context of page stream segmentation. The most plausible segmentation of a page stream into a sequence of multipage documents is obtained by optimizing a statistical model that represents the probability of each segmented multipage document belonging to a particular class. Experimental results are reported on a large sample of real administrative multipage documents.
Address Washington; USA; August 2013
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 1520-5363 ISBN Medium
Area Expedition Conference ICDAR
Notes DAG; 600.056; 602.101 Approved no
Call Number Admin @ si @ GRK2013c Serial 2345
Permanent link to this record
 
 
Author Jose Manuel Alvarez; Theo Gevers; Antonio Lopez
Title Evaluating Color Representation for Online Road Detection Type Conference Article
Year 2013 Publication ICCV Workshop on Computer Vision in Vehicle Technology: From Earth to Mars Abbreviated Journal
Volume Issue Pages (down) 594-595
Keywords
Abstract Detecting traversable road areas ahead a moving vehicle is a key process for modern autonomous driving systems. Most existing algorithms use color to classify pixels as road or background. These algorithms reduce the effect of lighting variations and weather conditions by exploiting the discriminant/invariant properties of different color representations. However, up to date, no comparison between these representations have been conducted. Therefore, in this paper, we perform an evaluation of existing color representations for road detection. More specifically, we focus on color planes derived from RGB data and their most com-
mon combinations. The evaluation is done on a set of 7000 road images acquired
using an on-board camera in different real-driving situations.
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 CVVT:E2M
Notes ADAS;ISE Approved no
Call Number Admin @ si @ AGL2013 Serial 2794
Permanent link to this record
 
 
Author Francesco Ciompi; Rui Hua; Simone Balocco; Marina Alberti; Oriol Pujol; Carles Caus; J. Mauri; Petia Radeva
Title Learning to Detect Stent Struts in Intravascular Ultrasound Type Conference Article
Year 2013 Publication 6th Iberian Conference on Pattern Recognition and Image Analysis Abbreviated Journal
Volume 7887 Issue Pages (down) 575-583
Keywords
Abstract In this paper we tackle the automatic detection of struts elements (metallic braces of a stent device) in Intravascular Ultrasound (IVUS) sequences. The proposed method is based on context-aware classification of IVUS images, where we use Multi-Class Multi-Scale Stacked Sequential Learning (M2SSL). Additionally, we introduce a novel technique to reduce the amount of required contextual features. The comparison with binary and multi-class learning is also performed, using a dataset of IVUS images with struts manually annotated by an expert. The best performing configuration reaches a F-measure F = 63.97% .
Address Madeira; Portugal; June 2013
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 978-3-642-38627-5 Medium
Area Expedition Conference IbPRIA
Notes MILAB; HuPBA; 605.203; 600.046 Approved no
Call Number Admin @ si @ CHB2013 Serial 2349
Permanent link to this record
 
 
Author David Roche; Debora Gil; Jesus Giraldo
Title Detecting loss of diversity for an efficient termination of EAs Type Conference Article
Year 2013 Publication 15th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing Abbreviated Journal
Volume Issue Pages (down) 561 - 566
Keywords EA termination; EA population diversity; EA steady state
Abstract Termination of Evolutionary Algorithms (EA) at its steady state so that useless iterations are not performed is a main point for its efficient application to black-box problems. Many EA algorithms evolve while there is still diversity in their population and, thus, they could be terminated by analyzing the behavior some measures of EA population diversity. This paper presents a numeric approximation to steady states that can be used to detect the moment EA population has lost its diversity for EA termination. Our condition has been applied to 3 EA paradigms based on diversity and a selection of functions
covering the properties most relevant for EA convergence.
Experiments show that our condition works regardless of the search space dimension and function landscape.
Address Timisoara; Rumania;
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 978-1-4799-3035-7 Medium
Area Expedition Conference SYNASC
Notes IAM; 600.044; 600.060; 605.203 Approved no
Call Number Admin @ si @ RGG2013c Serial 2299
Permanent link to this record
 
 
Author Muhammad Muzzamil Luqman; Jean-Yves Ramel; Josep Llados; Thierry Brouard
Title Fuzzy Multilevel Graph Embedding Type Journal Article
Year 2013 Publication Pattern Recognition Abbreviated Journal PR
Volume 46 Issue 2 Pages (down) 551-565
Keywords Pattern recognition; Graphics recognition; Graph clustering; Graph classification; Explicit graph embedding; Fuzzy logic
Abstract Structural pattern recognition approaches offer the most expressive, convenient, powerful but computational expensive representations of underlying relational information. To benefit from mature, less expensive and efficient state-of-the-art machine learning models of statistical pattern recognition they must be mapped to a low-dimensional vector space. Our method of explicit graph embedding bridges the gap between structural and statistical pattern recognition. We extract the topological, structural and attribute information from a graph and encode numeric details by fuzzy histograms and symbolic details by crisp histograms. The histograms are concatenated to achieve a simple and straightforward embedding of graph into a low-dimensional numeric feature vector. Experimentation on standard public graph datasets shows that our method outperforms the state-of-the-art methods of graph embedding for richly attributed graphs.
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 0031-3203 ISBN Medium
Area Expedition Conference
Notes DAG; 600.042; 600.045; 605.203 Approved no
Call Number Admin @ si @ LRL2013a Serial 2270
Permanent link to this record
 
 
Author David Aldavert; Marçal Rusiñol; Ricardo Toledo; Josep Llados
Title Integrating Visual and Textual Cues for Query-by-String Word Spotting Type Conference Article
Year 2013 Publication 12th International Conference on Document Analysis and Recognition Abbreviated Journal
Volume Issue Pages (down) 511 - 515
Keywords
Abstract In this paper, we present a word spotting framework that follows the query-by-string paradigm where word images are represented both by textual and visual representations. The textual representation is formulated in terms of character $n$-grams while the visual one is based on the bag-of-visual-words scheme. These two representations are merged together and projected to a sub-vector space. This transform allows to, given a textual query, retrieve word instances that were only represented by the visual modality. Moreover, this statistical representation can be used together with state-of-the-art indexation structures in order to deal with large-scale scenarios. The proposed method is evaluated using a collection of historical documents outperforming state-of-the-art performances.
Address Washington; USA; August 2013
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 1520-5363 ISBN Medium
Area Expedition Conference ICDAR
Notes DAG; ADAS; 600.045; 600.055; 600.061 Approved no
Call Number Admin @ si @ ART2013 Serial 2224
Permanent link to this record
 
 
Author Andreas Fischer; Volkmar Frinken; Horst Bunke; Ching Y. Suen
Title Improving HMM-Based Keyword Spotting with Character Language Models Type Conference Article
Year 2013 Publication 12th International Conference on Document Analysis and Recognition Abbreviated Journal
Volume Issue Pages (down) 506-510
Keywords
Abstract Facing high error rates and slow recognition speed for full text transcription of unconstrained handwriting images, keyword spotting is a promising alternative to locate specific search terms within scanned document images. We have previously proposed a learning-based method for keyword spotting using character hidden Markov models that showed a high performance when compared with traditional template image matching. In the lexicon-free approach pursued, only the text appearance was taken into account for recognition. In this paper, we integrate character n-gram language models into the spotting system in order to provide an additional language context. On the modern IAM database as well as the historical George Washington database, we demonstrate that character language models significantly improve the spotting performance.
Address Washington; USA; August 2013
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 1520-5363 ISBN Medium
Area Expedition Conference ICDAR
Notes DAG; 600.045; 605.203 Approved no
Call Number Admin @ si @ FFB2013 Serial 2295
Permanent link to this record
 
 
Author Victor Ponce; Sergio Escalera; Xavier Baro
Title Multi-modal Social Signal Analysis for Predicting Agreement in Conversation Settings Type Conference Article
Year 2013 Publication 15th ACM International Conference on Multimodal Interaction Abbreviated Journal
Volume Issue Pages (down) 495-502
Keywords
Abstract In this paper we present a non-invasive ambient intelligence framework for the analysis of non-verbal communication applied to conversational settings. In particular, we apply feature extraction techniques to multi-modal audio-RGB-depth data. We compute a set of behavioral indicators that define communicative cues coming from the fields of psychology and observational methodology. We test our methodology over data captured in victim-offender mediation scenarios. Using different state-of-the-art classification approaches, our system achieve upon 75% of recognition predicting agreement among the parts involved in the conversations, using as ground truth the experts opinions.
Address Sidney; Australia; December 2013
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 978-1-4503-2129-7 Medium
Area Expedition Conference ICMI
Notes HuPBA;MV Approved no
Call Number Admin @ si @ PEB2013 Serial 2488
Permanent link to this record
 
 
Author Naveen Onkarappa; Angel Sappa
Title Laplacian Derivative based Regularization for Optical Flow Estimation in Driving Scenario Type Conference Article
Year 2013 Publication 15th International Conference on Computer Analysis of Images and Patterns Abbreviated Journal
Volume 8048 Issue Pages (down) 483-490
Keywords Optical flow; regularization; Driver Assistance Systems; Performance Evaluation
Abstract Existing state of the art optical flow approaches, which are evaluated on standard datasets such as Middlebury, not necessarily have a similar performance when evaluated on driving scenarios. This drop on performance is due to several challenges arising on real scenarios during driving. Towards this direction, in this paper, we propose a modification to the regularization term in a variational optical flow formulation, that notably improves the results, specially in driving scenarios. The proposed modification consists on using the Laplacian derivatives of flow components in the regularization term instead of gradients of flow components. We show the improvements in results on a standard real image sequences dataset (KITTI).
Address York; UK; August 2013
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 978-3-642-40245-6 Medium
Area Expedition Conference CAIP
Notes ADAS; 600.055; 601.215 Approved no
Call Number Admin @ si @ OnS2013b Serial 2244
Permanent link to this record
 
 
Author Lluis Gomez; Dimosthenis Karatzas
Title Multi-script Text Extraction from Natural Scenes Type Conference Article
Year 2013 Publication 12th International Conference on Document Analysis and Recognition Abbreviated Journal
Volume Issue Pages (down) 467-471
Keywords
Abstract Scene text extraction methodologies are usually based in classification of individual regions or patches, using a priori knowledge for a given script or language. Human perception of text, on the other hand, is based on perceptual organisation through which text emerges as a perceptually significant group of atomic objects. Therefore humans are able to detect text even in languages and scripts never seen before. In this paper, we argue that the text extraction problem could be posed as the detection of meaningful groups of regions. We present a method built around a perceptual organisation framework that exploits collaboration of proximity and similarity laws to create text-group hypotheses. Experiments demonstrate that our algorithm is competitive with state of the art approaches on a standard dataset covering text in variable orientations and two languages.
Address Washington; USA; August 2013
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 1520-5363 ISBN Medium
Area Expedition Conference ICDAR
Notes DAG; 600.056; 601.158; 601.197 Approved no
Call Number Admin @ si @ GoK2013 Serial 2310
Permanent link to this record
 
 
Author Fadi Dornaika; Abdelmalik Moujahid; Bogdan Raducanu
Title Facial expression recognition using tracked facial actions: Classifier performance analysis Type Journal Article
Year 2013 Publication Engineering Applications of Artificial Intelligence Abbreviated Journal EAAI
Volume 26 Issue 1 Pages (down) 467-477
Keywords Visual face tracking; 3D deformable models; Facial actions; Dynamic facial expression recognition; Human–computer interaction
Abstract In this paper, we address the analysis and recognition of facial expressions in continuous videos. More precisely, we study classifiers performance that exploit head pose independent temporal facial action parameters. These are provided by an appearance-based 3D face tracker that simultaneously provides the 3D head pose and facial actions. The use of such tracker makes the recognition pose- and texture-independent. Two different schemes are studied. The first scheme adopts a dynamic time warping technique for recognizing expressions where training data are given by temporal signatures associated with different universal facial expressions. The second scheme models temporal signatures associated with facial actions with fixed length feature vectors (observations), and uses some machine learning algorithms in order to recognize the displayed expression. Experiments quantified the performance of different schemes. These were carried out on CMU video sequences and home-made video sequences. The results show that the use of dimension reduction techniques on the extracted time series can improve the classification performance. Moreover, these experiments show that the best recognition rate can be above 90%.
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 OR; 600.046;MV Approved no
Call Number Admin @ si @ DMR2013 Serial 2185
Permanent link to this record
 
 
Author Jiaolong Xu; David Vazquez; Antonio Lopez; Javier Marin; Daniel Ponsa
Title Learning a Multiview Part-based Model in Virtual World for Pedestrian Detection Type Conference Article
Year 2013 Publication IEEE Intelligent Vehicles Symposium Abbreviated Journal
Volume Issue Pages (down) 467 - 472
Keywords Pedestrian Detection; Virtual World; Part based
Abstract State-of-the-art deformable part-based models based on latent SVM have shown excellent results on human detection. In this paper, we propose to train a multiview deformable part-based model with automatically generated part examples from virtual-world data. The method is efficient as: (i) the part detectors are trained with precisely extracted virtual examples, thus no latent learning is needed, (ii) the multiview pedestrian detector enhances the performance of the pedestrian root model, (iii) a top-down approach is used for part detection which reduces the searching space. We evaluate our model on Daimler and Karlsruhe Pedestrian Benchmarks with publicly available Caltech pedestrian detection evaluation framework and the result outperforms the state-of-the-art latent SVM V4.0, on both average miss rate and speed (our detector is ten times faster).
Address Gold Coast; Australia; June 2013
Corporate Author Thesis
Publisher IEEE Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 1931-0587 ISBN 978-1-4673-2754-1 Medium
Area Expedition Conference IV
Notes ADAS; 600.054; 600.057 Approved no
Call Number XVL2013; ADAS @ adas @ xvl2013a Serial 2214
Permanent link to this record
 
 
Author Adriana Romero; Carlo Gatta
Title Do We Really Need All These Neurons? Type Conference Article
Year 2013 Publication 6th Iberian Conference on Pattern Recognition and Image Analysis Abbreviated Journal
Volume 7887 Issue Pages (down) 460--467
Keywords Retricted Boltzmann Machine; hidden units; unsupervised learning; classification
Abstract Restricted Boltzmann Machines (RBMs) are generative neural networks that have received much attention recently. In particular, choosing the appropriate number of hidden units is important as it might hinder their representative power. According to the literature, RBM require numerous hidden units to approximate any distribution properly. In this paper, we present an experiment to determine whether such amount of hidden units is required in a classification context. We then propose an incremental algorithm that trains RBM reusing the previously trained parameters using a trade-off measure to determine the appropriate number of hidden units. Results on the MNIST and OCR letters databases show that using a number of hidden units, which is one order of magnitude smaller than the literature estimate, suffices to achieve similar performance. Moreover, the proposed algorithm allows to estimate the required number of hidden units without the need of training many RBM from scratch.
Address Madeira; Portugal; June 2013
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 978-3-642-38627-5 Medium
Area Expedition Conference IbPRIA
Notes MILAB; 600.046 Approved no
Call Number Admin @ si @ RoG2013 Serial 2311
Permanent link to this record