Home << 1 2 3 4 5 6 7 8 9 10 >> [11–12]
List View
 | 
Citations
 | 
Details
   web
Records
Author Jiaolong Xu; Sebastian Ramos; Xu Hu; David Vazquez; Antonio Lopez
Title Multi-task Bilinear Classifiers for Visual Domain Adaptation Type Conference Article
Year 2013 Publication (up) Advances in Neural Information Processing Systems Workshop Abbreviated Journal
Volume Issue Pages
Keywords Domain Adaptation; Pedestrian Detection; ADAS
Abstract We propose a method that aims to lessen the significant accuracy degradation
that a discriminative classifier can suffer when it is trained in a specific domain (source domain) and applied in a different one (target domain). The principal reason for this degradation is the discrepancies in the distribution of the features that feed the classifier in different domains. Therefore, we propose a domain adaptation method that maps the features from the different domains into a common subspace and learns a discriminative domain-invariant classifier within it. Our algorithm combines bilinear classifiers and multi-task learning for domain adaptation.
The bilinear classifier encodes the feature transformation and classification
parameters by a matrix decomposition. In this way, specific feature transformations for multiple domains and a shared classifier are jointly learned in a multi-task learning framework. Focusing on domain adaptation for visual object detection, we apply this method to the state-of-the-art deformable part-based model for cross domain pedestrian detection. Experimental results show that our method significantly avoids the domain drift and improves the accuracy when compared to several baselines.
Address Lake Tahoe; Nevada; USA; 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 NIPSW
Notes ADAS; 600.054; 600.057; 601.217;ISE Approved no
Call Number ADAS @ adas @ XRH2013 Serial 2340
Permanent link to this record
 
 
Author Jaume Amores
Title Multiple Instance Classification: review, taxonomy and comparative study Type Journal Article
Year 2013 Publication (up) Artificial Intelligence Abbreviated Journal AI
Volume 201 Issue Pages 81-105
Keywords Multi-instance learning; Codebook; Bag-of-Words
Abstract Multiple Instance Learning (MIL) has become an important topic in the pattern recognition community, and many solutions to this problemhave been proposed until now. Despite this fact, there is a lack of comparative studies that shed light into the characteristics and behavior of the different methods. In this work we provide such an analysis focused on the classification task (i.e.,leaving out other learning tasks such as regression). In order to perform our study, we implemented
fourteen methods grouped into three different families. We analyze the performance of the approaches across a variety of well-known databases, and we also study their behavior in synthetic scenarios in order to highlight their characteristics. As a result of this analysis, we conclude that methods that extract global bag-level information show a clearly superior performance in general. In this sense, the analysis permits us to understand why some types of methods are more successful than others, and it permits us to establish guidelines in the design of new MIL
methods.
Address
Corporate Author Thesis
Publisher Elsevier Science Publishers Ltd. Essex, UK Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 0004-3702 ISBN Medium
Area Expedition Conference
Notes ADAS; 601.042; 600.057 Approved no
Call Number Admin @ si @ Amo2013 Serial 2273
Permanent link to this record
 
 
Author David Roche; Debora Gil; Jesus Giraldo
Title Mechanistic analysis of the function of agonists and allosteric modulators: Reconciling two-state and operational models Type Journal Article
Year 2013 Publication (up) British Journal of Pharmacology Abbreviated Journal BJP
Volume 169 Issue 6 Pages 1189-202
Keywords
Abstract Two-state and operational models of both agonism and allosterism are compared to identify and characterize common pharmacological parameters. To account for the receptor-dependent basal response, constitutive receptor activity is considered in the operational models. By arranging two-state models as the fraction of active receptors and operational models as the fractional response relative to the maximum effect of the system, a one-by-one correspondence between parameters is found. The comparative analysis allows a better understanding of complex allosteric interactions. In particular, the inclusion of constitutive receptor activity in the operational model of allosterism allows the characterization of modulators able to lower the basal response of the system; that is, allosteric modulators with negative intrinsic efficacy. Theoretical simulations and overall goodness of fit of the models to simulated data suggest that it is feasible to apply the models to experimental data and constitute one step forward in receptor theory formalism.
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 IAM; 600.044; 605.203 Approved no
Call Number IAM @ iam @ RGG2013b Serial 2195
Permanent link to this record
 
 
Author Kaida Xiao; Chenyang Fu; D.Mylonas; Dimosthenis Karatzas; S. Wuerger
Title Unique Hue Data for Colour Appearance Models. Part ii: Chromatic Adaptation Transform Type Journal Article
Year 2013 Publication (up) Color Research & Application Abbreviated Journal CRA
Volume 38 Issue 1 Pages 22-29
Keywords
Abstract Unique hue settings of 185 observers under three room-lighting conditions were used to evaluate the accuracy of full and mixed chromatic adaptation transform models of CIECAM02 in terms of unique hue reproduction. Perceptual hue shifts in CIECAM02 were evaluated for both models with no clear difference using the current Commission Internationale de l'Éclairage (CIE) recommendation for mixed chromatic adaptation ratio. Using our large dataset of unique hue data as a benchmark, an optimised parameter is proposed for chromatic adaptation under mixed illumination conditions that produces more accurate results in unique hue reproduction. © 2011 Wiley Periodicals, Inc. Col Res Appl, 2013
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 @ XFM2013 Serial 1822
Permanent link to this record
 
 
Author Bhaskar Chakraborty; Jordi Gonzalez; Xavier Roca
Title Large scale continuous visual event recognition using max-margin Hough transformation framework Type Journal Article
Year 2013 Publication (up) Computer Vision and Image Understanding Abbreviated Journal CVIU
Volume 117 Issue 10 Pages 1356–1368
Keywords
Abstract In this paper we propose a novel method for continuous visual event recognition (CVER) on a large scale video dataset using max-margin Hough transformation framework. Due to high scalability, diverse real environmental state and wide scene variability direct application of action recognition/detection methods such as spatio-temporal interest point (STIP)-local feature based technique, on the whole dataset is practically infeasible. To address this problem, we apply a motion region extraction technique which is based on motion segmentation and region clustering to identify possible candidate “event of interest” as a preprocessing step. On these candidate regions a STIP detector is applied and local motion features are computed. For activity representation we use generalized Hough transform framework where each feature point casts a weighted vote for possible activity class centre. A max-margin frame work is applied to learn the feature codebook weight. For activity detection, peaks in the Hough voting space are taken into account and initial event hypothesis is generated using the spatio-temporal information of the participating STIPs. For event recognition a verification Support Vector Machine is used. An extensive evaluation on benchmark large scale video surveillance dataset (VIRAT) and as well on a small scale benchmark dataset (MSR) shows that the proposed method is applicable on a wide range of continuous visual event recognition applications having extremely challenging conditions.
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 1077-3142 ISBN Medium
Area Expedition Conference
Notes ISE Approved no
Call Number Admin @ si @ CGR2013 Serial 2413
Permanent link to this record
 
 
Author Jorge Bernal; David Vazquez (eds)
Title Computer vision Trends and Challenges Type Book Whole
Year 2013 Publication (up) Computer vision Trends and Challenges Abbreviated Journal
Volume Issue Pages
Keywords CVCRD; Computer Vision
Abstract This book contains the papers presented at the Eighth CVC Workshop on Computer Vision Trends and Challenges (CVCR&D'2013). The workshop was held at the Computer Vision Center (Universitat Autònoma de Barcelona), the October 25th, 2013. The CVC workshops provide an excellent opportunity for young researchers and project engineers to share new ideas and knowledge about the progress of their work, and also, to discuss about challenges and future perspectives. In addition, the workshop is the welcome event for new people that recently have joined the institute.

The program of CVCR&D is organized in a single-track single-day workshop. It comprises several sessions dedicated to specific topics. For each session, a doctor working on the topic introduces the general research lines. The PhD students expose their specific research. A poster session will be held for open questions. Session topics cover the current research lines and development projects of the CVC: Medical Imaging, Medical Imaging, Color & Texture Analysis, Object Recognition, Image Sequence Evaluation, Advanced Driver Assistance Systems, Machine Vision, Document Analysis, Pattern Recognition and Applications. We want to thank all paper authors and Program Committee members. Their contribution shows that the CVC has a dynamic, active, and promising scientific community.

We hope you all enjoy this Eighth workshop and we are looking forward to meeting you and new people next year in the Ninth CVCR&D.
Address
Corporate Author Thesis
Publisher Place of Publication Editor Jorge Bernal; David Vazquez
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN 978-84-940902-2-6 Medium
Area Expedition Conference
Notes Approved no
Call Number ADAS @ adas @ BeV2013 Serial 2339
Permanent link to this record
 
 
Author Michal Drozdzal; Santiago Segui; Carolina Malagelada; Fernando Azpiroz; Petia Radeva
Title Adaptable image cuts for motility inspection using WCE Type Journal Article
Year 2013 Publication (up) Computerized Medical Imaging and Graphics Abbreviated Journal CMIG
Volume 37 Issue 1 Pages 72-80
Keywords
Abstract The Wireless Capsule Endoscopy (WCE) technology allows the visualization of the whole small intestine tract. Since the capsule is freely moving, mainly by the means of peristalsis, the data acquired during the study gives a lot of information about the intestinal motility. However, due to: (1) huge amount of frames, (2) complex intestinal scene appearance and (3) intestinal dynamics that make difficult the visualization of the small intestine physiological phenomena, the analysis of the WCE data requires computer-aided systems to speed up the analysis. In this paper, we propose an efficient algorithm for building a novel representation of the WCE video data, optimal for motility analysis and inspection. The algorithm transforms the 3D video data into 2D longitudinal view by choosing the most informative, from the intestinal motility point of view, part of each frame. This step maximizes the lumen visibility in its longitudinal extension. The task of finding “the best longitudinal view” has been defined as a cost function optimization problem which global minimum is obtained by using Dynamic Programming. Validation on both synthetic data and WCE data shows that the adaptive longitudinal view is a good alternative to the traditional motility analysis done by video analysis. The proposed novel data representation a new, holistic insight into the small intestine motility, allowing to easily define and analyze motility events that are difficult to spot by analyzing WCE video. Moreover, the visual inspection of small intestine motility is 4 times faster then by means of video skimming of the WCE.
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 MILAB; OR; 600.046; 605.203 Approved no
Call Number Admin @ si @ DSM2012 Serial 2151
Permanent link to this record
 
 
Author Miguel Reyes; Albert Clapes; Jose Ramirez; Juan R Revilla; Sergio Escalera
Title Automatic Digital Biometry Analysis based on Depth Maps Type Journal Article
Year 2013 Publication (up) Computers in Industry Abbreviated Journal COMPUTIND
Volume 64 Issue 9 Pages 1316-1325
Keywords Multi-modal data fusion; Depth maps; Posture analysis; Anthropometric data; Musculo-skeletal disorders; Gesture analysis
Abstract World Health Organization estimates that 80% of the world population is affected by back-related disorders during his life. Current practices to analyze musculo-skeletal disorders (MSDs) are expensive, subjective, and invasive. In this work, we propose a tool for static body posture analysis and dynamic range of movement estimation of the skeleton joints based on 3D anthropometric information from multi-modal data. Given a set of keypoints, RGB and depth data are aligned, depth surface is reconstructed, keypoints are matched, and accurate measurements about posture and spinal curvature are computed. Given a set of joints, range of movement measurements is also obtained. Moreover, gesture recognition based on joint movements is performed to look for the correctness in the development of physical exercises. The system shows high precision and reliable measurements, being useful for posture reeducation purposes to prevent MSDs, as well as tracking the posture evolution of patients in rehabilitation treatments.
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 HuPBA;MILAB Approved no
Call Number Admin @ si @ RCR2013 Serial 2252
Permanent link to this record
 
 
Author Joan Serrat; Felipe Lumbreras; Antonio Lopez
Title Cost estimation of custom hoses from STL files and CAD drawings Type Journal Article
Year 2013 Publication (up) Computers in Industry Abbreviated Journal COMPUTIND
Volume 64 Issue 3 Pages 299-309
Keywords On-line quotation; STL format; Regression; Gaussian process
Abstract We present a method for the cost estimation of custom hoses from CAD models. They can come in two formats, which are easy to generate: a STL file or the image of a CAD drawing showing several orthogonal projections. The challenges in either cases are, first, to obtain from them a high level 3D description of the shape, and second, to learn a regression function for the prediction of the manufacturing time, based on geometric features of the reconstructed shape. The chosen description is the 3D line along the medial axis of the tube and the diameter of the circular sections along it. In order to extract it from STL files, we have adapted RANSAC, a robust parametric fitting algorithm. As for CAD drawing images, we propose a new technique for 3D reconstruction from data entered on any number of orthogonal projections. The regression function is a Gaussian process, which does not constrain the function to adopt any specific form and is governed by just two parameters. We assess the accuracy of the manufacturing time estimation by k-fold cross validation on 171 STL file models for which the time is provided by an expert. The results show the feasibility of the method, whereby the relative error for 80% of the testing samples is below 15%.
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 ADAS; 600.057; 600.054; 605.203 Approved no
Call Number Admin @ si @ SLL2013; ADAS @ adas @ Serial 2161
Permanent link to this record
 
 
Author Ivet Rafegas
Title Exploring Low-Level Vision Models. Case Study: Saliency Prediction Type Report
Year 2013 Publication (up) CVC Technical Report Abbreviated Journal
Volume 175 Issue Pages
Keywords
Abstract
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
Notes CIC Approved no
Call Number Admin @ si @ Raf2013 Serial 2409
Permanent link to this record
 
 
Author Francesco Brughi
Title Artistic Heritage Motive Retrieval: an Explorative Study Type Report
Year 2013 Publication (up) CVC Technical Report Abbreviated Journal
Volume 176 Issue Pages
Keywords
Abstract
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
Notes IAM Approved no
Call Number Admin @ si @ Bru2013 Serial 2410
Permanent link to this record
 
 
Author David Vazquez; Jiaolong Xu; Sebastian Ramos; Antonio Lopez; Daniel Ponsa
Title Weakly Supervised Automatic Annotation of Pedestrian Bounding Boxes Type Conference Article
Year 2013 Publication (up) CVPR Workshop on Ground Truth – What is a good dataset? Abbreviated Journal
Volume Issue Pages 706 - 711
Keywords Pedestrian Detection; Domain Adaptation
Abstract Among the components of a pedestrian detector, its trained pedestrian classifier is crucial for achieving the desired performance. The initial task of the training process consists in collecting samples of pedestrians and background, which involves tiresome manual annotation of pedestrian bounding boxes (BBs). Thus, recent works have assessed the use of automatically collected samples from photo-realistic virtual worlds. However, learning from virtual-world samples and testing in real-world images may suffer the dataset shift problem. Accordingly, in this paper we assess an strategy to collect samples from the real world and retrain with them, thus avoiding the dataset shift, but in such a way that no BBs of real-world pedestrians have to be provided. In particular, we train a pedestrian classifier based on virtual-world samples (no human annotation required). Then, using such a classifier we collect pedestrian samples from real-world images by detection. After, a human oracle rejects the false detections efficiently (weak annotation). Finally, a new classifier is trained with the accepted detections. We show that this classifier is competitive with respect to the counterpart trained with samples collected by manually annotating hundreds of pedestrian BBs.
Address Portland; Oregon; June 2013
Corporate Author Thesis
Publisher IEEE 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 no
Call Number ADAS @ adas @ VXR2013a Serial 2219
Permanent link to this record
 
 
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 (up) CVPR Workshop on Ground Truth – What is a good dataset? Abbreviated Journal
Volume Issue Pages 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 David Roche; Debora Gil; Jesus Giraldo
Title Multiple active receptor conformation, agonist efficacy and maximum effect of the system: the conformation-based operational model of agonism, Type Journal Article
Year 2013 Publication (up) Drug Discovery Today Abbreviated Journal DDT
Volume 18 Issue 7-8 Pages 365-371
Keywords
Abstract The operational model of agonism assumes that the maximum effect a particular receptor system can achieve (the Em parameter) is fixed. Em estimates are above but close to the asymptotic maximum effects of endogenous agonists. The concept of Em is contradicted by superagonists and those positive allosteric modulators that significantly increase the maximum effect of endogenous agonists. An extension of the operational model is proposed that assumes that the Em parameter does not necessarily have a single value for a receptor system but has multiple values associated to multiple active receptor conformations. The model provides a mechanistic link between active receptor conformation and agonist efficacy, which can be useful for the analysis of agonist response under different receptor scenarios.
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 IAM; 600.057; 600.054 Approved no
Call Number IAM @ iam @ RGG2013a Serial 2190
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 (up) Engineering Applications of Artificial Intelligence Abbreviated Journal EAAI
Volume 26 Issue 1 Pages 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