|   | 
Details
   web
Records
Author Volkmar Frinken; Andreas Fischer; Horst Bunke; Alicia Fornes
Title Co-training for Handwritten Word Recognition Type Conference Article
Year 2011 Publication 11th International Conference on Document Analysis and Recognition Abbreviated Journal
Volume Issue Pages 314-318
Keywords
Abstract (up) To cope with the tremendous variations of writing styles encountered between different individuals, unconstrained automatic handwriting recognition systems need to be trained on large sets of labeled data. Traditionally, the training data has to be labeled manually, which is a laborious and costly process. Semi-supervised learning techniques offer methods to utilize unlabeled data, which can be obtained cheaply in large amounts in order, to reduce the need for labeled data. In this paper, we propose the use of Co-Training for improving the recognition accuracy of two weakly trained handwriting recognition systems. The first one is based on Recurrent Neural Networks while the second one is based on Hidden Markov Models. On the IAM off-line handwriting database we demonstrate a significant increase of the recognition accuracy can be achieved with Co-Training for single word recognition.
Address Beijing, China
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 ICDAR
Notes DAG Approved no
Call Number Admin @ si @ FFB2011 Serial 1789
Permanent link to this record
 

 
Author Petia Radeva; A.Amini; J.Huang; Enric Marti
Title Deformable B-Solids and Implicit Snakes for Localization and Tracking of SPAMM MRI-Data Type Conference Article
Year 1996 Publication Workshop on Mathematical Methods in Biomedical Image Analysis Abbreviated Journal
Volume Issue Pages 192-201
Keywords
Abstract (up) To date, MRI-SPAMM data from different image slices have been analyzed independently. In this paper, we propose an approach for 3D tag localization and tracking of SPAMM data by a novel deformable B-solid. The solid is defined in terms of a 3D tensor product B-spline. The isoparametric curves of the B-spline solid have special importance. These are termed implicit snakes as they deform under image forces from tag lines in different image slices. The localization and tracking of tag lines is performed under constraints of continuity and smoothness of the B-solid. The framework unifies the problems of localization, and displacement fitting and interpolation into the same procedure utilizing B-spline bases for interpolation. To track motion from boundaries and restrict image forces to the myocardium, a volumetric model is employed as a pair of coupled endocardial and epicardial B-spline surfaces. To recover deformations in the LV an energy-minimization problem is posed where both tag and ...
Address San Francisco CA
Corporate Author Thesis
Publisher IEEE Computer Society Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN 0-8186-7368-0 Medium
Area Expedition Conference MMBIA ’96
Notes MILAB;IAM; Approved no
Call Number IAM @ iam @ RAH1996 Serial 1630
Permanent link to this record
 

 
Author Petia Radeva; Amir Amini; Jintao Huang; Enric Marti
Title Deformable B-Solids: application for localization and tracking of MRI-SPAMM data Type Report
Year 1996 Publication CVC Technical Report Abbreviated Journal
Volume Issue 8 Pages
Keywords
Abstract (up) To date, MRI-SPAMM data from different image slices have been analyzed independently. In this paper, we propose an approach for 3D tag localization and tracking of SPAMM data by a novel deformable B-solid. The solid is defined in terms of a 3D tensor product B-spline. The isoparametric curves of the B-spline solid have special importance. These are termed implicit snakes as they deform under image forces from tag lines in different image slices. The localization and tracking of tag lines is performed under constraints of continuity and smoothness of the B-solid. The framework unifies the problems of localization, and displacement fitting and interpolation into the same procedure utilizing B-spline bases for interpolation. To track motion from boundaries and restrict image forces to the myocardium, a volumetric model is employed as a pair of coupled endocardial and epicardial B-spline surfaces. To recover deformations in the LV an energy-minimization problem is posed where both tag and ...
Address
Corporate Author Thesis
Publisher CVC (UAB) 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;IAM Approved no
Call Number IAM @ iam @ RHM1996 Serial 1631
Permanent link to this record
 

 
Author Jordi Roca
Title Constancy and inconstancy in categorical colour perception Type Book Whole
Year 2012 Publication PhD Thesis, Universitat Autonoma de Barcelona-CVC Abbreviated Journal
Volume Issue Pages
Keywords
Abstract (up) To recognise objects is perhaps the most important task an autonomous system, either biological or artificial needs to perform. In the context of human vision, this is partly achieved by recognizing the colour of surfaces despite changes in the wavelength distribution of the illumination, a property called colour constancy. Correct surface colour recognition may be adequately accomplished by colour category matching without the need to match colours precisely, therefore categorical colour constancy is likely to play an important role for object identification to be successful. The main aim of this work is to study the relationship between colour constancy and categorical colour perception. Previous studies of colour constancy have shown the influence of factors such the spatio-chromatic properties of the background, individual observer's performance, semantics, etc. However there is very little systematic study of these influences. To this end, we developed a new approach to colour constancy which includes both individual observers' categorical perception, the categorical structure of the background, and their interrelations resulting in a more comprehensive characterization of the phenomenon. In our study, we first developed a new method to analyse the categorical structure of 3D colour space, which allowed us to characterize individual categorical colour perception as well as quantify inter-individual variations in terms of shape and centroid location of 3D categorical regions. Second, we developed a new colour constancy paradigm, termed chromatic setting, which allows measuring the precise location of nine categorically-relevant points in colour space under immersive illumination. Additionally, we derived from these measurements a new colour constancy index which takes into account the magnitude and orientation of the chromatic shift, memory effects and the interrelations among colours and a model of colour naming tuned to each observer/adaptation state. Our results lead to the following conclusions: (1) There exists large inter-individual variations in the categorical structure of colour space, and thus colour naming ability varies significantly but this is not well predicted by low-level chromatic discrimination ability; (2) Analysis of the average colour naming space suggested the need for an additional three basic colour terms (turquoise, lilac and lime) for optimal colour communication; (3) Chromatic setting improved the precision of more complex linear colour constancy models and suggested that mechanisms other than cone gain might be best suited to explain colour constancy; (4) The categorical structure of colour space is broadly stable under illuminant changes for categorically balanced backgrounds; (5) Categorical inconstancy exists for categorically unbalanced backgrounds thus indicating that categorical information perceived in the initial stages of adaptation may constrain further categorical perception.
Address
Corporate Author Thesis Ph.D. thesis
Publisher Place of Publication Editor Maria Vanrell;C. Alejandro Parraga
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 @ Roc2012 Serial 2893
Permanent link to this record
 

 
Author Petia Radeva; Michal Drozdzal; Santiago Segui; Laura Igual; Carolina Malagelada; Fernando Azpiroz; Jordi Vitria
Title Active labeling: Application to wireless endoscopy analysis Type Conference Article
Year 2012 Publication High Performance Computing and Simulation, International Conference on Abbreviated Journal
Volume Issue Pages 174-181
Keywords
Abstract (up) Today, robust learners trained in a real supervised machine learning application should count with a rich collection of positive and negative examples. Although in many applications, it is not difficult to obtain huge amount of data, labeling those data can be a very expensive process, especially when dealing with data of high variability and complexity. A good example of such cases are data from medical imaging applications where annotating anomalies like tumors, polyps, atherosclerotic plaque or informative frames in wireless endoscopy need highly trained experts. Building a representative set of training data from medical videos (e.g. Wireless Capsule Endoscopy) means that thousands of frames to be labeled by an expert. It is quite normal that data in new videos come different and thus are not represented by the training set. In this paper, we review the main approaches on active learning and illustrate how active learning can help to reduce expert effort in constructing the training sets. We show that applying active learning criteria, the number of human interventions can be significantly reduced. The proposed system allows the annotation of informative/non-informative frames of Wireless Capsule Endoscopy video containing more than 30000 frames each one with less than 100 expert ”clicks”.
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 978-1-4673-2359-8 Medium
Area Expedition Conference HPCS
Notes MILAB; OR;MV Approved no
Call Number Admin @ si @ RDS2012 Serial 2152
Permanent link to this record
 

 
Author Khalid El Asnaoui; Petia Radeva
Title Automatically Assess Day Similarity Using Visual Lifelogs Type Journal Article
Year 2020 Publication International Journal of Intelligent Systems Abbreviated Journal IJIS
Volume 29 Issue Pages 298–310
Keywords
Abstract (up) Today, we witness the appearance of many lifelogging cameras that are able to capture the life of a person wearing the camera and which produce a large number of images everyday. Automatically characterizing the experience and extracting patterns of behavior of individuals from this huge collection of unlabeled and unstructured egocentric data present major challenges and require novel and efficient algorithmic solutions. The main goal of this work is to propose a new method to automatically assess day similarity from the lifelogging images of a person. We propose a technique to measure the similarity between images based on the Swain’s distance and generalize it to detect the similarity between daily visual data. To this purpose, we apply the dynamic time warping (DTW) combined with the Swain’s distance for final day similarity estimation. For validation, we apply our technique on the Egocentric Dataset of University of Barcelona (EDUB) of 4912 daily images acquired by four persons with preliminary encouraging results.
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; no proj Approved no
Call Number AsR2020 Serial 3409
Permanent link to this record
 

 
Author Xim Cerda-Company; C. Alejandro Parraga; Xavier Otazu
Title Which tone-mapping operator is the best? A comparative study of perceptual quality Type Journal Article
Year 2018 Publication Journal of the Optical Society of America A Abbreviated Journal JOSA A
Volume 35 Issue 4 Pages 626-638
Keywords
Abstract (up) Tone-mapping operators (TMO) are designed to generate perceptually similar low-dynamic range images from high-dynamic range ones. We studied the performance of fifteen TMOs in two psychophysical experiments where observers compared the digitally-generated tone-mapped images to their corresponding physical scenes. All experiments were performed in a controlled environment and the setups were
designed to emphasize different image properties: in the first experiment we evaluated the local relationships among intensity-levels, and in the second one we evaluated global visual appearance among physical scenes and tone-mapped images, which were presented side by side. We ranked the TMOs according
to how well they reproduced the results obtained in the physical scene. Our results show that ranking position clearly depends on the adopted evaluation criteria, which implies that, in general, these tone-mapping algorithms consider either local or global image attributes but rarely both. Regarding the
question of which TMO is the best, KimKautz [1] and Krawczyk [2] obtained the better results across the different experiments. We conclude that a more thorough and standardized evaluation criteria is needed to study all the characteristics of TMOs, as there is ample room for improvement in future developments.
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 NEUROBIT; 600.120; 600.128 Approved no
Call Number Admin @ si @ CPO2018 Serial 3088
Permanent link to this record
 

 
Author Xavier Otazu
Title Perceptual tone-mapping operator based on multiresolution contrast decomposition Type Abstract
Year 2012 Publication Perception Abbreviated Journal PER
Volume 41 Issue Pages 86
Keywords
Abstract (up) Tone-mapping operators (TMO) are used to display high dynamic range(HDR) images in low dynamic range (LDR) displays. Many computational and biologically inspired approaches have been used in the literature, being many of them based on multiresolution decompositions. In this work, a simple two stage model for TMO is presented. The first stage is a novel multiresolution contrast decomposition, which is inspired in a pyramidal contrast decomposition (Peli, 1990 Journal of the Optical Society of America7(10), 2032-2040).
This novel multiresolution decomposition represents the Michelson contrast of the image at different spatial scales. This multiresolution contrast representation, applied on the intensity channel of an opponent colour decomposition, is processed by a non-linear saturating model of V1 neurons (Albrecht et al, 2002 Journal ofNeurophysiology 88(2) 888-913). This saturation model depends on the visual frequency, and it has been modified in order to include information from the extended Contrast Sensitivity Function (e-CSF) (Otazu et al, 2010 Journal ofVision10(12) 5).
A set of HDR images in Radiance RGBE format (from CIS HDR Photographic Survey and Greg Ward database) have been used to test the model, obtaining a set of LDR images. The resulting LDR images do not show the usual halo or color modification artifacts.
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 0301-0066 ISBN Medium
Area Expedition Conference
Notes CIC Approved no
Call Number Admin @ si @ Ota2012 Serial 2179
Permanent link to this record
 

 
Author Aymen Azaza; Joost Van de Weijer; Ali Douik; Javad Zolfaghari Bengar; Marc Masana
Title Saliency from High-Level Semantic Image Features Type Journal
Year 2020 Publication SN Computer Science Abbreviated Journal SN
Volume 1 Issue 4 Pages 1-12
Keywords
Abstract (up) Top-down semantic information is known to play an important role in assigning saliency. Recently, large strides have been made in improving state-of-the-art semantic image understanding in the fields of object detection and semantic segmentation. Therefore, since these methods have now reached a high-level of maturity, evaluation of the impact of high-level image understanding on saliency estimation is now feasible. We propose several saliency features which are computed from object detection and semantic segmentation results. We combine these features with a standard baseline method for saliency detection to evaluate their importance. Experiments demonstrate that the proposed features derived from object detection and semantic segmentation improve saliency estimation significantly. Moreover, they show that our method obtains state-of-the-art results on (FT, ImgSal, and SOD datasets) and obtains competitive results on four other datasets (ECSSD, PASCAL-S, MSRA-B, and HKU-IS).
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes LAMP; 600.120; 600.109; 600.106 Approved no
Call Number Admin @ si @ AWD2020 Serial 3503
Permanent link to this record
 

 
Author Jose Luis Gomez; Gabriel Villalonga; Antonio Lopez
Title Co-Training for Deep Object Detection: Comparing Single-Modal and Multi-Modal Approaches Type Journal Article
Year 2021 Publication Sensors Abbreviated Journal SENS
Volume 21 Issue 9 Pages 3185
Keywords co-training; multi-modality; vision-based object detection; ADAS; self-driving
Abstract (up) Top-performing computer vision models are powered by convolutional neural networks (CNNs). Training an accurate CNN highly depends on both the raw sensor data and their associated ground truth (GT). Collecting such GT is usually done through human labeling, which is time-consuming and does not scale as we wish. This data-labeling bottleneck may be intensified due to domain shifts among image sensors, which could force per-sensor data labeling. In this paper, we focus on the use of co-training, a semi-supervised learning (SSL) method, for obtaining self-labeled object bounding boxes (BBs), i.e., the GT to train deep object detectors. In particular, we assess the goodness of multi-modal co-training by relying on two different views of an image, namely, appearance (RGB) and estimated depth (D). Moreover, we compare appearance-based single-modal co-training with multi-modal. Our results suggest that in a standard SSL setting (no domain shift, a few human-labeled data) and under virtual-to-real domain shift (many virtual-world labeled data, no human-labeled data) multi-modal co-training outperforms single-modal. In the latter case, by performing GAN-based domain translation both co-training modalities are on par, at least when using an off-the-shelf depth estimation model not specifically trained on the translated images.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes ADAS; 600.118 Approved no
Call Number Admin @ si @ GVL2021 Serial 3562
Permanent link to this record
 

 
Author Naveen Onkarappa; Angel Sappa
Title A Novel Space Variant Image Representation Type Journal Article
Year 2013 Publication Journal of Mathematical Imaging and Vision Abbreviated Journal JMIV
Volume 47 Issue 1-2 Pages 48-59
Keywords Space-variant representation; Log-polar mapping; Onboard vision applications
Abstract (up) Traditionally, in machine vision images are represented using cartesian coordinates with uniform sampling along the axes. On the contrary, biological vision systems represent images using polar coordinates with non-uniform sampling. For various advantages provided by space-variant representations many researchers are interested in space-variant computer vision. In this direction the current work proposes a novel and simple space variant representation of images. The proposed representation is compared with the classical log-polar mapping. The log-polar representation is motivated by biological vision having the characteristic of higher resolution at the fovea and reduced resolution at the periphery. On the contrary to the log-polar, the proposed new representation has higher resolution at the periphery and lower resolution at the fovea. Our proposal is proved to be a better representation in navigational scenarios such as driver assistance systems and robotics. The experimental results involve analysis of optical flow fields computed on both proposed and log-polar representations. Additionally, an egomotion estimation application is also shown as an illustrative example. The experimental analysis comprises results from synthetic as well as real sequences.
Address
Corporate Author Thesis
Publisher Springer US Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 0924-9907 ISBN Medium
Area Expedition Conference
Notes ADAS; 600.055; 605.203; 601.215 Approved no
Call Number Admin @ si @ OnS2013a Serial 2243
Permanent link to this record
 

 
Author Sergio Escalera; Oriol Pujol; Petia Radeva
Title Traffic sign recognition system with β -correction Type Journal Article
Year 2010 Publication Machine Vision and Applications Abbreviated Journal MVA
Volume 21 Issue 2 Pages 99–111
Keywords
Abstract (up) Traffic sign classification represents a classical application of multi-object recognition processing in uncontrolled adverse environments. Lack of visibility, illumination changes, and partial occlusions are just a few problems. In this paper, we introduce a novel system for multi-class classification of traffic signs based on error correcting output codes (ECOC). ECOC is based on an ensemble of binary classifiers that are trained on bi-partition of classes. We classify a wide set of traffic signs types using robust error correcting codings. Moreover, we introduce the novel β-correction decoding strategy that outperforms the state-of-the-art decoding techniques, classifying a high number of classes with great success.
Address
Corporate Author Thesis
Publisher Springer-Verlag Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 0932-8092 ISBN Medium
Area Expedition Conference
Notes MILAB;HUPBA Approved no
Call Number BCNPCL @ bcnpcl @ EPR2010a Serial 1276
Permanent link to this record
 

 
Author Jon Almazan; Bojana Gajic; Naila Murray; Diane Larlus
Title Re-ID done right: towards good practices for person re-identification Type Miscellaneous
Year 2018 Publication Arxiv Abbreviated Journal
Volume Issue Pages
Keywords
Abstract (up) Training a deep architecture using a ranking loss has become standard for the person re-identification task. Increasingly, these deep architectures include additional components that leverage part detections, attribute predictions, pose estimators and other auxiliary information, in order to more effectively localize and align discriminative image regions. In this paper we adopt a different approach and carefully design each component of a simple deep architecture and, critically, the strategy for training it effectively for person re-identification. We extensively evaluate each design choice, leading to a list of good practices for person re-identification. By following these practices, our approach outperforms the state of the art, including more complex methods with auxiliary components, by large margins on four benchmark datasets. We also provide a qualitative analysis of our trained representation which indicates that, while compact, it is able to capture information from localized and discriminative regions, in a manner akin to an implicit attention mechanism.
Address January 2018
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 Approved no
Call Number Admin @ si @ Serial 3711
Permanent link to this record
 

 
Author Bojana Gajic; Ariel Amato; Ramon Baldrich; Carlo Gatta
Title Bag of Negatives for Siamese Architectures Type Conference Article
Year 2019 Publication 30th British Machine Vision Conference Abbreviated Journal
Volume Issue Pages
Keywords
Abstract (up) Training a Siamese architecture for re-identification with a large number of identities is a challenging task due to the difficulty of finding relevant negative samples efficiently. In this work we present Bag of Negatives (BoN), a method for accelerated and improved training of Siamese networks that scales well on datasets with a very large number of identities. BoN is an efficient and loss-independent method, able to select a bag of high quality negatives, based on a novel online hashing strategy.
Address Cardiff; United Kingdom; September 2019
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 BMVC
Notes CIC; 600.140; 600.118 Approved no
Call Number Admin @ si @ GAB2019b Serial 3263
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 CVPR Workshop on Ground Truth – What is a good dataset? Abbreviated Journal
Volume Issue Pages 688 - 693
Keywords Pedestrian Detection; Domain Adaptation
Abstract (up) 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