Home << 1 2 3 4 5 6 7 8 9 10 >> [11–12]
List View
 | 
Citations
 | 
Details
   web
Records
Author (down) Fahad Shahbaz Khan; Muhammad Anwer Rao; Joost Van de Weijer; Andrew Bagdanov; Antonio Lopez; Michael Felsberg
Title Coloring Action Recognition in Still Images Type Journal Article
Year 2013 Publication International Journal of Computer Vision Abbreviated Journal IJCV
Volume 105 Issue 3 Pages 205-221
Keywords
Abstract In this article we investigate the problem of human action recognition in static images. By action recognition we intend a class of problems which includes both action classification and action detection (i.e. simultaneous localization and classification). Bag-of-words image representations yield promising results for action classification, and deformable part models perform very well object detection. The representations for action recognition typically use only shape cues and ignore color information. Inspired by the recent success of color in image classification and object detection, we investigate the potential of color for action classification and detection in static images. We perform a comprehensive evaluation of color descriptors and fusion approaches for action recognition. Experiments were conducted on the three datasets most used for benchmarking action recognition in still images: Willow, PASCAL VOC 2010 and Stanford-40. Our experiments demonstrate that incorporating color information considerably improves recognition performance, and that a descriptor based on color names outperforms pure color descriptors. Our experiments demonstrate that late fusion of color and shape information outperforms other approaches on action recognition. Finally, we show that the different color–shape fusion approaches result in complementary information and combining them yields state-of-the-art performance for action classification.
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 0920-5691 ISBN Medium
Area Expedition Conference
Notes CIC; ADAS; 600.057; 600.048 Approved no
Call Number Admin @ si @ KRW2013 Serial 2285
Permanent link to this record
 
 
Author (down) Fahad Shahbaz Khan; Joost Van de Weijer; Sadiq Ali; Michael Felsberg
Title Evaluating the impact of color on texture recognition Type Conference Article
Year 2013 Publication 15th International Conference on Computer Analysis of Images and Patterns Abbreviated Journal
Volume 8047 Issue Pages 154-162
Keywords Color; Texture; image representation
Abstract State-of-the-art texture descriptors typically operate on grey scale images while ignoring color information. A common way to obtain a joint color-texture representation is to combine the two visual cues at the pixel level. However, such an approach provides sub-optimal results for texture categorisation task.
In this paper we investigate how to optimally exploit color information for texture recognition. We evaluate a variety of color descriptors, popular in image classification, for texture categorisation. In addition we analyze different fusion approaches to combine color and texture cues. Experiments are conducted on the challenging scenes and 10 class texture datasets. Our experiments clearly suggest that in all cases color names provide the best performance. Late fusion is the best strategy to combine color and texture. By selecting the best color descriptor with optimal fusion strategy provides a gain of 5% to 8% compared to texture alone on scenes and texture datasets.
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
Series Volume Series Issue Edition
ISSN 0302-9743 ISBN 978-3-642-40260-9 Medium
Area Expedition Conference CAIP
Notes CIC; 600.048 Approved no
Call Number Admin @ si @ KWA2013 Serial 2263
Permanent link to this record
 
 
Author (down) Fadi Dornaika; Bogdan Raducanu
Title Out-of-Sample Embedding for Manifold Learning Applied to Face Recognition Type Conference Article
Year 2013 Publication IEEE International Workshop on Analysis and Modeling of Faces and Gestures Abbreviated Journal
Volume Issue Pages 862-868
Keywords
Abstract Manifold learning techniques are affected by two critical aspects: (i) the design of the adjacency graphs, and (ii) the embedding of new test data---the out-of-sample problem. For the first aspect, the proposed schemes were heuristically driven. For the second aspect, the difficulty resides in finding an accurate mapping that transfers unseen data samples into an existing manifold. Past works addressing these two aspects were heavily parametric in the sense that the optimal performance is only reached for a suitable parameter choice that should be known in advance. In this paper, we demonstrate that sparse coding theory not only serves for automatic graph reconstruction as shown in recent works, but also represents an accurate alternative for out-of-sample embedding. Considering for a case study the Laplacian Eigenmaps, we applied our method to the face recognition problem. To evaluate the effectiveness of the proposed out-of-sample embedding, experiments are conducted using the k-nearest neighbor (KNN) and Kernel Support Vector Machines (KSVM) classifiers on four public face databases. The experimental results show that the proposed model is able to achieve high categorization effectiveness as well as high consistency with non-linear embeddings/manifolds obtained in batch modes.
Address Portland; USA; June 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 CVPRW
Notes OR; 600.046;MV Approved no
Call Number Admin @ si @ DoR2013 Serial 2236
Permanent link to this record
 
 
Author (down) Fadi Dornaika; Alireza Bosaghzadeh; Bogdan Raducanu
Title Efficient Graph Construction for Label Propagation based Multi-observation Face Recognition Type Conference Article
Year 2013 Publication Human Behavior Understanding 4th International Workshop Abbreviated Journal
Volume 8212 Issue Pages 124-135
Keywords
Abstract Workshop on Human Behavior Understanding
Human-machine interaction is a hot topic nowadays in the communities of multimedia and computer vision. In this context, face recognition algorithms (used as primary cue for a person’s identity assessment) work well under controlled conditions but degrade significantly when tested in real-world environments. Recently, graph-based label propagation for multi-observation face recognition was proposed. However, the associated graphs were constructed in an ad-hoc manner (e.g., using the KNN graph) that cannot adapt optimally to the data. In this paper, we propose a novel approach for efficient and adaptive graph construction that can be used for multi-observation face recognition as well as for other recognition problems. Experimental results performed on Honda video face database, show a distinct advantage of the proposed method over the standard graph construction methods.
Address Barcelona
Corporate Author Thesis
Publisher Springer International Publishing 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 978-3-319-02713-5 Medium
Area Expedition Conference HBU
Notes OR;MV Approved no
Call Number Admin @ si @ DBR2013 Serial 2315
Permanent link to this record
 
 
Author (down) 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 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 (down) Ernest Valveny; Oriol Ramos Terrades; Joan Mas; Marçal Rusiñol
Title Interactive Document Retrieval and Classification. Type Book Chapter
Year 2013 Publication Multimodal Interaction in Image and Video Applications Abbreviated Journal
Volume 48 Issue Pages 17-30
Keywords
Abstract In this chapter we describe a system for document retrieval and classification following the interactive-predictive framework. In particular, the system addresses two different scenarios of document analysis: document classification based on visual appearance and logo detection. These two classical problems of document analysis are formulated following the interactive-predictive model, taking the user interaction into account to make easier the process of annotating and labelling the documents. A system implementing this model in a real scenario is presented and analyzed. This system also takes advantage of active learning techniques to speed up the task of labelling the documents.
Address
Corporate Author Thesis
Publisher Springer Berlin Heidelberg Place of Publication Editor Angel Sappa; Jordi Vitria
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 1868-4394 ISBN 978-3-642-35931-6 Medium
Area Expedition Conference
Notes DAG Approved no
Call Number Admin @ si @ VRM2013 Serial 2341
Permanent link to this record
 
 
Author (down) Enric Marti; Ferran Poveda; Antoni Gurgui; Jaume Rocarias; Debora Gil; Aura Hernandez-Sabate
Title Una experiencia de estructura, funcionamiento y evaluación de la asignatura de graficos por computador con metodologia de aprendizaje basado en proyectos Type Miscellaneous
Year 2013 Publication IV Congreso Internacional UNIVEST Abbreviated Journal
Volume Issue Pages
Keywords
Abstract IV Congreso Internacional UNIVEST
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 UNIVEST
Notes IAM; ADAS Approved no
Call Number Admin @ si @ MPG2013b Serial 2384
Permanent link to this record
 
 
Author (down) Enric Marti; Ferran Poveda; Antoni Gurgui; Jaume Rocarias; Debora Gil
Title Una propuesta de seguimiento, tutorías on line y evaluación en la metodología de Aprendizaje Basado en Proyectos Type Miscellaneous
Year 2013 Publication IV Congreso Internacional UNIVEST Abbreviated Journal
Volume Issue Pages
Keywords
Abstract Poster
Address Girona
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 UNIVEST
Notes IAM Approved no
Call Number Admin @ si @ MPG2013a Serial 2304
Permanent link to this record
 
 
Author (down) Dimosthenis Karatzas; Faisal Shafait; Seiichi Uchida; Masakazu Iwamura; Lluis Gomez; Sergi Robles; Joan Mas; David Fernandez; Jon Almazan; Lluis Pere de las Heras
Title ICDAR 2013 Robust Reading Competition Type Conference Article
Year 2013 Publication 12th International Conference on Document Analysis and Recognition Abbreviated Journal
Volume Issue Pages 1484-1493
Keywords
Abstract This report presents the final results of the ICDAR 2013 Robust Reading Competition. The competition is structured in three Challenges addressing text extraction in different application domains, namely born-digital images, real scene images and real-scene videos. The Challenges are organised around specific tasks covering text localisation, text segmentation and word recognition. The competition took place in the first quarter of 2013, and received a total of 42 submissions over the different tasks offered. This report describes the datasets and ground truth specification, details the performance evaluation protocols used and presents the final results along with a brief summary of the participating methods.
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 Approved no
Call Number Admin @ si @ KSU2013 Serial 2318
Permanent link to this record
 
 
Author (down) Debora Gil; Agnes Borras; Sergio Vera; Miguel Angel Gonzalez Ballester
Title A Validation Benchmark for Assessment of Medial Surface Quality for Medical Applications Type Conference Article
Year 2013 Publication 9th International Conference on Computer Vision Systems Abbreviated Journal
Volume 7963 Issue Pages 334-343
Keywords Medial Surfaces; Shape Representation; Medical Applications; Performance Evaluation
Abstract Confident use of medial surfaces in medical decision support systems requires evaluating their quality for detecting pathological deformations and describing anatomical volumes. Validation in the medical imaging field is a challenging task mainly due to the difficulties for getting consensual ground truth. In this paper we propose a validation benchmark for assessing medial surfaces in the context of medical applications. Our benchmark includes a home-made database of synthetic medial surfaces and volumes and specific scores for evaluating surface accuracy, its stability against volume deformations and its capabilities for accurate reconstruction of anatomical volumes.
Address Sant Petersburg; Russia; July 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 978-3-642-39401-0 Medium
Area Expedition Conference ICVS
Notes IAM; 600.044; 600.060 Approved no
Call Number Admin @ si @ GBV2013 Serial 2300
Permanent link to this record
 
 
Author (down) 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 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 (down) David Vazquez; Antonio Lopez; Daniel Ponsa; David Geronimo
Title Interactive Training of Human Detectors Type Book Chapter
Year 2013 Publication Multiodal Interaction in Image and Video Applications Abbreviated Journal
Volume 48 Issue Pages 169-182
Keywords Pedestrian Detection; Virtual World; AdaBoost; Domain Adaptation
Abstract Image based human detection remains as a challenging problem. Most promising detectors rely on classifiers trained with labelled samples. However, labelling is a manual labor intensive step. To overcome this problem we propose to collect images of pedestrians from a virtual city, i.e., with automatic labels, and train a pedestrian detector with them, which works fine when such virtual-world data are similar to testing one, i.e., real-world pedestrians in urban areas. When testing data is acquired in different conditions than training one, e.g., human detection in personal photo albums, dataset shift appears. In previous work, we cast this problem as one of domain adaptation and solve it with an active learning procedure. In this work, we focus on the same problem but evaluating a different set of faster to compute features, i.e., Haar, EOH and their combination. In particular, we train a classifier with virtual-world data, using such features and Real AdaBoost as learning machine. This classifier is applied to real-world training images. Then, a human oracle interactively corrects the wrong detections, i.e., few miss detections are manually annotated and some false ones are pointed out too. A low amount of manual annotation is fixed as restriction. Real- and virtual-world difficult samples are combined within what we call cool world and we retrain the classifier with this data. Our experiments show that this adapted classifier is equivalent to the one trained with only real-world data but requiring 90% less manual annotations.
Address Springer Heidelberg New York Dordrecht London
Corporate Author Thesis
Publisher Springer Berlin Heidelberg Place of Publication Editor
Language English Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 1868-4394 ISBN 978-3-642-35931-6 Medium
Area Expedition Conference
Notes ADAS; 600.057; 600.054; 605.203 Approved no
Call Number VLP2013; ADAS @ adas @ vlp2013 Serial 2193
Permanent link to this record
 
 
Author (down) David Vazquez
Title Domain Adaptation of Virtual and Real Worlds for Pedestrian Detection Type Book Whole
Year 2013 Publication PhD Thesis, Universitat de Barcelona-CVC Abbreviated Journal
Volume 1 Issue 1 Pages 1-105
Keywords Pedestrian Detection; Domain Adaptation
Abstract Pedestrian detection is of paramount interest for many applications, e.g. Advanced Driver Assistance Systems, Intelligent Video Surveillance and Multimedia systems. Most promising pedestrian detectors rely on appearance-based classifiers trained with annotated data. However, the required annotation step represents an intensive and subjective task for humans, what makes worth to minimize their intervention in this process by using computational tools like realistic virtual worlds. The reason to use these kind of tools relies in the fact that they allow the automatic generation of precise and rich annotations of visual information. Nevertheless, the use of this kind of data comes with the following question: can a pedestrian appearance model learnt with virtual-world data work successfully for pedestrian detection in real-world scenarios?. To answer this question, we conduct different experiments that suggest a positive answer. However, the pedestrian classifiers trained with virtual-world data can suffer the so called dataset shift problem as real-world based classifiers does. Accordingly, we have designed different domain adaptation techniques to face this problem, all of them integrated in a same framework (V-AYLA). We have explored different methods to train a domain adapted pedestrian classifiers by collecting a few pedestrian samples from the target domain (real world) and combining them with many samples of the source domain (virtual world). The extensive experiments we present show that pedestrian detectors developed within the V-AYLA framework do achieve domain adaptation. Ideally, we would like to adapt our system without any human intervention. Therefore, as a first proof of concept we also propose an unsupervised domain adaptation technique that avoids human intervention during the adaptation process. To the best of our knowledge, this Thesis work is the first demonstrating adaptation of virtual and real worlds for developing an object detector. Last but not least, we also assessed a different strategy to avoid the dataset shift that consists in collecting real-world samples and retrain with them in such a way that no bounding boxes of real-world pedestrians have to be provided. We show that the generated classifier is competitive with respect to the counterpart trained with samples collected by manually annotating pedestrian bounding boxes. The results presented on this Thesis not only end with a proposal for adapting a virtual-world pedestrian detector to the real world, but also it goes further by pointing out a new methodology that would allow the system to adapt to different situations, which we hope will provide the foundations for future research in this unexplored area.
Address Barcelona
Corporate Author Thesis Ph.D. thesis
Publisher Ediciones Graficas Rey Place of Publication Barcelona Editor Antonio Lopez;Daniel Ponsa
Language English Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN 978-84-940530-1-6 Medium
Area Expedition Conference
Notes adas Approved yes
Call Number ADAS @ adas @ Vaz2013 Serial 2276
Permanent link to this record
 
 
Author (down) 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 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 (down) 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 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