|   | 
Details
   web
Records
Author Javad Zolfaghari Bengar; Bogdan Raducanu; Joost Van de Weijer
Title When Deep Learners Change Their Mind: Learning Dynamics for Active Learning Type Conference Article
Year 2021 Publication 19th International Conference on Computer Analysis of Images and Patterns Abbreviated Journal
Volume (down) 13052 Issue 1 Pages 403-413
Keywords
Abstract Active learning aims to select samples to be annotated that yield the largest performance improvement for the learning algorithm. Many methods approach this problem by measuring the informativeness of samples and do this based on the certainty of the network predictions for samples. However, it is well-known that neural networks are overly confident about their prediction and are therefore an untrustworthy source to assess sample informativeness. In this paper, we propose a new informativeness-based active learning method. Our measure is derived from the learning dynamics of a neural network. More precisely we track the label assignment of the unlabeled data pool during the training of the algorithm. We capture the learning dynamics with a metric called label-dispersion, which is low when the network consistently assigns the same label to the sample during the training of the network and high when the assigned label changes frequently. We show that label-dispersion is a promising predictor of the uncertainty of the network, and show on two benchmark datasets that an active learning algorithm based on label-dispersion obtains excellent results.
Address September 2021
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 CAIP
Notes LAMP; Approved no
Call Number Admin @ si @ ZRV2021 Serial 3673
Permanent link to this record
 

 
Author Gemma Rotger; Francesc Moreno-Noguer; Felipe Lumbreras; Antonio Agudo
Title Single view facial hair 3D reconstruction Type Conference Article
Year 2019 Publication 9th Iberian Conference on Pattern Recognition and Image Analysis Abbreviated Journal
Volume (down) 11867 Issue Pages 423-436
Keywords 3D Vision; Shape Reconstruction; Facial Hair Modeling
Abstract n this work, we introduce a novel energy-based framework that addresses the challenging problem of 3D reconstruction of facial hair from a single RGB image. To this end, we identify hair pixels over the image via texture analysis and then determine individual hair fibers that are modeled by means of a parametric hair model based on 3D helixes. We propose to minimize an energy composed of several terms, in order to adapt the hair parameters that better fit the image detections. The final hairs respond to the resulting fibers after a post-processing step where we encourage further realism. The resulting approach generates realistic facial hair fibers from solely an RGB image without assuming any training data nor user interaction. We provide an experimental evaluation on real-world pictures where several facial hair styles and image conditions are observed, showing consistent results and establishing a comparison with respect to competing approaches.
Address Madrid; July 2019
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title LNCS
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference IbPRIA
Notes MSIAU; 600.086; 600.130; 600.122 Approved no
Call Number Admin @ si @ Serial 3707
Permanent link to this record
 

 
Author Muhammad Anwer Rao; Fahad Shahbaz Khan; Joost Van de Weijer; Jorma Laaksonen
Title Top-Down Deep Appearance Attention for Action Recognition Type Conference Article
Year 2017 Publication 20th Scandinavian Conference on Image Analysis Abbreviated Journal
Volume (down) 10269 Issue Pages 297-309
Keywords Action recognition; CNNs; Feature fusion
Abstract Recognizing human actions in videos is a challenging problem in computer vision. Recently, convolutional neural network based deep features have shown promising results for action recognition. In this paper, we investigate the problem of fusing deep appearance and motion cues for action recognition. We propose a video representation which combines deep appearance and motion based local convolutional features within the bag-of-deep-features framework. Firstly, dense deep appearance and motion based local convolutional features are extracted from spatial (RGB) and temporal (flow) networks, respectively. Both visual cues are processed in parallel by constructing separate visual vocabularies for appearance and motion. A category-specific appearance map is then learned to modulate the weights of the deep motion features. The proposed representation is discriminative and binds the deep local convolutional features to their spatial locations. Experiments are performed on two challenging datasets: JHMDB dataset with 21 action classes and ACT dataset with 43 categories. The results clearly demonstrate that our approach outperforms both standard approaches of early and late feature fusion. Further, our approach is only employing action labels and without exploiting body part information, but achieves competitive performance compared to the state-of-the-art deep features based approaches.
Address Tromso; June 2017
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title LNCS
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference SCIA
Notes LAMP; 600.109; 600.068; 600.120 Approved no
Call Number Admin @ si @ RKW2017b Serial 3039
Permanent link to this record
 

 
Author Veronica Romero; Alicia Fornes; Enrique Vidal; Joan Andreu Sanchez
Title Information Extraction in Handwritten Marriage Licenses Books Using the MGGI Methodology Type Conference Article
Year 2017 Publication 8th Iberian Conference on Pattern Recognition and Image Analysis Abbreviated Journal
Volume (down) 10255 Issue Pages 287-294
Keywords Handwritten Text Recognition; Information extraction; Language modeling; MGGI; Categories-based language model
Abstract Historical records of daily activities provide intriguing insights into the life of our ancestors, useful for demographic and genealogical research. For example, marriage license books have been used for centuries by ecclesiastical and secular institutions to register marriages. These books follow a simple structure of the text in the records with a evolutionary vocabulary, mainly composed of proper names that change along the time. This distinct vocabulary makes automatic transcription and semantic information extraction difficult tasks. In previous works we studied the use of category-based language models and how a Grammatical Inference technique known as MGGI could improve the accuracy of these tasks. In this work we analyze the main causes of the semantic errors observed in previous results and apply a better implementation of the MGGI technique to solve these problems. Using the resulting language model, transcription and information extraction experiments have been carried out, and the results support our proposed approach.
Address Faro; Portugal; June 2017
Corporate Author Thesis
Publisher Place of Publication Editor L.A. Alexandre; J.Salvador Sanchez; Joao M. F. Rodriguez
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title LNCS
Series Volume Series Issue Edition
ISSN ISBN 978-3-319-58837-7 Medium
Area Expedition Conference IbPRIA
Notes DAG; 602.006; 600.097; 600.121 Approved no
Call Number Admin @ si @ RFV2017 Serial 2952
Permanent link to this record
 

 
Author Juan Ramon Terven Salinas; Joaquin Salas; Bogdan Raducanu
Title Robust Head Gestures Recognition for Assistive Technology Type Book Chapter
Year 2014 Publication Pattern Recognition Abbreviated Journal
Volume (down) 8495 Issue Pages 152-161
Keywords
Abstract This paper presents a system capable of recognizing six head gestures: nodding, shaking, turning right, turning left, looking up, and looking down. The main difference of our system compared to other methods is that the Hidden Markov Models presented in this paper, are fully connected and consider all possible states in any given order, providing the following advantages to the system: (1) allows unconstrained movement of the head and (2) it can be easily integrated into a wearable device (e.g. glasses, neck-hung devices), in which case it can robustly recognize gestures in the presence of ego-motion. Experimental results show that this approach outperforms common methods that use restricted HMMs for each gesture.
Address
Corporate Author Thesis
Publisher Springer International Publishing 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 978-3-319-07490-0 Medium
Area Expedition Conference
Notes LAMP; Approved no
Call Number Admin @ si @ TSR2014b Serial 2505
Permanent link to this record
 

 
Author Javier Varona; Juan J. Villanueva
Title NeuroFilters: Neural Networks for image Processing. Type Conference Article
Year 1997 Publication Proceedings Volume 3101, New Image Processing Techniques and Applications: Algorithms, Methods, and Components II Abbreviated Journal
Volume (down) 3101 Issue Pages
Keywords
Abstract
Address Munich
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 ISE @ ise @ VaV1997a Serial 207
Permanent link to this record
 

 
Author Agnes Borras; Francesc Tous; Josep Llados; Maria Vanrell
Title High-Level Clothes Description Based on Colour-Texture and Structural Features Type Conference Article
Year 2003 Publication 1rst. Iberian Conference on Pattern Recognition and Image Analysis IbPRIA 2003 Abbreviated Journal
Volume (down) 2652 Issue Pages 108-116
Keywords
Abstract ecture Notes in Computer Science 2652 108–116
Address Palma de Mallorca
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title LNCS
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference IbPRIA
Notes DAG;CIC Approved no
Call Number CAT @ cat @ BTL2003b Serial 369
Permanent link to this record
 

 
Author David Guillamet; B. Moghaddam; Jordi Vitria
Title Modeling High-Order Dependencies in Local Appearance Models Type Conference Article
Year 2003 Publication 1rst. Iberian Conference on Pattern Recognition and Image Analysis IbPRIA 2003 Abbreviated Journal
Volume (down) 2652 Issue Pages 308-316
Keywords
Abstract
Address Springer-Verlag
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title LNCS
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference IbPRIA
Notes OR;MV Approved no
Call Number BCNPCL @ bcnpcl @ GMV2003a Serial 376
Permanent link to this record
 

 
Author David Guillamet; Jordi Vitria
Title An Experimental Evaluation of K-nn for Linear Transforms of Positive Data Type Conference Article
Year 2003 Publication 1rst. Iberian Conference on Pattern Recognition and Image Analysis IbPRIA 2003 Abbreviated Journal
Volume (down) 2652 Issue Pages 317-325
Keywords
Abstract
Address Springer-Verlag
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title LNCS
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference IbPRIA
Notes OR;MV Approved no
Call Number BCNPCL @ bcnpcl @ GuV2003a Serial 379
Permanent link to this record
 

 
Author David Lloret; Joan Serrat; Antonio Lopez; Juan J. Villanueva
Title Ultrasound to MR Volume Registration for Brain Sinking Measurement Type Conference Article
Year 2003 Publication 1rst. Iberian Conference on Pattern Recognition and Image Analysis IbPRIA 2003 Abbreviated Journal
Volume (down) 2652 Issue Pages 420-427
Keywords
Abstract
Address Springer-Verlag
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title LNCS
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference IbPRIA
Notes ADAS Approved no
Call Number ADAS @ adas @ LSL2003a Serial 384
Permanent link to this record
 

 
Author David Masip; Jordi Vitria
Title An Experimental Comparision of Dimensionality Reduction for Face Verification Methods Type Conference Article
Year 2003 Publication 1rst. Iberian Conference on Pattern Recognition and Image Analysis IbPRIA 2003 Abbreviated Journal
Volume (down) 2652 Issue Pages 530-537
Keywords
Abstract
Address Springer-Verlag
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title LNCS
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference IbPRIA
Notes OR;MV Approved no
Call Number BCNPCL @ bcnpcl @ MaV2003a Serial 386
Permanent link to this record
 

 
Author Daniel Ponsa; Xavier Roca
Title Multiple Model Approach to Deformable Shape Tracking Type Conference Article
Year 2003 Publication 1rst. Iberian Conference on Pattern Recognition and Image Analysis IbPRIA 2003 Abbreviated Journal
Volume (down) 2652 Issue Pages 782-792
Keywords
Abstract
Address Springer-Verlag
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title LNCS
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference IbPRIA
Notes ADAS;ISE Approved no
Call Number ADAS @ adas @ PoR2003 Serial 397
Permanent link to this record
 

 
Author Anna Salvatella; Maria Vanrell; Ramon Baldrich
Title Subtexture Components for Texture Description Type Conference Article
Year 2003 Publication 1rst. Iberian Conference on Pattern Recognition and Image Analysis IbPRIA 2003 Abbreviated Journal
Volume (down) 2652 Issue Pages 884-892
Keywords
Abstract
Address Springer-Verlag
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title LNCS
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference IbPRIA
Notes CIC Approved no
Call Number CAT @ cat @ SVR2003 Serial 421
Permanent link to this record
 

 
Author A.F. Sole; S. Ngan; G. Sapiro; X. Hu; Antonio Lopez
Title Anisotropic 2-D and 3-D Averaging of fMRI Signals Type Journal Article
Year 2001 Publication IEEE Transactions on Medical Imaging Abbreviated Journal
Volume (down) 2020 Issue 2 Pages 86-93
Keywords
Abstract
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes ADAS Approved no
Call Number ADAS @ adas @ SNS2001 Serial 165
Permanent link to this record
 

 
Author Josep Llados; Gemma Sanchez; Enric Marti
Title A String-Based Method to Recognize Symbols and Structural Textures in Architectural Plans. Type Conference Article
Year 1997 Publication Graphics Recognition Algorithms and Systems. GREC 1997. Abbreviated Journal
Volume (down) 1389 Issue Pages 91-103
Keywords
Abstract
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title LNCS
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes DAG Approved no
Call Number DAG @ dag @ LSM1997 Serial 44
Permanent link to this record