Home [11–20] << 21 22 23 24 25 26 27 28 29 30 >> [31–40]
List View
 | 
Citations
 | 
Details
   web
Records
Author Manuel Carbonell; Joan Mas; Mauricio Villegas; Alicia Fornes; Josep Llados
Title End-to-End Handwritten Text Detection and Transcription in Full Pages Type Conference Article
Year 2019 Publication 2nd International Workshop on Machine Learning Abbreviated Journal
Volume 5 Issue Pages 29-34
Keywords Handwritten Text Recognition; Layout Analysis; Text segmentation; Deep Neural Networks; Multi-task learning
Abstract When transcribing handwritten document images, inaccuracies in the text segmentation step often cause errors in the subsequent transcription step. For this reason, some recent methods propose to perform the recognition at paragraph level. But still, errors in the segmentation of paragraphs can affect
the transcription performance. In this work, we propose an end-to-end framework to transcribe full pages. The joint text detection and transcription allows to remove the layout analysis requirement at test time. The experimental results show that our approach can achieve comparable results to models that assume
segmented paragraphs, and suggest that joining the two tasks brings an improvement over doing the two tasks separately.
Address (down) Sydney; Australia; 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 ICDAR WML
Notes DAG; 600.140; 601.311; 600.140 Approved no
Call Number Admin @ si @ CMV2019 Serial 3353
Permanent link to this record
 
 
Author Asma Bensalah; Pau Riba; Alicia Fornes; Josep Llados
Title Shoot less and Sketch more: An Efficient Sketch Classification via Joining Graph Neural Networks and Few-shot Learning Type Conference Article
Year 2019 Publication 13th IAPR International Workshop on Graphics Recognition Abbreviated Journal
Volume Issue Pages 80-85
Keywords Sketch classification; Convolutional Neural Network; Graph Neural Network; Few-shot learning
Abstract With the emergence of the touchpad devices and drawing tablets, a new era of sketching started afresh. However, the recognition of sketches is still a tough task due to the variability of the drawing styles. Moreover, in some application scenarios there is few labelled data available for training,
which imposes a limitation for deep learning architectures. In addition, in many cases there is a need to generate models able to adapt to new classes. In order to cope with these limitations, we propose a method based on few-shot learning and graph neural networks for classifying sketches aiming for an efficient neural model. We test our approach with several databases of
sketches, showing promising results.
Address (down) Sydney; Australia; 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 GREC
Notes DAG; 600.140; 601.302; 600.121 Approved no
Call Number Admin @ si @ BRF2019 Serial 3354
Permanent link to this record
 
 
Author Pau Riba; Anjan Dutta; Lutz Goldmann; Alicia Fornes; Oriol Ramos Terrades; Josep Llados
Title Table Detection in Invoice Documents by Graph Neural Networks Type Conference Article
Year 2019 Publication 15th International Conference on Document Analysis and Recognition Abbreviated Journal
Volume Issue Pages 122-127
Keywords
Abstract Tabular structures in documents offer a complementary dimension to the raw textual data, representing logical or quantitative relationships among pieces of information. In digital mail room applications, where a large amount of
administrative documents must be processed with reasonable accuracy, the detection and interpretation of tables is crucial. Table recognition has gained interest in document image analysis, in particular in unconstrained formats (absence of rule lines, unknown information of rows and columns). In this work, we propose a graph-based approach for detecting tables in document images. Instead of using the raw content (recognized text), we make use of the location, context and content type, thus it is purely a structure perception approach, not dependent on the language and the quality of the text
reading. Our framework makes use of Graph Neural Networks (GNNs) in order to describe the local repetitive structural information of tables in invoice documents. Our proposed model has been experimentally validated in two invoice datasets and achieved encouraging results. Additionally, due to the scarcity
of benchmark datasets for this task, we have contributed to the community a novel dataset derived from the RVL-CDIP invoice data. It will be publicly released to facilitate future research.
Address (down) Sydney; Australia; 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 ICDAR
Notes DAG; 600.140; 601.302; 602.167; 600.121; 600.141 Approved no
Call Number Admin @ si @ RDG2019 Serial 3355
Permanent link to this record
 
 
Author Ekta Vats; Anders Hast; Alicia Fornes
Title Training-Free and Segmentation-Free Word Spotting using Feature Matching and Query Expansion Type Conference Article
Year 2019 Publication 15th International Conference on Document Analysis and Recognition Abbreviated Journal
Volume Issue Pages 1294-1299
Keywords Word spotting; Segmentation-free; Trainingfree; Query expansion; Feature matching
Abstract Historical handwritten text recognition is an interesting yet challenging problem. In recent times, deep learning based methods have achieved significant performance in handwritten text recognition. However, handwriting recognition using deep learning needs training data, and often, text must be previously segmented into lines (or even words). These limitations constrain the application of HTR techniques in document collections, because training data or segmented words are not always available. Therefore, this paper proposes a training-free and segmentation-free word spotting approach that can be applied in unconstrained scenarios. The proposed word spotting framework is based on document query word expansion and relaxed feature matching algorithm, which can easily be parallelised. Since handwritten words posses distinct shape and characteristics, this work uses a combination of different keypoint detectors
and Fourier-based descriptors to obtain a sufficient degree of relaxed matching. The effectiveness of the proposed method is empirically evaluated on well-known benchmark datasets using standard evaluation measures. The use of informative features along with query expansion significantly contributed in efficient performance of the proposed method.
Address (down) Sydney; Australia; 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 ICDAR
Notes DAG; 600.140; 600.121 Approved no
Call Number Admin @ si @ VHF2019 Serial 3356
Permanent link to this record
 
 
Author Yainuvis Socarras; Sebastian Ramos; David Vazquez; Antonio Lopez; Theo Gevers
Title Adapting Pedestrian Detection from Synthetic to Far Infrared Images Type Conference Article
Year 2013 Publication ICCV Workshop on Visual Domain Adaptation and Dataset Bias Abbreviated Journal
Volume Issue Pages
Keywords Domain Adaptation; Far Infrared; Pedestrian Detection
Abstract We present different techniques to adapt a pedestrian classifier trained with synthetic images and the corresponding automatically generated annotations to operate with far infrared (FIR) images. The information contained in this kind of images allow us to develop a robust pedestrian detector invariant to extreme illumination changes.
Address (down) Sydney; Australia; December 2013
Corporate Author Thesis
Publisher Place of Publication Sydney, Australy Editor
Language English Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference ICCVW-VisDA
Notes ADAS; 600.054; 600.055; 600.057; 601.217;ISE Approved no
Call Number ADAS @ adas @ SRV2013 Serial 2334
Permanent link to this record
 
 
Author Patricia Marquez; Debora Gil; Aura Hernandez-Sabate
Title Evaluation of the Capabilities of Confidence Measures for Assessing Optical Flow Quality Type Conference Article
Year 2013 Publication ICCV Workshop on Computer Vision in Vehicle Technology: From Earth to Mars Abbreviated Journal
Volume Issue Pages 624-631
Keywords
Abstract Assessing Optical Flow (OF) quality is essential for its further use in reliable decision support systems. The absence of ground truth in such situations leads to the computation of OF Confidence Measures (CM) obtained from either input or output data. A fair comparison across the capabilities of the different CM for bounding OF error is required in order to choose the best OF-CM pair for discarding points where OF computation is not reliable. This paper presents a statistical probabilistic framework for assessing the quality of a given CM. Our quality measure is given in terms of the percentage of pixels whose OF error bound can not be determined by CM values. We also provide statistical tools for the computation of CM values that ensures a given accuracy of the flow field.
Address (down) Sydney; Australia; December 2013
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference CVTT:E2M
Notes IAM; ADAS; 600.044; 600.057; 601.145 Approved no
Call Number Admin @ si @ MGH2013b Serial 2351
Permanent link to this record
 
 
Author Javier Marin; David Vazquez; Antonio Lopez; Jaume Amores; Bastian Leibe
Title Random Forests of Local Experts for Pedestrian Detection Type Conference Article
Year 2013 Publication 15th IEEE International Conference on Computer Vision Abbreviated Journal
Volume Issue Pages 2592 - 2599
Keywords ADAS; Random Forest; Pedestrian Detection
Abstract Pedestrian detection is one of the most challenging tasks in computer vision, and has received a lot of attention in the last years. Recently, some authors have shown the advantages of using combinations of part/patch-based detectors in order to cope with the large variability of poses and the existence of partial occlusions. In this paper, we propose a pedestrian detection method that efficiently combines multiple local experts by means of a Random Forest ensemble. The proposed method works with rich block-based representations such as HOG and LBP, in such a way that the same features are reused by the multiple local experts, so that no extra computational cost is needed with respect to a holistic method. Furthermore, we demonstrate how to integrate the proposed approach with a cascaded architecture in order to achieve not only high accuracy but also an acceptable efficiency. In particular, the resulting detector operates at five frames per second using a laptop machine. We tested the proposed method with well-known challenging datasets such as Caltech, ETH, Daimler, and INRIA. The method proposed in this work consistently ranks among the top performers in all the datasets, being either the best method or having a small difference with the best one.
Address (down) Sydney; Australia; December 2013
Corporate Author Thesis
Publisher IEEE Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 1550-5499 ISBN Medium
Area Expedition Conference ICCV
Notes ADAS; 600.057; 600.054 Approved no
Call Number ADAS @ adas @ MVL2013 Serial 2333
Permanent link to this record
 
 
Author Jon Almazan; Albert Gordo; Alicia Fornes; Ernest Valveny
Title Handwritten Word Spotting with Corrected Attributes Type Conference Article
Year 2013 Publication 15th IEEE International Conference on Computer Vision Abbreviated Journal
Volume Issue Pages 1017-1024
Keywords
Abstract We propose an approach to multi-writer word spotting, where the goal is to find a query word in a dataset comprised of document images. We propose an attributes-based approach that leads to a low-dimensional, fixed-length representation of the word images that is fast to compute and, especially, fast to compare. This approach naturally leads to an unified representation of word images and strings, which seamlessly allows one to indistinctly perform query-by-example, where the query is an image, and query-by-string, where the query is a string. We also propose a calibration scheme to correct the attributes scores based on Canonical Correlation Analysis that greatly improves the results on a challenging dataset. We test our approach on two public datasets showing state-of-the-art results.
Address (down) Sydney; Australia; December 2013
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 1550-5499 ISBN Medium
Area Expedition Conference ICCV
Notes DAG Approved no
Call Number Admin @ si @ AGF2013 Serial 2327
Permanent link to this record
 
 
Author Gemma Roig; Xavier Boix; R. de Nijs; Sebastian Ramos; K. Kühnlenz; Luc Van Gool
Title Active MAP Inference in CRFs for Efficient Semantic Segmentation Type Conference Article
Year 2013 Publication 15th IEEE International Conference on Computer Vision Abbreviated Journal
Volume Issue Pages 2312 - 2319
Keywords Semantic Segmentation
Abstract Most MAP inference algorithms for CRFs optimize an energy function knowing all the potentials. In this paper, we focus on CRFs where the computational cost of instantiating the potentials is orders of magnitude higher than MAP inference. This is often the case in semantic image segmentation, where most potentials are instantiated by slow classifiers fed with costly features. We introduce Active MAP inference 1) to on-the-fly select a subset of potentials to be instantiated in the energy function, leaving the rest of the parameters of the potentials unknown, and 2) to estimate the MAP labeling from such incomplete energy function. Results for semantic segmentation benchmarks, namely PASCAL VOC 2010 [5] and MSRC-21 [19], show that Active MAP inference achieves similar levels of accuracy but with major efficiency gains.
Address (down) Sydney; Australia; December 2013
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN 1550-5499 ISBN Medium
Area Expedition Conference ICCV
Notes ADAS; 600.057 Approved no
Call Number ADAS @ adas @ RBN2013 Serial 2377
Permanent link to this record
 
 
Author Cesar Isaza; Joaquin Salas; Bogdan Raducanu
Title Toward the Detection of Urban Infrastructures Edge Shadows Type Conference Article
Year 2010 Publication 12th International Conference on Advanced Concepts for Intelligent Vision Systems Abbreviated Journal
Volume 6474 Issue I Pages 30–37
Keywords
Abstract In this paper, we propose a novel technique to detect the shadows cast by urban infrastructure, such as buildings, billboards, and traffic signs, using a sequence of images taken from a fixed camera. In our approach, we compute two different background models in parallel: one for the edges and one for the reflected light intensity. An algorithm is proposed to train the system to distinguish between moving edges in general and edges that belong to static objects, creating an edge background model. Then, during operation, a background intensity model allow us to separate between moving and static objects. Those edges included in the moving objects and those that belong to the edge background model are subtracted from the current image edges. The remaining edges are the ones cast by urban infrastructure. Our method is tested on a typical crossroad scene and the results show that the approach is sound and promising.
Address (down) Sydney, Australia
Corporate Author Thesis
Publisher Springer Berlin Heidelberg Place of Publication Editor eds. Blanc–Talon et al
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title LNCS
Series Volume Series Issue Edition
ISSN 0302-9743 ISBN 978-3-642-17687-6 Medium
Area Expedition Conference ACIVS
Notes OR;MV Approved no
Call Number BCNPCL @ bcnpcl @ ISR2010 Serial 1458
Permanent link to this record
 
 
Author Fadi Dornaika; Bogdan Raducanu
Title Recognizing Facial Expressions in Videos Using a Facial Action Analysis-Synthesis Scheme Type Miscellaneous
Year 2006 Publication International Conference on Advanced Video and Signal Based Surveillance, (AVSS 2006), ISBN: 0–7695–2688–8 Abbreviated Journal
Volume Issue Pages
Keywords
Abstract
Address (down) Sydney (Australia)
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 OR;MV Approved no
Call Number BCNPCL @ bcnpcl @ DoR2006 Serial 799
Permanent link to this record
 
 
Author Fares Alnajar; Theo Gevers; Roberto Valenti; Sennay Ghebreab
Title Calibration-free Gaze Estimation using Human Gaze Patterns Type Conference Article
Year 2013 Publication 15th IEEE International Conference on Computer Vision Abbreviated Journal
Volume Issue Pages 137-144
Keywords
Abstract We present a novel method to auto-calibrate gaze estimators based on gaze patterns obtained from other viewers. Our method is based on the observation that the gaze patterns of humans are indicative of where a new viewer will look at [12]. When a new viewer is looking at a stimulus, we first estimate a topology of gaze points (initial gaze points). Next, these points are transformed so that they match the gaze patterns of other humans to find the correct gaze points. In a flexible uncalibrated setup with a web camera and no chin rest, the proposed method was tested on ten subjects and ten images. The method estimates the gaze points after looking at a stimulus for a few seconds with an average accuracy of 4.3 im. Although the reported performance is lower than what could be achieved with dedicated hardware or calibrated setup, the proposed method still provides a sufficient accuracy to trace the viewer attention. This is promising considering the fact that auto-calibration is done in a flexible setup , without the use of a chin rest, and based only on a few seconds of gaze initialization data. To the best of our knowledge, this is the first work to use human gaze patterns in order to auto-calibrate gaze estimators.
Address (down) Sydney
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 ICCV
Notes ALTRES;ISE Approved no
Call Number Admin @ si @ AGV2013 Serial 2365
Permanent link to this record
 
 
Author Hamdi Dibeklioglu; Albert Ali Salah; Theo Gevers
Title Like Father, Like Son: Facial Expression Dynamics for Kinship Verification Type Conference Article
Year 2013 Publication 15th IEEE International Conference on Computer Vision Abbreviated Journal
Volume Issue Pages 1497-1504
Keywords
Abstract Kinship verification from facial appearance is a difficult problem. This paper explores the possibility of employing facial expression dynamics in this problem. By using features that describe facial dynamics and spatio-temporal appearance over smile expressions, we show that it is possible to improve the state of the art in this problem, and verify that it is indeed possible to recognize kinship by resemblance of facial expressions. The proposed method is tested on different kin relationships. On the average, 72.89% verification accuracy is achieved on spontaneous smiles.
Address (down) Sydney
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 ICCV
Notes ALTRES;ISE Approved no
Call Number Admin @ si @ DSG2013 Serial 2366
Permanent link to this record
 
 
Author V. Valev; Petia Radeva
Title Constructing Quantitative Non-Reducible Descriptors. Type Miscellaneous
Year 1995 Publication 9th Scandinavian Conference on Artificial Intelligence Abbreviated Journal
Volume Issue Pages
Keywords
Abstract
Address (down) Sweden
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 Approved no
Call Number BCNPCL @ bcnpcl @ VaR1995b Serial 140
Permanent link to this record
 
 
Author Victor Ponce; Hugo Jair Escalante; Sergio Escalera; Xavier Baro
Title Gesture and Action Recognition by Evolved Dynamic Subgestures Type Conference Article
Year 2015 Publication 26th British Machine Vision Conference Abbreviated Journal
Volume Issue Pages 129.1-129.13
Keywords
Abstract This paper introduces a framework for gesture and action recognition based on the evolution of temporal gesture primitives, or subgestures. Our work is inspired on the principle of producing genetic variations within a population of gesture subsequences, with the goal of obtaining a set of gesture units that enhance the generalization capability of standard gesture recognition approaches. In our context, gesture primitives are evolved over time using dynamic programming and generative models in order to recognize complex actions. In few generations, the proposed subgesture-based representation
of actions and gestures outperforms the state of the art results on the MSRDaily3D and MSRAction3D datasets.
Address (down) Swansea; uk; September 2015
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 HuPBA;MV Approved no
Call Number Admin @ si @ PEE2015 Serial 2657
Permanent link to this record