toggle visibility Search & Display Options

Select All    Deselect All
 |   | 
Details
  Records Links
Author Lei Kang; Juan Ignacio Toledo; Pau Riba; Mauricio Villegas; Alicia Fornes; Marçal Rusiñol edit   pdf
url  openurl
  Title Convolve, Attend and Spell: An Attention-based Sequence-to-Sequence Model for Handwritten Word Recognition Type Conference Article
  Year 2018 Publication 40th German Conference on Pattern Recognition Abbreviated Journal  
  Volume Issue Pages 459-472  
  Keywords  
  Abstract This paper proposes Convolve, Attend and Spell, an attention based sequence-to-sequence model for handwritten word recognition. The proposed architecture has three main parts: an encoder, consisting of a CNN and a bi-directional GRU, an attention mechanism devoted to focus on the pertinent features and a decoder formed by a one-directional GRU, able to spell the corresponding word, character by character. Compared with the recent state-of-the-art, our model achieves competitive results on the IAM dataset without needing any pre-processing step, predefined lexicon nor language model. Code and additional results are available in https://github.com/omni-us/research-seq2seq-HTR.  
  Address Stuttgart; Germany; October 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 (up) Medium  
  Area Expedition Conference GCPR  
  Notes DAG; 600.097; 603.057; 302.065; 601.302; 600.084; 600.121; 600.129 Approved no  
  Call Number Admin @ si @ KTR2018 Serial 3167  
Permanent link to this record
 

 
Author Pau Riba; Andreas Fischer; Josep Llados; Alicia Fornes edit   pdf
doi  openurl
  Title Learning Graph Distances with Message Passing Neural Networks Type Conference Article
  Year 2018 Publication 24th International Conference on Pattern Recognition Abbreviated Journal  
  Volume Issue Pages 2239-2244  
  Keywords ★Best Paper Award★  
  Abstract Graph representations have been widely used in pattern recognition thanks to their powerful representation formalism and rich theoretical background. A number of error-tolerant graph matching algorithms such as graph edit distance have been proposed for computing a distance between two labelled graphs. However, they typically suffer from a high
computational complexity, which makes it difficult to apply
these matching algorithms in a real scenario. In this paper, we propose an efficient graph distance based on the emerging field of geometric deep learning. Our method employs a message passing neural network to capture the graph structure and learns a metric with a siamese network approach. The performance of the proposed graph distance is validated in two application cases, graph classification and graph retrieval of handwritten words, and shows a promising performance when compared with
(approximate) graph edit distance benchmarks.
 
  Address Beijing; China; August 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 (up) Medium  
  Area Expedition Conference ICPR  
  Notes DAG; 600.097; 603.057; 601.302; 600.121 Approved no  
  Call Number Admin @ si @ RFL2018 Serial 3168  
Permanent link to this record
 

 
Author Jialuo Chen; Pau Riba; Alicia Fornes; Juan Mas; Josep Llados; Joana Maria Pujadas-Mora edit   pdf
doi  openurl
  Title Word-Hunter: A Gamesourcing Experience to Validate the Transcription of Historical Manuscripts Type Conference Article
  Year 2018 Publication 16th International Conference on Frontiers in Handwriting Recognition Abbreviated Journal  
  Volume Issue Pages 528-533  
  Keywords Crowdsourcing; Gamification; Handwritten documents; Performance evaluation  
  Abstract Nowadays, there are still many handwritten historical documents in archives waiting to be transcribed and indexed. Since manual transcription is tedious and time consuming, the automatic transcription seems the path to follow. However, the performance of current handwriting recognition techniques is not perfect, so a manual validation is mandatory. Crowdsourcing is a good strategy for manual validation, however it is a tedious task. In this paper we analyze experiences based in gamification
in order to propose and design a gamesourcing framework that increases the interest of users. Then, we describe and analyze our experience when validating the automatic transcription using the gamesourcing application. Moreover, thanks to the combination of clustering and handwriting recognition techniques, we can speed up the validation while maintaining the performance.
 
  Address Niagara Falls, USA; August 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 (up) Medium  
  Area Expedition Conference ICFHR  
  Notes DAG; 600.097; 603.057; 600.121 Approved no  
  Call Number Admin @ si @ CRF2018 Serial 3169  
Permanent link to this record
 

 
Author Manuel Carbonell; Mauricio Villegas; Alicia Fornes; Josep Llados edit   pdf
openurl 
  Title Joint Recognition of Handwritten Text and Named Entities with a Neural End-to-end Model Type Conference Article
  Year 2018 Publication 13th IAPR International Workshop on Document Analysis Systems Abbreviated Journal  
  Volume Issue Pages 399-404  
  Keywords Named entity recognition; Handwritten Text Recognition; neural networks  
  Abstract When extracting information from handwritten documents, text transcription and named entity recognition are usually faced as separate subsequent tasks. This has the disadvantage that errors in the first module affect heavily the
performance of the second module. In this work we propose to do both tasks jointly, using a single neural network with a common architecture used for plain text recognition. Experimentally, the work has been tested on a collection of historical marriage records. Results of experiments are presented to show the effect on the performance for different
configurations: different ways of encoding the information, doing or not transfer learning and processing at text line or multi-line region level. The results are comparable to state of the art reported in the ICDAR 2017 Information Extraction competition, even though the proposed technique does not use any dictionaries, language modeling or post processing.
 
  Address Vienna; Austria; April 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 (up) Medium  
  Area Expedition Conference DAS  
  Notes DAG; 600.097; 603.057; 601.311; 600.121 Approved no  
  Call Number Admin @ si @ CVF2018 Serial 3170  
Permanent link to this record
 

 
Author Katerine Diaz; Jesus Martinez del Rincon; Marçal Rusiñol; Aura Hernandez-Sabate edit   pdf
doi  openurl
  Title Feature Extraction by Using Dual-Generalized Discriminative Common Vectors Type Journal Article
  Year 2019 Publication Journal of Mathematical Imaging and Vision Abbreviated Journal JMIV  
  Volume 61 Issue 3 Pages 331-351  
  Keywords Online feature extraction; Generalized discriminative common vectors; Dual learning; Incremental learning; Decremental learning  
  Abstract In this paper, a dual online subspace-based learning method called dual-generalized discriminative common vectors (Dual-GDCV) is presented. The method extends incremental GDCV by exploiting simultaneously both the concepts of incremental and decremental learning for supervised feature extraction and classification. Our methodology is able to update the feature representation space without recalculating the full projection or accessing the previously processed training data. It allows both adding information and removing unnecessary data from a knowledge base in an efficient way, while retaining the previously acquired knowledge. The proposed method has been theoretically proved and empirically validated in six standard face recognition and classification datasets, under two scenarios: (1) removing and adding samples of existent classes, and (2) removing and adding new classes to a classification problem. Results show a considerable computational gain without compromising the accuracy of the model in comparison with both batch methodologies and other state-of-art adaptive methods.  
  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 (up) Medium  
  Area Expedition Conference  
  Notes DAG; ADAS; 600.084; 600.118; 600.121; 600.129;IAM Approved no  
  Call Number Admin @ si @ DRR2019 Serial 3172  
Permanent link to this record
 

 
Author Raul Gomez; Lluis Gomez; Jaume Gibert; Dimosthenis Karatzas edit   pdf
url  openurl
  Title Learning from# Barcelona Instagram data what Locals and Tourists post about its Neighbourhoods Type Conference Article
  Year 2018 Publication 15th European Conference on Computer Vision Workshops Abbreviated Journal  
  Volume 11134 Issue Pages 530-544  
  Keywords  
  Abstract Massive tourism is becoming a big problem for some cities, such as Barcelona, due to its concentration in some neighborhoods. In this work we gather Instagram data related to Barcelona consisting on images-captions pairs and, using the text as a supervisory signal, we learn relations between images, words and neighborhoods. Our goal is to learn which visual elements appear in photos when people is posting about each neighborhood. We perform a language separate treatment of the data and show that it can be extrapolated to a tourists and locals separate analysis, and that tourism is reflected in Social Media at a neighborhood level. The presented pipeline allows analyzing the differences between the images that tourists and locals associate to the different neighborhoods. The proposed method, which can be extended to other cities or subjects, proves that Instagram data can be used to train multi-modal (image and text) machine learning models that are useful to analyze publications about a city at a neighborhood level. We publish the collected dataset, InstaBarcelona and the code used in the analysis.  
  Address Munich; Alemanya; September 2018  
  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 (up) Medium  
  Area Expedition Conference ECCVW  
  Notes DAG; 600.129; 601.338; 600.121 Approved no  
  Call Number Admin @ si @ GGG2018b Serial 3176  
Permanent link to this record
 

 
Author Y. Patel; Lluis Gomez; Raul Gomez; Marçal Rusiñol; Dimosthenis Karatzas; C.V. Jawahar edit  openurl
  Title TextTopicNet-Self-Supervised Learning of Visual Features Through Embedding Images on Semantic Text Spaces Type Miscellaneous
  Year 2018 Publication Arxiv Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract The immense success of deep learning based methods in computer vision heavily relies on large scale training datasets. These richly annotated datasets help the network learn discriminative visual features. Collecting and annotating such datasets requires a tremendous amount of human effort and annotations are limited to popular set of classes. As an alternative, learning visual features by designing auxiliary tasks which make use of freely available self-supervision has become increasingly popular in the computer vision community.
In this paper, we put forward an idea to take advantage of multi-modal context to provide self-supervision for the training of computer vision algorithms. We show that adequate visual features can be learned efficiently by training a CNN to predict the semantic textual context in which a particular image is more probable to appear as an illustration. More specifically we use popular text embedding techniques to provide the self-supervision for the training of deep CNN.
 
  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 (up) Medium  
  Area Expedition Conference  
  Notes DAG; 600.084; 601.338; 600.121 Approved no  
  Call Number Admin @ si @ PGG2018 Serial 3177  
Permanent link to this record
 

 
Author Anguelos Nicolaou; Sounak Dey; V.Christlein; A.Maier; Dimosthenis Karatzas edit   pdf
url  openurl
  Title Non-deterministic Behavior of Ranking-based Metrics when Evaluating Embeddings Type Conference Article
  Year 2018 Publication International Workshop on Reproducible Research in Pattern Recognition Abbreviated Journal  
  Volume 11455 Issue Pages 71-82  
  Keywords  
  Abstract Embedding data into vector spaces is a very popular strategy of pattern recognition methods. When distances between embeddings are quantized, performance metrics become ambiguous. In this paper, we present an analysis of the ambiguity quantized distances introduce and provide bounds on the effect. We demonstrate that it can have a measurable effect in empirical data in state-of-the-art systems. We also approach the phenomenon from a computer security perspective and demonstrate how someone being evaluated by a third party can exploit this ambiguity and greatly outperform a random predictor without even access to the input data. We also suggest a simple solution making the performance metrics, which rely on ranking, totally deterministic and impervious to such exploits.  
  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 (up) Medium  
  Area Expedition Conference  
  Notes DAG; 600.121; 600.129 Approved no  
  Call Number Admin @ si @ NDC2018 Serial 3178  
Permanent link to this record
 

 
Author Dena Bazazian; Dimosthenis Karatzas; Andrew Bagdanov edit   pdf
doi  openurl
  Title Word Spotting in Scene Images based on Character Recognition Type Conference Article
  Year 2018 Publication IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops Abbreviated Journal  
  Volume Issue Pages 1872-1874  
  Keywords  
  Abstract In this paper we address the problem of unconstrained Word Spotting in scene images. We train a Fully Convolutional Network to produce heatmaps of all the character classes. Then, we employ the Text Proposals approach and, via a rectangle classifier, detect the most likely rectangle for each query word based on the character attribute maps. We evaluate the proposed method on ICDAR2015 and show that it is capable of identifying and recognizing query words in natural scene images.  
  Address Salt Lake City; USA; June 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 (up) Medium  
  Area Expedition Conference CVPRW  
  Notes DAG; 600.129; 600.121 Approved no  
  Call Number BKB2018a Serial 3179  
Permanent link to this record
 

 
Author Marçal Rusiñol; Dimosthenis Karatzas; Josep Llados edit  doi
openurl 
  Title Automatic Verification of Properly Signed Multi-page Document Images Type Conference Article
  Year 2015 Publication Proceedings of the Eleventh International Symposium on Visual Computing Abbreviated Journal  
  Volume 9475 Issue Pages 327-336  
  Keywords Document Image; Manual Inspection; Signature Verification; Rejection Criterion; Document Flow  
  Abstract In this paper we present an industrial application for the automatic screening of incoming multi-page documents in a banking workflow aimed at determining whether these documents are properly signed or not. The proposed method is divided in three main steps. First individual pages are classified in order to identify the pages that should contain a signature. In a second step, we segment within those key pages the location where the signatures should appear. The last step checks whether the signatures are present or not. Our method is tested in a real large-scale environment and we report the results when checking two different types of real multi-page contracts, having in total more than 14,500 pages.  
  Address Las Vegas, Nevada, USA; December 2015  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title LNCS  
  Series Volume 9475 Series Issue Edition  
  ISSN ISBN (up) Medium  
  Area Expedition Conference ISVC  
  Notes DAG; 600.077 Approved no  
  Call Number Admin @ si @ Serial 3189  
Permanent link to this record
Select All    Deselect All
 |   | 
Details

Save Citations:
Export Records: