toggle visibility Search & Display Options

Select All    Deselect All
 |   | 
Details
  Records Links
Author Jaume Gibert; Ernest Valveny; Horst Bunke edit  doi
isbn  openurl
  Title Dimensionality Reduction for Graph of Words Embedding Type Conference Article
  Year 2011 Publication 8th IAPR-TC-15 International Workshop. Graph-Based Representations in Pattern Recognition Abbreviated Journal  
  Volume 6658 Issue Pages 22-31  
  Keywords  
  Abstract The Graph of Words Embedding consists in mapping every graph of a given dataset to a feature vector by counting unary and binary relations between node attributes of the graph. While it shows good properties in classification problems, it suffers from high dimensionality and sparsity. These two issues are addressed in this article. Two well-known techniques for dimensionality reduction, kernel principal component analysis (kPCA) and independent component analysis (ICA), are applied to the embedded graphs. We discuss their performance compared to the classification of the original vectors on three different public databases of graphs.  
  Address Münster, Germany  
  Corporate Author Thesis  
  Publisher Place of Publication Editor Xiaoyi Jiang; Miquel Ferrer; Andrea Torsello  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title LNCS  
  Series Volume Series Issue Edition  
  ISSN ISBN 978-3-642-20843-0 Medium  
  Area Expedition Conference (up) GbRPR  
  Notes DAG Approved no  
  Call Number Admin @ si @ GVB2011a Serial 1743  
Permanent link to this record
 

 
Author Pau Riba; Josep Llados; Alicia Fornes; Anjan Dutta edit   pdf
url  doi
isbn  openurl
  Title Large-scale Graph Indexing using Binary Embeddings of Node Contexts Type Conference Article
  Year 2015 Publication 10th IAPR-TC15 Workshop on Graph-based Representations in Pattern Recognition Abbreviated Journal  
  Volume 9069 Issue Pages 208-217  
  Keywords Graph matching; Graph indexing; Application in document analysis; Word spotting; Binary embedding  
  Abstract Graph-based representations are experiencing a growing usage in visual recognition and retrieval due to their representational power in front of classical appearance-based representations in terms of feature vectors. Retrieving a query graph from a large dataset of graphs has the drawback of the high computational complexity required to compare the query and the target graphs. The most important property for a large-scale retrieval is the search time complexity to be sub-linear in the number of database examples. In this paper we propose a fast indexation formalism for graph retrieval. A binary embedding is defined as hashing keys for graph nodes. Given a database of labeled graphs, graph nodes are complemented with vectors of attributes representing their local context. Hence, each attribute counts the length of a walk of order k originated in a vertex with label l. Each attribute vector is converted to a binary code applying a binary-valued hash function. Therefore, graph retrieval is formulated in terms of finding target graphs in the database whose nodes have a small Hamming distance from the query nodes, easily computed with bitwise logical operators. As an application example, we validate the performance of the proposed methods in a handwritten word spotting scenario in images of historical documents.  
  Address Beijing; China; May 2015  
  Corporate Author Thesis  
  Publisher Springer International Publishing Place of Publication Editor C.-L.Liu; B.Luo; W.G.Kropatsch; J.Cheng  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title LNCS  
  Series Volume Series Issue Edition  
  ISSN 0302-9743 ISBN 978-3-319-18223-0 Medium  
  Area Expedition Conference (up) GbRPR  
  Notes DAG; 600.061; 602.006; 600.077 Approved no  
  Call Number Admin @ si @ RLF2015a Serial 2618  
Permanent link to this record
 

 
Author Pau Riba; Josep Llados; Alicia Fornes edit   pdf
doi  openurl
  Title Error-tolerant coarse-to-fine matching model for hierarchical graphs Type Conference Article
  Year 2017 Publication 11th IAPR-TC-15 International Workshop on Graph-Based Representations in Pattern Recognition Abbreviated Journal  
  Volume 10310 Issue Pages 107-117  
  Keywords Graph matching; Hierarchical graph; Graph-based representation; Coarse-to-fine matching  
  Abstract Graph-based representations are effective tools to capture structural information from visual elements. However, retrieving a query graph from a large database of graphs implies a high computational complexity. Moreover, these representations are very sensitive to noise or small changes. In this work, a novel hierarchical graph representation is designed. Using graph clustering techniques adapted from graph-based social media analysis, we propose to generate a hierarchy able to deal with different levels of abstraction while keeping information about the topology. For the proposed representations, a coarse-to-fine matching method is defined. These approaches are validated using real scenarios such as classification of colour images and handwritten word spotting.  
  Address Anacapri; Italy; May 2017  
  Corporate Author Thesis  
  Publisher Springer International Publishing Place of Publication Editor Pasquale Foggia; Cheng-Lin Liu; Mario Vento  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference (up) GbRPR  
  Notes DAG; 600.097; 601.302; 600.121 Approved no  
  Call Number Admin @ si @ RLF2017a Serial 2951  
Permanent link to this record
 

 
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 Medium  
  Area Expedition Conference (up) 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 Salim Jouili; Salvatore Tabbone; Ernest Valveny edit   pdf
doi  isbn
openurl 
  Title Comparing Graph Similarity Measures for Graphical Recognition Type Book Chapter
  Year 2010 Publication Graphics Recognition. Achievements, Challenges, and Evolution. 8th International Workshop, GREC 2009. Selected Papers Abbreviated Journal  
  Volume 6020 Issue Pages 37-48  
  Keywords  
  Abstract In this paper we evaluate four graph distance measures. The analysis is performed for document retrieval tasks. For this aim, different kind of documents are used including line drawings (symbols), ancient documents (ornamental letters), shapes and trademark-logos. The experimental results show that the performance of each graph distance measure depends on the kind of data and the graph representation technique.  
  Address  
  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 978-3-642-13727-3 Medium  
  Area Expedition Conference (up) GREC  
  Notes DAG Approved no  
  Call Number Admin @ si @ JTV2010 Serial 2404  
Permanent link to this record
 

 
Author W. Liu; Josep Llados edit  openurl
  Title Graphics Recognition. Ten Years Review and Future Perspectives Type Book Whole
  Year 2006 Publication 6th International Workshop Abbreviated Journal  
  Volume 3926 Issue Pages  
  Keywords  
  Abstract  
  Address Hong Kong (China)  
  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 (up) GREC  
  Notes DAG Approved no  
  Call Number DAG @ dag @ LiL2006 Serial 800  
Permanent link to this record
 

 
Author Partha Pratim Roy; Eduard Vazquez; Josep Llados; Ramon Baldrich; Umapada Pal edit  openurl
  Title A System to Retrieve Text/Symbols from Color Maps using Connected Component and Skeleton Analysis Type Conference Article
  Year 2007 Publication Seventh IAPR International Workshop on Graphics Recognition Abbreviated Journal  
  Volume Issue Pages 79–78  
  Keywords  
  Abstract  
  Address Curitiba (Brasil)  
  Corporate Author Thesis  
  Publisher Place of Publication Editor J. Llados, W. Liu, J.M. Ogier  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference (up) GREC  
  Notes CAT; DAG;CIC Approved no  
  Call Number CAT @ cat @ RVL2007 Serial 836  
Permanent link to this record
 

 
Author Mathieu Nicolas Delalandre; Tony Pridmore; Ernest Valveny; Eric Trupin; Herve Locteau edit  openurl
  Title Building Synthetic Graphical Documents for Performance Evaluation Type Conference Article
  Year 2007 Publication Seventh IAPR International Workshop on Graphics Recognition Abbreviated Journal  
  Volume Issue Pages 84–87  
  Keywords  
  Abstract  
  Address Curitiba (Brasil)  
  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 (up) GREC  
  Notes DAG Approved no  
  Call Number DAG @ dag @ DPV2007 Serial 840  
Permanent link to this record
 

 
Author Mathieu Nicolas Delalandre; Jean-Marc Ogier; Josep Llados edit  openurl
  Title A Fast System for the Retrieval of Ornamental Letter Image Type Conference Article
  Year 2007 Publication Seventh IAPR International Workshop on Graphics Recognition Abbreviated Journal  
  Volume Issue Pages 51–54  
  Keywords  
  Abstract  
  Address Curitiba (Brasil)  
  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 (up) GREC  
  Notes DAG Approved no  
  Call Number DAG @ dag @ DOL2007 Serial 841  
Permanent link to this record
 

 
Author Joan Mas; J.A. Jorge; Gemma Sanchez; Josep Llados edit  openurl
  Title Describing and Parising Hand-Drawn Sketches using a Syntactic Approach Type Conference Article
  Year 2007 Publication Seventh IAPR International Workshop on Graphics Recognition Abbreviated Journal  
  Volume Issue Pages 61–62  
  Keywords  
  Abstract  
  Address Curitiba (Brasil)  
  Corporate Author Thesis  
  Publisher Place of Publication Editor J. Llados, W. Liu, J.M. Ogier  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference (up) GREC  
  Notes DAG Approved no  
  Call Number DAG @ dag @ MJS2007 Serial 845  
Permanent link to this record
Select All    Deselect All
 |   | 
Details

Save Citations:
Export Records: