toggle visibility Search & Display Options

Select All    Deselect All
 |   | 
Details
  Records Links
Author V. Poulain d'Andecy; Emmanuel Hartmann; Marçal Rusiñol edit   pdf
doi  openurl
  Title Field Extraction by hybrid incremental and a-priori structural templates Type Conference Article
  Year 2018 Publication 13th IAPR International Workshop on Document Analysis Systems Abbreviated Journal  
  Volume Issue Pages 251 - 256  
  Keywords Layout Analysis; information extraction; incremental learning  
  Abstract In this paper, we present an incremental framework for extracting information fields from administrative documents. First, we demonstrate some limits of the existing state-of-the-art methods such as the delay of the system efficiency. This is a concern in industrial context when we have only few samples of each document class. Based on this analysis, we propose a hybrid system combining incremental learning by means of itf-df statistics and a-priori generic
models. We report in the experimental section our results obtained with a dataset of real invoices.
 
  Address Viena; 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 (up) ISBN Medium  
  Area Expedition Conference DAS  
  Notes DAG; 600.084; 600.129; 600.121 Approved no  
  Call Number Admin @ si @ PHR2018 Serial 3106  
Permanent link to this record
 

 
Author Lluis Gomez; Andres Mafla; Marçal Rusiñol; Dimosthenis Karatzas edit   pdf
url  openurl
  Title Single Shot Scene Text Retrieval Type Conference Article
  Year 2018 Publication 15th European Conference on Computer Vision Abbreviated Journal  
  Volume 11218 Issue Pages 728-744  
  Keywords Image retrieval; Scene text; Word spotting; Convolutional Neural Networks; Region Proposals Networks; PHOC  
  Abstract Textual information found in scene images provides high level semantic information about the image and its context and it can be leveraged for better scene understanding. In this paper we address the problem of scene text retrieval: given a text query, the system must return all images containing the queried text. The novelty of the proposed model consists in the usage of a single shot CNN architecture that predicts at the same time bounding boxes and a compact text representation of the words in them. In this way, the text based image retrieval task can be casted as a simple nearest neighbor search of the query text representation over the outputs of the CNN over the entire image
database. Our experiments demonstrate that the proposed architecture
outperforms previous state-of-the-art while it offers a significant increase
in processing speed.
 
  Address Munich; 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 (up) ISBN Medium  
  Area Expedition Conference ECCV  
  Notes DAG; 600.084; 601.338; 600.121; 600.129 Approved no  
  Call Number Admin @ si @ GMR2018 Serial 3143  
Permanent link to this record
 

 
Author Mohammed Al Rawi; Dimosthenis Karatzas edit   pdf
openurl 
  Title On the Labeling Correctness in Computer Vision Datasets Type Conference Article
  Year 2018 Publication Proceedings of the Workshop on Interactive Adaptive Learning, co-located with European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract Image datasets have heavily been used to build computer vision systems.
These datasets are either manually or automatically labeled, which is a
problem as both labeling methods are prone to errors. To investigate this problem, we use a majority voting ensemble that combines the results from several Convolutional Neural Networks (CNNs). Majority voting ensembles not only enhance the overall performance, but can also be used to estimate the confidence level of each sample. We also examined Softmax as another form to estimate posterior probability. We have designed various experiments with a range of different ensembles built from one or different, or temporal/snapshot CNNs, which have been trained multiple times stochastically. We analyzed CIFAR10, CIFAR100, EMNIST, and SVHN datasets and we found quite a few incorrect
labels, both in the training and testing sets. We also present detailed confidence analysis on these datasets and we found that the ensemble is better than the Softmax when used estimate the per-sample confidence. This work thus proposes an approach that can be used to scrutinize and verify the labeling of computer vision datasets, which can later be applied to weakly/semi-supervised learning. We propose a measure, based on the Odds-Ratio, to quantify how many of these incorrectly classified labels are actually incorrectly labeled and how many of these are confusing. The proposed methods are easily scalable to larger datasets, like ImageNet, LSUN and SUN, as each CNN instance is trained for 60 epochs; or even faster, by implementing a temporal (snapshot) ensemble.
 
  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 (up) ISBN Medium  
  Area Expedition Conference ECML-PKDDW  
  Notes DAG; 600.121; 600.129 Approved no  
  Call Number Admin @ si @ RaK2018 Serial 3144  
Permanent link to this record
 

 
Author Thanh Nam Le; Muhammad Muzzamil Luqman; Anjan Dutta; Pierre Heroux; Christophe Rigaud; Clement Guerin; Pasquale Foggia; Jean Christophe Burie; Jean Marc Ogier; Josep Llados; Sebastien Adam edit  url
openurl 
  Title Subgraph spotting in graph representations of comic book images Type Journal Article
  Year 2018 Publication Pattern Recognition Letters Abbreviated Journal PRL  
  Volume 112 Issue Pages 118-124  
  Keywords Attributed graph; Region adjacency graph; Graph matching; Graph isomorphism; Subgraph isomorphism; Subgraph spotting; Graph indexing; Graph retrieval; Query by example; Dataset and comic book images  
  Abstract Graph-based representations are the most powerful data structures for extracting, representing and preserving the structural information of underlying data. Subgraph spotting is an interesting research problem, especially for studying and investigating the structural information based content-based image retrieval (CBIR) and query by example (QBE) in image databases. In this paper we address the problem of lack of freely available ground-truthed datasets for subgraph spotting and present a new dataset for subgraph spotting in graph representations of comic book images (SSGCI) with its ground-truth and evaluation protocol. Experimental results of two state-of-the-art methods of subgraph spotting are presented on the new SSGCI dataset.  
  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 (up) ISBN Medium  
  Area Expedition Conference  
  Notes DAG; 600.097; 600.121 Approved no  
  Call Number Admin @ si @ LLD2018 Serial 3150  
Permanent link to this record
 

 
Author Sounak Dey; Anjan Dutta; Suman Ghosh; Ernest Valveny; Josep Llados edit   pdf
openurl 
  Title Aligning Salient Objects to Queries: A Multi-modal and Multi-object Image Retrieval Framework Type Conference Article
  Year 2018 Publication 14th Asian Conference on Computer Vision Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract In this paper we propose an approach for multi-modal image retrieval in multi-labelled images. A multi-modal deep network architecture is formulated to jointly model sketches and text as input query modalities into a common embedding space, which is then further aligned with the image feature space. Our architecture also relies on a salient object detection through a supervised LSTM-based visual attention model learned from convolutional features. Both the alignment between the queries and the image and the supervision of the attention on the images are obtained by generalizing the Hungarian Algorithm using different loss functions. This permits encoding the object-based features and its alignment with the query irrespective of the availability of the co-occurrence of different objects in the training set. We validate the performance of our approach on standard single/multi-object datasets, showing state-of-the art performance in every dataset.  
  Address Perth; Australia; December 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 (up) ISBN Medium  
  Area Expedition Conference ACCV  
  Notes DAG; 600.097; 600.121; 600.129 Approved no  
  Call Number Admin @ si @ DDG2018a Serial 3151  
Permanent link to this record
 

 
Author Sounak Dey; Anjan Dutta; Suman Ghosh; Ernest Valveny; Josep Llados; Umapada Pal edit   pdf
doi  openurl
  Title Learning Cross-Modal Deep Embeddings for Multi-Object Image Retrieval using Text and Sketch Type Conference Article
  Year 2018 Publication 24th International Conference on Pattern Recognition Abbreviated Journal  
  Volume Issue Pages 916 - 921  
  Keywords  
  Abstract In this work we introduce a cross modal image retrieval system that allows both text and sketch as input modalities for the query. A cross-modal deep network architecture is formulated to jointly model the sketch and text input modalities as well as the the image output modality, learning a common embedding between text and images and between sketches and images. In addition, an attention model is used to selectively focus the attention on the different objects of the image, allowing for retrieval with multiple objects in the query. Experiments show that the proposed method performs the best in both single and multiple object image retrieval in standard datasets.  
  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 (up) ISBN Medium  
  Area Expedition Conference ICPR  
  Notes DAG; 602.167; 602.168; 600.097; 600.084; 600.121; 600.129 Approved no  
  Call Number Admin @ si @ DDG2018b Serial 3152  
Permanent link to this record
 

 
Author Fernando Vilariño; Dimosthenis Karatzas; Alberto Valcarce edit  openurl
  Title The Library Living Lab Barcelona: A participative approach to technology as an enabling factor for innovation in cultural spaces Type Journal
  Year 2018 Publication Technology Innovation Management Review Abbreviated Journal  
  Volume Issue Pages  
  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 (up) ISBN Medium  
  Area Expedition Conference  
  Notes DAG; MV; 600.097; 600.121; 600.129;SIAI Approved no  
  Call Number Admin @ si @ VKV2018a Serial 3153  
Permanent link to this record
 

 
Author Fernando Vilariño; Dimosthenis Karatzas; Alberto Valcarce edit  openurl
  Title Libraries as New Innovation Hubs: The Library Living Lab Type Conference Article
  Year 2018 Publication 30th ISPIM Innovation Conference Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract Libraries are in deep transformation both in EU and around the world, and they are thriving within a great window of opportunity for innovation. In this paper, we show how the Library Living Lab in Barcelona participated of this changing scenario and contributed to create the Bibliolab program, where more than 200 public libraries give voice to their users in a global user-centric innovation initiative, using technology as enabling factor. The Library Living Lab is a real 4-helix implementation where Universities, Research Centers, Public Administration, Companies and the Neighbors are joint together to explore how technology transforms the cultural experience of people. This case is an example of scalability and provides reference tools for policy making, sustainability, user engage methodologies and governance. We provide specific examples of new prototypes and services that help to understand how to redefine the role of the Library as a real hub for social innovation.  
  Address Stockholm; May 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 (up) ISBN Medium  
  Area Expedition Conference ISPIM  
  Notes DAG; MV; 600.097; 600.121; 600.129;SIAI Approved no  
  Call Number Admin @ si @ VKV2018b Serial 3154  
Permanent link to this record
 

 
Author Juan Ignacio Toledo; Manuel Carbonell; Alicia Fornes; Josep Llados edit  url
openurl 
  Title Information Extraction from Historical Handwritten Document Images with a Context-aware Neural Model Type Journal Article
  Year 2019 Publication Pattern Recognition Abbreviated Journal PR  
  Volume 86 Issue Pages 27-36  
  Keywords Document image analysis; Handwritten documents; Named entity recognition; Deep neural networks  
  Abstract Many historical manuscripts that hold trustworthy memories of the past societies contain information organized in a structured layout (e.g. census, birth or marriage records). The precious information stored in these documents cannot be effectively used nor accessed without costly annotation efforts. The transcription driven by the semantic categories of words is crucial for the subsequent access. In this paper we describe an approach to extract information from structured historical handwritten text images and build a knowledge representation for the extraction of meaning out of historical data. The method extracts information, such as named entities, without the need of an intermediate transcription step, thanks to the incorporation of context information through language models. Our system has two variants, the first one is based on bigrams, whereas the second one is based on recurrent neural networks. Concretely, our second architecture integrates a Convolutional Neural Network to model visual information from word images together with a Bidirecitonal Long Short Term Memory network to model the relation among the words. This integrated sequential approach is able to extract more information than just the semantic category (e.g. a semantic category can be associated to a person in a record). Our system is generic, it deals with out-of-vocabulary words by design, and it can be applied to structured handwritten texts from different domains. The method has been validated with the ICDAR IEHHR competition protocol, outperforming the existing approaches.  
  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 (up) ISBN Medium  
  Area Expedition Conference  
  Notes DAG; 600.097; 601.311; 603.057; 600.084; 600.140; 600.121 Approved no  
  Call Number Admin @ si @ TCF2019 Serial 3166  
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 (up) ISBN 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
Select All    Deselect All
 |   | 
Details

Save Citations:
Export Records: