toggle visibility Search & Display Options

Select All    Deselect All
 |   | 
Details
  Records Links
Author (down) Ruben Tito; Dimosthenis Karatzas; Ernest Valveny edit   pdf
url  openurl
  Title Document Collection Visual Question Answering Type Conference Article
  Year 2021 Publication 16th International Conference on Document Analysis and Recognition Abbreviated Journal  
  Volume 12822 Issue Pages 778-792  
  Keywords Document collection; Visual Question Answering  
  Abstract Current tasks and methods in Document Understanding aims to process documents as single elements. However, documents are usually organized in collections (historical records, purchase invoices), that provide context useful for their interpretation. To address this problem, we introduce Document Collection Visual Question Answering (DocCVQA) a new dataset and related task, where questions are posed over a whole collection of document images and the goal is not only to provide the answer to the given question, but also to retrieve the set of documents that contain the information needed to infer the answer. Along with the dataset we propose a new evaluation metric and baselines which provide further insights to the new dataset and task.  
  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 ICDAR  
  Notes DAG; 600.121 Approved no  
  Call Number Admin @ si @ TKV2021 Serial 3622  
Permanent link to this record
 

 
Author (down) Ruben Tito; Dimosthenis Karatzas; Ernest Valveny edit   pdf
doi  openurl
  Title Hierarchical multimodal transformers for Multi-Page DocVQA Type Journal Article
  Year 2023 Publication Pattern Recognition Abbreviated Journal PR  
  Volume 144 Issue Pages 109834  
  Keywords  
  Abstract Document Visual Question Answering (DocVQA) refers to the task of answering questions from document images. Existing work on DocVQA only considers single-page documents. However, in real scenarios documents are mostly composed of multiple pages that should be processed altogether. In this work we extend DocVQA to the multi-page scenario. For that, we first create a new dataset, MP-DocVQA, where questions are posed over multi-page documents instead of single pages. Second, we propose a new hierarchical method, Hi-VT5, based on the T5 architecture, that overcomes the limitations of current methods to process long multi-page documents. The proposed method is based on a hierarchical transformer architecture where the encoder summarizes the most relevant information of every page and then, the decoder takes this summarized information to generate the final answer. Through extensive experimentation, we demonstrate that our method is able, in a single stage, to answer the questions and provide the page that contains the relevant information to find the answer, which can be used as a kind of explainability measure.  
  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 ISSN 0031-3203 ISBN Medium  
  Area Expedition Conference  
  Notes DAG; 600.155; 600.121 Approved no  
  Call Number Admin @ si @ TKV2023 Serial 3825  
Permanent link to this record
 

 
Author (down) Ruben Tito; Dimosthenis Karatzas; Ernest Valveny edit   pdf
url  openurl
  Title Hierarchical multimodal transformers for Multipage DocVQA Type Journal Article
  Year 2023 Publication Pattern Recognition Abbreviated Journal PR  
  Volume 144 Issue 109834 Pages  
  Keywords  
  Abstract Existing work on DocVQA only considers single-page documents. However, in real applications documents are mostly composed of multiple pages that should be processed altogether. In this work, we propose a new multimodal hierarchical method Hi-VT5, that overcomes the limitations of current methods to process long multipage documents. In contrast to previous hierarchical methods that focus on different semantic granularity (He et al., 2021) or different subtasks (Zhou et al., 2022) used in image classification. Our method is a hierarchical transformer architecture where the encoder learns to summarize the most relevant information of every page and then, the decoder uses this summarized representation to generate the final answer, following a bottom-up approach. Moreover, due to the lack of multipage DocVQA datasets, we also introduce MP-DocVQA, an extension of SP-DocVQA where questions are posed over multipage documents instead of single pages. Through extensive experimentation, we demonstrate that Hi-VT5 is able, in a single stage, to answer the questions and provide the page that contains the answer, which can be used as a kind of explainability measure.  
  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 DAG Approved no  
  Call Number Admin @ si @ TKV2023 Serial 3836  
Permanent link to this record
 

 
Author (down) Ruben Perez Tito edit  isbn
openurl 
  Title Exploring the role of Text in Visual Question Answering on Natural Scenes and Documents Type Book Whole
  Year 2023 Publication PhD Thesis, Universitat Autonoma de Barcelona-CVC Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract Visual Question Answering (VQA) is the task where given an image and a natural language question, the objective is to generate a natural language answer. At the intersection between computer vision and natural language processing, this task can be seen as a measure of image understanding capabilities, as it requires to reason about objects, actions, colors, positions, the relations between the different elements as well as commonsense reasoning, world knowledge, arithmetic skills and natural language understanding. However, even though the text present in the images conveys important semantically rich information that is explicit and not available in any other form, most VQA methods remained illiterate, largely
ignoring the text despite its potential significance. In this thesis, we set out on a journey to bring reading capabilities to computer vision models applied to the VQA task, creating new datasets and methods that can read, reason and integrate the text with other visual cues in natural scene images and documents.
In Chapter 3, we address the combination of scene text with visual information to fully understand all the nuances of natural scene images. To achieve this objective, we define a new sub-task of VQA that requires reading the text in the image, and highlight the limitations of the current methods. In addition, we propose a new architecture that integrates both modalities and jointly reasons about textual and visual features. In Chapter 5, we shift the domain of VQA with reading capabilities and apply it on scanned industry document images, providing a high-level end-purpose perspective to Document Understanding, which has been
primarily focused on digitizing the document’s contents and extracting key values without considering the ultimate purpose of the extracted information. For this, we create a dataset which requires methods to reason about the unique and challenging elements of documents, such as text, images, tables, graphs and complex layouts, to provide accurate answers in natural language. However, we observed that explicit visual features provide a slight contribution in the overall performance, since the main information is usually conveyed within the text and its position. In consequence, in Chapter 6, we propose VQA on infographic images, seeking for document images with more visually rich elements that require to fully exploit visual information in order to answer the questions. We show the performance gap of
different methods when used over industry scanned and infographic images, and propose a new method that integrates the visual features in early stages, which allows the transformer architecture to exploit the visual features during the self-attention operation. Instead, in Chapter 7, we apply VQA on a big collection of single-page documents, where the methods must find which documents are relevant to answer the question, and provide the answer itself. Finally, in Chapter 8, mimicking real-world application problems where systems must process documents with multiple pages, we address the multipage document visual question answering task. We demonstrate the limitations of existing methods, including models specifically designed to process long sequences. To overcome these limitations, we propose
a hierarchical architecture that can process long documents, answer questions, and provide the index of the page where the information to answer the question is located as an explainability measure.
 
  Address  
  Corporate Author Thesis Ph.D. thesis  
  Publisher IMPRIMA Place of Publication Editor Ernest Valveny  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN 978-84-124793-5-5 Medium  
  Area Expedition Conference  
  Notes DAG Approved no  
  Call Number Admin @ si @ Per2023 Serial 3967  
Permanent link to this record
 

 
Author (down) Robert Benavente; Gemma Sanchez; Ramon Baldrich; Maria Vanrell; Josep Llados edit  openurl
  Title Normalized colour segmentation for human appearance description. Type Conference Article
  Year 2000 Publication 15 th International Conference on Pattern Recognition Abbreviated Journal  
  Volume 3 Issue Pages 637-641  
  Keywords  
  Abstract  
  Address Barcelona.  
  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 ICPR  
  Notes DAG;CIC Approved no  
  Call Number CAT @ cat @ BSB2000 Serial 223  
Permanent link to this record
 

 
Author (down) Robert Benavente; Ernest Valveny; Jaume Garcia; Agata Lapedriza; Miquel Ferrer; Gemma Sanchez edit  openurl
  Title Una experiencia de adaptacion al EEES de las asignaturas de programacion en Ingenieria Informatica Type Miscellaneous
  Year 2008 Publication V Congreso Iberoamericano de Docencia Universitaria, pp. 213–216 Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract  
  Address Valencia  
  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;DAG;CIC;MV Approved no  
  Call Number BCNPCL @ bcnpcl @ BVG2008 Serial 1031  
Permanent link to this record
 

 
Author (down) Ricardo Toledo; Ramon Baldrich; Ernest Valveny; Petia Radeva edit  openurl
  Title Enhancing snakes for vessel detection in angiography images. Type Miscellaneous
  Year 2002 Publication Proceedings of the Second IASTED International Conference Visualization, Imaging and Image Proceesing VIIP 2002: 139–144. 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 ISBN Medium  
  Area Expedition Conference  
  Notes MILAB;DAG;CIC;ADAS Approved no  
  Call Number BCNPCL @ bcnpcl @ TBV2002 Serial 300  
Permanent link to this record
 

 
Author (down) Ricard Coll; Alicia Fornes; Josep Llados edit  doi
isbn  openurl
  Title Graphological Analysis of Handwritten Text Documents for Human Resources Recruitment Type Conference Article
  Year 2009 Publication 10th International Conference on Document Analysis and Recognition Abbreviated Journal  
  Volume Issue Pages 1081–1085  
  Keywords  
  Abstract The use of graphology in recruitment processes has become a popular tool in many human resources companies. This paper presents a model that links features from handwritten images to a number of personality characteristics used to measure applicant aptitudes for the job in a particular hiring scenario. In particular we propose a model of measuring active personality and leadership of the writer. Graphological features that define such a profile are measured in terms of document and script attributes like layout configuration, letter size, shape, slant and skew angle of lines, etc. After the extraction, data is classified using a neural network. An experimental framework with real samples has been constructed to illustrate the performance of the approach.  
  Address Barcelona, Spain  
  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 1520-5363 ISBN 978-1-4244-4500-4 Medium  
  Area Expedition Conference ICDAR  
  Notes DAG Approved no  
  Call Number DAG @ dag @ CFL2009 Serial 1221  
Permanent link to this record
 

 
Author (down) Raul Gomez; Yahui Liu; Marco de Nadai; Dimosthenis Karatzas; Bruno Lepri; Nicu Sebe edit   pdf
url  openurl
  Title Retrieval Guided Unsupervised Multi-domain Image to Image Translation Type Conference Article
  Year 2020 Publication 28th ACM International Conference on Multimedia Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract Image to image translation aims to learn a mapping that transforms an image from one visual domain to another. Recent works assume that images descriptors can be disentangled into a domain-invariant content representation and a domain-specific style representation. Thus, translation models seek to preserve the content of source images while changing the style to a target visual domain. However, synthesizing new images is extremely challenging especially in multi-domain translations, as the network has to compose content and style to generate reliable and diverse images in multiple domains. In this paper we propose the use of an image retrieval system to assist the image-to-image translation task. First, we train an image-to-image translation model to map images to multiple domains. Then, we train an image retrieval model using real and generated images to find images similar to a query one in content but in a different domain. Finally, we exploit the image retrieval system to fine-tune the image-to-image translation model and generate higher quality images. Our experiments show the effectiveness of the proposed solution and highlight the contribution of the retrieval network, which can benefit from additional unlabeled data and help image-to-image translation models in the presence of scarce data.  
  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 ACM  
  Notes DAG; 600.121 Approved no  
  Call Number Admin @ si @ GLN2020 Serial 3497  
Permanent link to this record
 

 
Author (down) Raul Gomez; Lluis Gomez; Jaume Gibert; Dimosthenis Karatzas edit   pdf
url  openurl
  Title Learning to Learn from Web Data through Deep Semantic Embeddings Type Conference Article
  Year 2018 Publication 15th European Conference on Computer Vision Workshops Abbreviated Journal  
  Volume 11134 Issue Pages 514-529  
  Keywords  
  Abstract In this paper we propose to learn a multimodal image and text embedding from Web and Social Media data, aiming to leverage the semantic knowledge learnt in the text domain and transfer it to a visual model for semantic image retrieval. We demonstrate that the pipeline can learn from images with associated text without supervision and perform a thourough analysis of five different text embeddings in three different benchmarks. We show that the embeddings learnt with Web and Social Media data have competitive performances over supervised methods in the text based image retrieval task, and we clearly outperform state of the art in the MIRFlickr dataset when training in the target data. Further we demonstrate how semantic multimodal image retrieval can be performed using the learnt embeddings, going beyond classical instance-level retrieval problems. Finally, we present a new dataset, InstaCities1M, composed by Instagram images and their associated texts that can be used for fair comparison of image-text embeddings.  
  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 Medium  
  Area Expedition Conference ECCVW  
  Notes DAG; 600.129; 601.338; 600.121 Approved no  
  Call Number Admin @ si @ GGG2018a Serial 3175  
Permanent link to this record
Select All    Deselect All
 |   | 
Details

Save Citations:
Export Records: