|
Records |
Links |
|
Author |
Ruben Tito; Dimosthenis Karatzas; Ernest Valveny |
![download PDF file pdf](http://refbase.cvc.uab.es/img/file_PDF.gif)
![find record details (via OpenURL) openurl](http://refbase.cvc.uab.es/img/xref.gif)
|
|
Title |
Hierarchical multimodal transformers for Multipage DocVQA |
Type ![sorted by Type field, descending order (down)](http://refbase.cvc.uab.es/img/sort_desc.gif) |
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 |
Ayan Banerjee; Sanket Biswas; Josep Llados; Umapada Pal |
![goto web page url](http://refbase.cvc.uab.es/img/www.gif)
![find record details (via OpenURL) openurl](http://refbase.cvc.uab.es/img/xref.gif)
|
|
Title |
SemiDocSeg: Harnessing Semi-Supervised Learning for Document Layout Analysis |
Type ![sorted by Type field, descending order (down)](http://refbase.cvc.uab.es/img/sort_desc.gif) |
Journal Article |
|
Year |
2024 |
Publication |
International Journal on Document Analysis and Recognition |
Abbreviated Journal |
IJDAR |
|
|
Volume |
|
Issue |
|
Pages |
|
|
|
Keywords |
Document layout analysis; Semi-supervised learning; Co-Occurrence matrix; Instance segmentation; Swin transformer |
|
|
Abstract |
Document Layout Analysis (DLA) is the process of automatically identifying and categorizing the structural components (e.g. Text, Figure, Table, etc.) within a document to extract meaningful content and establish the page's layout structure. It is a crucial stage in document parsing, contributing to their comprehension. However, traditional DLA approaches often demand a significant volume of labeled training data, and the labor-intensive task of generating high-quality annotated training data poses a substantial challenge. In order to address this challenge, we proposed a semi-supervised setting that aims to perform learning on limited annotated categories by eliminating exhaustive and expensive mask annotations. The proposed setting is expected to be generalizable to novel categories as it learns the underlying positional information through a support set and class information through Co-Occurrence that can be generalized from annotated categories to novel categories. Here, we first extract features from the input image and support set with a shared multi-scale feature acquisition backbone. Then, the extracted feature representation is fed to the transformer encoder as a query. Later on, we utilize a semantic embedding network before the decoder to capture the underlying semantic relationships and similarities between different instances, enabling the model to make accurate predictions or classifications with only a limited amount of labeled data. Extensive experimentation on competitive benchmarks like PRIMA, DocLayNet, and Historical Japanese (HJ) demonstrate that this generalized setup obtains significant performance compared to the conventional supervised approach. |
|
|
Address |
June 2024 |
|
|
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 @ BBL2024a |
Serial |
4001 |
|
Permanent link to this record |
|
|
|
|
Author |
Josep Llados; Gemma Sanchez |
![find record details (via OpenURL) openurl](http://refbase.cvc.uab.es/img/xref.gif)
|
|
Title |
Graph Matching vs. Graph Parsing in Graphics Recognition: A Combined Approach |
Type ![sorted by Type field, descending order (down)](http://refbase.cvc.uab.es/img/sort_desc.gif) |
Journal |
|
Year |
2004 |
Publication |
International Journal of Pattern Recognition and Artificial Intelligence |
Abbreviated Journal |
IJPRAI |
|
|
Volume |
18 |
Issue |
3 |
Pages |
455–473 |
|
|
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 |
DAG; IF: 0.588 |
Approved |
no |
|
|
Call Number |
DAG @ dag @ LlS2004 |
Serial |
445 |
|
Permanent link to this record |
|
|
|
|
Author |
Ernest Valveny; Philippe Dosch |
![find record details (via OpenURL) openurl](http://refbase.cvc.uab.es/img/xref.gif)
|
|
Title |
A general framework for the evaluation of symbol recognition methods |
Type ![sorted by Type field, descending order (down)](http://refbase.cvc.uab.es/img/sort_desc.gif) |
Journal |
|
Year |
2006 |
Publication |
International Journal on Document Analysis and Recognition |
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 |
DAG |
Approved |
no |
|
|
Call Number |
DAG @ dag @ VaD2006 |
Serial |
686 |
|
Permanent link to this record |
|
|
|
|
Author |
Josep Llados; Dorothea Blostein |
![find record details (via OpenURL) openurl](http://refbase.cvc.uab.es/img/xref.gif)
|
|
Title |
Special Issue on Graphics Recognition |
Type ![sorted by Type field, descending order (down)](http://refbase.cvc.uab.es/img/sort_desc.gif) |
Journal |
|
Year |
2007 |
Publication |
International Journal on Document Analysis and Recognition |
Abbreviated Journal |
IJDAR |
|
|
Volume |
9 |
Issue |
1 |
Pages |
1–2 |
|
|
Keywords |
|
|
|
Abstract |
|
|
|
Address |
|
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
Guest Editors |
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 |
DAG @ dag @ LlB2007 |
Serial |
781 |
|
Permanent link to this record |
|
|
|
|
Author |
Ernest Valveny; Philippe Dosch; Adam Winstanley; Yu Zhou; Su Yang; Luo Yan; Liu Wenyin; Dave Elliman; Mathieu Nicolas Delalandre; Eric Trupin; Sebastien Adam; Jean-Marc Ogier |
![find record details (via OpenURL) openurl](http://refbase.cvc.uab.es/img/xref.gif)
|
|
Title |
A general framework for the evaluation of symbol recognition methods |
Type ![sorted by Type field, descending order (down)](http://refbase.cvc.uab.es/img/sort_desc.gif) |
Journal |
|
Year |
2006 |
Publication |
International Journal on Document Analysis and Recognition (IJDAR), 9(1): 59–74 |
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 |
DAG |
Approved |
no |
|
|
Call Number |
DAG @ dag @ VDW2006 |
Serial |
801 |
|
Permanent link to this record |
|
|
|
|
Author |
Gemma Sanchez; Alicia Fornes; Joan Mas; Josep Llados |
![find record details (via OpenURL) openurl](http://refbase.cvc.uab.es/img/xref.gif)
|
|
Title |
Computer Vision Tools for Visually Impaired Children Learning |
Type ![sorted by Type field, descending order (down)](http://refbase.cvc.uab.es/img/sort_desc.gif) |
Journal |
|
Year |
2007 |
Publication |
|
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 |
DAG |
Approved |
no |
|
|
Call Number |
DAG @ dag @ SFM2007a |
Serial |
891 |
|
Permanent link to this record |
|
|
|
|
Author |
Gemma Sanchez; Alicia Fornes; Joan Mas; Josep Llados |
![find record details (via OpenURL) openurl](http://refbase.cvc.uab.es/img/xref.gif)
|
|
Title |
Computer Vision Tools for Visually Impaired Children Learning |
Type ![sorted by Type field, descending order (down)](http://refbase.cvc.uab.es/img/sort_desc.gif) |
Journal |
|
Year |
2007 |
Publication |
|
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 |
DAG |
Approved |
no |
|
|
Call Number |
DAG @ dag @ SFM2007b |
Serial |
892 |
|
Permanent link to this record |
|
|
|
|
Author |
Ernest Valveny; Philippe Dosch |
![find record details (via OpenURL) openurl](http://refbase.cvc.uab.es/img/xref.gif)
|
|
Title |
A General Framework for the Evaluation of Symbol Recognition Methods |
Type ![sorted by Type field, descending order (down)](http://refbase.cvc.uab.es/img/sort_desc.gif) |
Journal |
|
Year |
2007 |
Publication |
International Journal on Document Analysis and Recognition, vol. 9(1), pp 59–74 |
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 |
DAG |
Approved |
no |
|
|
Call Number |
DAG @ dag @ VaD2007 |
Serial |
893 |
|
Permanent link to this record |
|
|
|
|
Author |
Josep Llados; J. Lopez-Krahe; D. Archambault |
![find record details (via OpenURL) openurl](http://refbase.cvc.uab.es/img/xref.gif)
|
|
Title |
Special Issue on Information Technologies for Visually Impaired People |
Type ![sorted by Type field, descending order (down)](http://refbase.cvc.uab.es/img/sort_desc.gif) |
Journal |
|
Year |
2007 |
Publication |
Novatica |
Abbreviated Journal |
|
|
|
Volume |
186 |
Issue |
|
Pages |
4-7 |
|
|
Keywords |
|
|
|
Abstract |
|
|
|
Address |
|
|
|
Corporate Author |
|
Thesis |
|
|
|
Publisher |
Guest Editors |
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 |
DAG @ dag @ LLA2007a |
Serial |
903 |
|
Permanent link to this record |