|
|
Josep Llados, Ernest Valveny, Gemma Sanchez and Enric Marti. 2003. A Case Study of Pattern Recognition: Symbol Recognition in Graphic Documentsa. Proceedings of Pattern Recognition in Information Systems. ICEIS Press, 1–13.
|
|
|
|
Gemma Sanchez and 6 others. 2003. A system for virtual prototyping of architectural projects. Proceedings of Fifth IAPR International Workshop on Pattern Recognition.65–74.
|
|
|
|
Gemma Sanchez and Josep Llados. 2003. Syntactic models to represent perceptually regular repetitive patterns in graphic documents.
|
|
|
|
Philippe Dosch and Josep Llados. 2003. Vectorial Signatures for Symbol Discrimination.
|
|
|
|
Josep Llados and Gemma Sanchez. 2003. Symbol Recognition Using Graphs.
|
|
|
|
Emanuele Vivoli, Ali Furkan Biten, Andres Mafla, Dimosthenis Karatzas and Lluis Gomez. 2022. MUST-VQA: MUltilingual Scene-text VQA. Proceedings European Conference on Computer Vision Workshops.345–358. (LNCS.)
Abstract: In this paper, we present a framework for Multilingual Scene Text Visual Question Answering that deals with new languages in a zero-shot fashion. Specifically, we consider the task of Scene Text Visual Question Answering (STVQA) in which the question can be asked in different languages and it is not necessarily aligned to the scene text language. Thus, we first introduce a natural step towards a more generalized version of STVQA: MUST-VQA. Accounting for this, we discuss two evaluation scenarios in the constrained setting, namely IID and zero-shot and we demonstrate that the models can perform on a par on a zero-shot setting. We further provide extensive experimentation and show the effectiveness of adapting multilingual language models into STVQA tasks.
Keywords: Visual question answering; Scene text; Translation robustness; Multilingual models; Zero-shot transfer; Power of language models
|
|
|
|
Sergi Garcia Bordils and 7 others. 2022. Out-of-Vocabulary Challenge Report. Proceedings European Conference on Computer Vision Workshops.359–375. (LNCS.)
Abstract: This paper presents final results of the Out-Of-Vocabulary 2022 (OOV) challenge. The OOV contest introduces an important aspect that is not commonly studied by Optical Character Recognition (OCR) models, namely, the recognition of unseen scene text instances at training time. The competition compiles a collection of public scene text datasets comprising of 326,385 images with 4,864,405 scene text instances, thus covering a wide range of data distributions. A new and independent validation and test set is formed with scene text instances that are out of vocabulary at training time. The competition was structured in two tasks, end-to-end and cropped scene text recognition respectively. A thorough analysis of results from baselines and different participants is presented. Interestingly, current state-of-the-art models show a significant performance gap under the newly studied setting. We conclude that the OOV dataset proposed in this challenge will be an essential area to be explored in order to develop scene text models that achieve more robust and generalized predictions.
|
|
|
|
Ramon Baldrich, Ricardo Toledo, Ernest Valveny and Maria Vanrell. 2002. Perceptual Colour Image Segmentation..
|
|
|
|
Ernest Valveny, Ricardo Toledo, Ramon Baldrich and Enric Marti. 2002. Combining recognition-based in segmentation-based approaches for graphic symol recognition using deformable template matching. Proceeding of the Second IASTED International Conference Visualization, Imaging and Image Proceesing VIIP 2002.502–507.
|
|
|
|
Josep Llados, Enric Marti and Jaime Lopez-Krahe. 1999. A Hough-based method for hatched pattern detection in maps and diagrams. Proceeding of the Fifth Int. Conf. Document Analysis and Recognition ICDAR ’99.479–482.
Abstract: A hatched area is characterized by a set of parallel straight lines placed at regular intervals. In this paper, a Hough-based schema is introduced to recognize hatched areas in technical documents from attributed graph structures representing the document once it has been vectorized. Defining a Hough-based transform from a graph instead of the raster image allows to drastically reduce the processing time and, second, to obtain more reliable results because straight lines have already been detected in the vectorization step. A second advantage of the proposed method is that no assumptions must be made a priori about the slope and frequency of hatching patterns, but they are computed in run time for each hatched area.
|
|
