|
|
Gemma Sanchez, Josep Llados and K. Tombre. 2001. An Algorithm to Recognize Graphical Textured Symbols using String Representations..
|
|
|
|
V. Chapaprieta and Ernest Valveny. 2001. Handwritten Digit Recognition Using Point Distribution Models..
|
|
|
|
Josep Llados, J. Lopez-Krahe and Enric Marti. 1999. A Hough-based method for hatched pattern detection in maps and diagrams..
|
|
|
|
Hongxing Gao, Marçal Rusiñol, Dimosthenis Karatzas, Apostolos Antonacopoulos and Josep Llados. 2013. An interactive appearance-based document retrieval system for historical newspapers. Proceedings of the International Conference on Computer Vision Theory and Applications.84–87.
Abstract: In this paper we present a retrieval-based application aimed at assisting a user to semi-automatically segment an incoming flow of historical newspaper images by automatically detecting a particular type of pages based on their appearance. A visual descriptor is used to assess page similarity while a relevance feedback process allow refining the results iteratively. The application is tested on a large dataset of digitised historic newspapers.
|
|
|
|
Christophe Rigaud, Dimosthenis Karatzas, Joost Van de Weijer, Jean-Christophe Burie and Jean-Marc Ogier. 2013. Automatic text localisation in scanned comic books. Proceedings of the International Conference on Computer Vision Theory and Applications.814–819.
Abstract: Comic books constitute an important cultural heritage asset in many countries. Digitization combined with subsequent document understanding enable direct content-based search as opposed to metadata only search (e.g. album title or author name). Few studies have been done in this direction. In this work we detail a novel approach for the automatic text localization in scanned comics book pages, an essential step towards a fully automatic comics book understanding. We focus on speech text as it is semantically important and represents the majority of the text present in comics. The approach is compared with existing methods of text localization found in the literature and results are presented.
Keywords: Text localization; comics; text/graphic separation; complex background; unstructured document
|
|
|
|
Oriol Ramos Terrades, Salvatore Tabbone and Ernest Valveny. 2007. Optimal Linear Combination for Two-class Classifiers. Proceedings of the International Conference on Advances in Pattern Recognition.
|
|
|
|
Soumya Jahagirdar, Minesh Mathew, Dimosthenis Karatzas and CV Jawahar. 2023. Watching the News: Towards VideoQA Models that can Read. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer.
Abstract: Video Question Answering methods focus on commonsense reasoning and visual cognition of objects or persons and their interactions over time. Current VideoQA approaches ignore the textual information present in the video. Instead, we argue that textual information is complementary to the action and provides essential contextualisation cues to the reasoning process. To this end, we propose a novel VideoQA task that requires reading and understanding the text in the video. To explore this direction, we focus on news videos and require QA systems to comprehend and answer questions about the topics presented by combining visual and textual cues in the video. We introduce the ``NewsVideoQA'' dataset that comprises more than 8,600 QA pairs on 3,000+ news videos obtained from diverse news channels from around the world. We demonstrate the limitations of current Scene Text VQA and VideoQA methods and propose ways to incorporate scene text information into VideoQA methods.
|
|
|
|
Soumya Jahagirdar, Minesh Mathew, Dimosthenis Karatzas and CV Jawahar. 2023. Understanding Video Scenes Through Text: Insights from Text-Based Video Question Answering. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops.
Abstract: Researchers have extensively studied the field of vision and language, discovering that both visual and textual content is crucial for understanding scenes effectively. Particularly, comprehending text in videos holds great significance, requiring both scene text understanding and temporal reasoning. This paper focuses on exploring two recently introduced datasets, NewsVideoQA and M4-ViteVQA, which aim to address video question answering based on textual content. The NewsVideoQA dataset contains question-answer pairs related to the text in news videos, while M4- ViteVQA comprises question-answer pairs from diverse categories like vlogging, traveling, and shopping. We provide an analysis of the formulation of these datasets on various levels, exploring the degree of visual understanding and multi-frame comprehension required for answering the questions. Additionally, the study includes experimentation with BERT-QA, a text-only model, which demonstrates comparable performance to the original methods on both datasets, indicating the shortcomings in the formulation of these datasets. Furthermore, we also look into the domain adaptation aspect by examining the effectiveness of training on M4-ViteVQA and evaluating on NewsVideoQA and vice-versa, thereby shedding light on the challenges and potential benefits of out-of-domain training.
|
|
|
|
Oriol Ramos Terrades and Ernest Valveny. 2003. Indexing Technical Symbols Using Ridgelets Transform.
|
|
|
|
Ernest Valveny and Enric Marti. 1999. Application of deformable template matching to symbol recognition in hand-written architectural draw. Proceedings of the Fifth International Conference on. Bangalore (India).
Abstract: We propose to use deformable template matching as a new approach to recognize characters and lineal symbols in hand-written line drawings, instead of traditional methods based on vectorization and feature extraction. Bayesian formulation of the deformable template matching allows combining fidelity to the ideal shape of the symbol with maximum flexibility to get the best fit to the input image. Lineal nature of symbols can be exploited to define a suitable representation of models and the set of deformations to be applied to them. Matching, however, is done over the original binary image to avoid losing relevant features during vectorization. We have applied this method to hand-written architectural drawings and experimental results demonstrate that symbols with high distortions from ideal shape can be accurately identified.
|
|
