Mostrando 5 resultados de: 5
Filtros aplicados
Publisher
International Journal on Document Analysis and Recognition(1)
Pattern Recognition(1)
Pattern Recognition Letters(1)
Proceedings - 2021 IEEE Winter Conference on Applications of Computer Vision, WACV 2021(1)
Proceedings - International Conference on Pattern Recognition(1)
Área temáticas
Funcionamiento de bibliotecas y archivos(3)
Métodos informáticos especiales(3)
Programación informática, programas, datos, seguridad(2)
Derechos civiles y políticos(1)
Imágenes fotográficas(1)
Área de conocimiento
Ciencias de la computación(5)
Visión por computadora(3)
Minería de datos(1)
Visualización de información(1)
Origen
scopus(5)
Asking questions on handwritten document collections
Conference ObjectAbstract: This work addresses the problem of Question Answering (QA) on handwritten document collections. UnliPalabras claves:Handwritten documents, Information Retrieval, Question answeringAutores:Jawahar C.V., Karatzas D., Lluís Álvarez Gómez, Mathew M.Fuentes:scopusMultimodal grid features and cell pointers for scene text visual question answering
ArticleAbstract: This paper presents a new model for the task of scene text visual question answering. In this task qPalabras claves:41A05, 41A10, 65D05, 65D17, deep learning, MSC, Multi-modal learning, Scene text, Visual question answeringAutores:Furkan Biten A., Karatzas D., Lluís Álvarez Gómez, Mafla A., Rusiñol M., Tito R., Valveny E.Fuentes:scopusReal-time Lexicon-free Scene Text Retrieval
ArticleAbstract: In this work, we address the task of scene text retrieval: given a text query, the system returns alPalabras claves:convolutional neural networks, Image retrieval, PHOC, Region proposal networks, Scene text detection, Scene text recognition, Word spottingAutores:Dey S., Karatzas D., Lluís Álvarez Gómez, Mafla A., Rusiñol M., Tito R., Valveny E.Fuentes:scopusStacMR: Scene-text aware cross-modal retrieval
Conference ObjectAbstract: Recent models for cross-modal retrieval have benefited from an increasingly rich understanding of viPalabras claves:Autores:Karatzas D., Larlus D., Lluís Álvarez Gómez, Mafla A., Rezende R.S.Fuentes:scopusText recognition - Real world data and where to find them
Conference ObjectAbstract: We present a method for exploiting weakly annotated images to improve text extraction pipelines. ThePalabras claves:Autores:Janouskova K., Karatzas D., Lluís Álvarez Gómez, Matas J.Fuentes:scopus