Mostrando 5 resultados de: 5
Filtros aplicados
Subtipo de publicación
Conference Object(5)
Publisher
ICMR 2019 - Proceedings of the 2019 ACM International Conference on Multimedia Retrieval(1)
International Journal on Document Analysis and Recognition(1)
Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017(1)
Proceedings of the IEEE International Conference on Computer Vision(1)
Proceedings of the International Conference on Document Analysis and Recognition, ICDAR(1)
Área temáticas
Métodos informáticos especiales(3)
Imprenta y actividades conexas(2)
Biblioteconomía y Documentación informatica(1)
Ciencias de la computación(1)
Derechos civiles y políticos(1)
Área de conocimiento
Visión por computadora(3)
Aprendizaje automático(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:scopusICDAR 2019 competition on scene text visual question answering
Conference ObjectAbstract: This paper presents final results of ICDAR 2019 Scene Text Visual Question Answering competition (STPalabras claves:Scene text, Scene understanding, Vision and language, Visual question answeringAutores:Furkan Biten A., Jawahar C.V., Karatzas D., Lluís Álvarez Gómez, Mafla A., Mathew M., Rusiñol M., Tito R., Valveny E.Fuentes:scopusScene text visual question answering
Conference ObjectAbstract: Current visual question answering datasets do not consider the rich semantic information conveyed byPalabras claves:Autores:Furkan Biten A., Jawahar C.V., Karatzas D., Lluís Álvarez Gómez, Mafla A., Rusiñol M., Tito R., Valveny E.Fuentes:scopusSelf-supervised learning of visual features through embedding images into text topic spaces
Conference ObjectAbstract: End-to-end training from scratch of current deep architectures for new computer vision problems woulPalabras claves:Autores:Jawahar C.V., Karatzas D., Lluís Álvarez Gómez, Patel Y., Rusiñol M.Fuentes:scopusSelf-supervised visual representations for cross-modal retrieval
Conference ObjectAbstract: Cross-modal retrieval methods have been significantly improved in last years with the use of deep nePalabras claves:Cross-modal retrieval, Self-supervised learning, Visual representationsAutores:Jawahar C.V., Karatzas D., Lluís Álvarez Gómez, Patel Y., Rusiñol M.Fuentes:scopus