Skip to main content

LEYENDO EL ENTORNO: INTEGRANDO SISTEMAS DE LECTURA EN MODELOS DE INTERPRETACION DE ESCENAS HOLISTICOS

TIN2017-89779-P

•
Funding agency name Agencia Estatal de Investigación
Funding agency acronym AEI
Program Programa Estatal de Fomento de la Investigación Científica y Técnica de Excelencia
Subprogram Subprograma Estatal de Generación de Conocimiento
Call Proyectos de I+D (Excelencia / Generación de Conocimiento)
Call year 2017
State Plan 2017-2020 Plan Estatal de Investigación Científica y Técnica y de Innovación
Beneficiary centre CENTRO DE VISION POR COMPUTADOR

Resultados relacionados

Resultados totales (Incluyendo duplicados): 2
Encontrada(s) 1 página(s)

Dipòsit Digital de Documents de la UAB
Publication Artículo científico (JournalArticle)

Real-time Lexicon-free Scene Text Retrieval

  • Mafla Delgado, Andres Patricio|||0000-0003-2575-6093
  • Pérez Tito, Rubèn
  • Sounak, Dey|||0000-0001-6704-6810
  • Gomez Bigorda, Lluis|||0000-0003-1408-9803
  • Rossinyol, Marçal|||0000-0002-1734-2205
  • Valveny Llobet, Ernest|||0000-0002-0368-9697
  • Karatzas, Dimosthenis|||0000-0001-8762-4454
In this work, we address the task of scene text retrieval: given a text query, the system returns all im- ages containing the queried text. The proposed model uses a single shot CNN architecture that predicts bounding boxes and builds a compact representation of spotted words. In this way, this problem can be modeled as a nearest neighbor search of the textual representation of a query over the outputs of the CNN collected from the totality of an image database. Our experiments demonstrate that the proposed model outperforms previous state-of-the-art, while offering a significant increase in processing speed and unmatched expressiveness with samples never seen at training time. Several experiments to assess the generalization capability of the model are conducted in a multilingual dataset, as well as an application of real-time text spotting in videos.
Dipòsit Digital de Documents de la UAB
Publication Capítulo o parte de un libro (BookPart)

Location Sensitive Image Retrieval and Tagging

  • Gómez Bruballa, Raúl Álamo|||0000-0003-4460-3500
  • Gibert, Jaume|||0000-0002-9723-3913
  • Gomez Bigorda, Lluis|||0000-0003-1408-9803
  • Karatzas, Dimosthenis|||0000-0001-8762-4454
People from different parts of the globe describe objects and concepts in distinct manners. Visual appearance can thus vary across different geographic locations, which makes location a relevant contextual information when analysing visual data. In this work, we address the task of image retrieval related to a given tag conditioned on a certain location on Earth. We present LocSens, a model that learns to rank triplets of images, tags and coordinates by plausibility, and two training strategies to balance the location influence in the final ranking. LocSens learns to fuse textual and location information of multimodal queries to retrieve related images at different levels of location granularity, and successfully utilizes location information to improve image tagging.