Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 3
Encontrada(s) 1 página(s)

Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

VLX-Stories: a semantically linked event platform for media publishers

  • Fernández Cañellas, Dèlia
  • Espadaler, Joan
  • Garolera, Blai
  • Rodríguez, David
  • Canet, Gemma
  • Colom, Aleix
  • Rimmek, Joan Marco
  • Giró Nieto, Xavier
  • Bou Balust, Elisenda
  • Riveiro, Juan Carlos
In the recent years, video sharing in social media from different video recording devices has resulted in a exponential growth of videos on the Internet. Such video data is continuously increasing with daily recordings related to a wide number of topics. In this context, video understanding has become a critical problem to address. Video search and indexation benefits from the use of keyword tags related to the video content, but most of the shared video content does not contain these tags. Although the use of deep learning has become essential for image analysis in several areas, video domain is still a relatively unexplored field for these type of methods. On the other hand knowledge graphs as Freebase or WordNet store high quantities of information about the word and relations that can be used to disambiguate concepts and relate them through contextual information In this research project we search to explore and improve the understanding of video content through the use of automatic tagging models based on Machine Learning and Deep Learning techniques, improved by the use of knowledge bases., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

What is going on in the world? A display platform for media understanding

  • Fernàndez, Dèlia
  • Varas, David
  • Espadaler, Joan
  • Masuda, Issey
  • Giró Nieto, Xavier
  • Riveiro, Juan Carlos
  • Bou Balust, Elisenda
News broadcasters and on-line publishers daily generate a large amount of articles and videos describing events currently happening in the world. In this work, we present a system that automatically indexes videos from a library and links them to stories developing in the news. The user interface displays in an intuitive manner the links between videos and stories and allows navigation through related content by using associated tags. This interface is a powerful industrial tool for publishers to index, retrieve and visualize their video content. It helps them identify which topics require more attention or retrieve related content that has already been published about the stories., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Explore, discover and learn: unsupervised discovery of state-covering skills

  • Campos Camúñez, Víctor
  • Trott, Alex
  • Xiong, Caiming
  • Socher, Richard
  • Giró Nieto, Xavier
  • Torres Viñals, Jordi
Acquiring abilities in the absence of a task-oriented reward function is at the frontier of reinforcement learning research. This problem has been studied through the lens of empowerment, which draws a connection between option discovery and information theory. Information-theoretic skill discovery methods have garnered much interest from the community, but little research has been conducted in understanding their limitations. Through theoretical analysis and empirical evidence, we show that existing algorithms suffer from a common limitation -- they discover options that provide a poor coverage of the state space. In light of this, we propose 'Explore, Discover and Learn' (EDL), an alternative approach to information-theoretic skill discovery. Crucially, EDL optimizes the same information-theoretic objective derived from the empowerment literature, but addresses the optimization problem using different machinery. We perform an extensive evaluation of skill discovery methods on controlled environments and show that EDL offers significant advantages, such as overcoming the coverage problem, reducing the dependence of learned skills on the initial state, and allowing the user to define a prior over which behaviors should be learned., This work was partially supported by the Spanish Ministry of Science and Innovation and the European Regional Development Fund under contracts TEC2016-75976-R and TIN2015-65316-P, by the BSC-CNS Severo Ochoa program SEV-2015-0493, and by Generalitat de Catalunya under contracts 2017-SGR-1414 and 2017-DI-011. Víctor Campos was supported by Obra Social “la Caixa” through La Caixa-Severo Ochoa International Doctoral Fellowship program., Peer Reviewed, Postprint (published version)