Exploració per autor "Ventura, Carles"

Ara es mostren els items 1-4 de 4

    • Insight Centre for Data Analytics (DCU) at TRECVid 2014: instance search and semantic indexing tasks 

      McGuinness, Kevin; Mohedano, Eva; Zhang, ZhenXing; Hu, Feiyan; Abatal, Rami; Gurrin, Cathal; O'Connor, Noel; Smeaton, Alan F.; Salvador Aguilera, Amaia; Giró Nieto, Xavier; Ventura, Carles (2014)
      Text en actes de congrés
      Accés obert
      Insight-DCU participated in the instance search (INS) and semantic indexing (SIN) tasks in 2014. Two very different approaches were submitted for instance search, one based on features extracted using pre-trained deep ...

    • Multiresolution co-clustering for uncalibrated multiview segmentation 

      Ventura, Carles; Varas, David; Vilaplana Besler, Verónica; Giró Nieto, Xavier; Marqués Acosta, Fernando (2019-05-04)
      Article
      Accés obert
      We propose a technique for coherently co-clustering uncalibrated views of a scene with a contour-based representation. Our work extends the previous framework, an iterative algorithm for segmenting sequences with small ...

    • System architecture of a web service for Content-Based Image Retrieval 

      Giró Nieto, Xavier; Ventura, Carles; Pont Tuset, Jordi; Cortés Yuste, Silvia; Marqués Acosta, Fernando (Association for Computing Machinery (ACM), 2010)
      Comunicació de congrés
      Accés obert
      This paper presents the system architecture of a Content- Based Image Retrieval system implemented as a web service. The proposed solution is composed of two parts, a client run- ning a graphical user interface for query ...

    • Video object linguistic grounding 

      Herrera-Palacio, Alba; Ventura, Carles; Giró Nieto, Xavier (Association for Computing Machinery (ACM), 2019)
      Comunicació de congrés
      Accés restringit per política de l'editorial
      The goal of this work is segmenting on a video sequence the objects which are mentioned in a linguistic description of the scene. We have adapted an existing deep neural network that achieves state of the art performance ...