Now showing items 1-5 of 5

    • Context-unsupervised adversarial network for video sensors 

      Canet Tarrés, Gemma; Pardàs Feliu, Montse (Multidisciplinary Digital Publishing Institute (MDPI), 2022-04-21)
      Open Access
      Foreground object segmentation is a crucial first step for surveillance systems based on networks of video sensors. This problem in the context of dynamic scenes has been widely explored in the last two decades, but it ...
    • Estimating the mass of a black hole 

      Canet Tarrés, Gemma; Melgarejo Lermas, Irene (Universitat Politècnica de Catalunya, 2017)
      Open Access
      A black hole is a region of spacetime where the force of gravity makes it impossible for anything to escape it. Therefore, the only way to study its properties is by analyzing the X-rays it emits. The aim of this project ...
    • Refinement network for unsupervised on the scene foreground segmentation 

      Pardàs Feliu, Montse; Canet Tarrés, Gemma (European Association for Signal Processing (EURASIP), 2020)
      Conference report
      Open Access
      Unsupervised learning represents one of the most interesting challenges in computer vision today. The task has an immense practical value with many applications in artificial intelligence and emerging technologies, as large ...
    • Using heterogeneity for obtaining the Medial Axis Transform of natural images 

      Canet Tarrés, Gemma (Universitat Politècnica de Catalunya, 2018-05)
      Bachelor thesis
      Open Access
      From Blum's Medial Axis Transform, that obtains the skeleton of binary images by joining the centers of all maximal inscribed disks in the shape, the AMAT was developed. The Appearance-MAT is a method that aims to compute ...
    • VLX-Stories: building an online Event Knowledge Base with Emerging Entity detection 

      Fernández Cañellas, Dèlia; Espadaler, Joan; Rodríguez, David; Garolera, Blai; Canet Tarrés, Gemma; Colom Serra, Aleix; Rimmek, Joan Marco; Giró Nieto, Xavier; Bou Balust, Elisenda; Riveiro, Juan Carlos (Springer, 2019)
      Conference lecture
      Restricted access - publisher's policy
      We present an online multilingual system for event detection and comprehension from media feeds. The system retrieves information from news sites, aggregates them into events (event detection), and summarizes them by ...