• Click'n'Cut: crowdsourced interactive segmentation with object candidates 

      Carlier, Axel; Charvillat, Vincent; Salvador Aguilera, Amaia; Giró Nieto, Xavier; Marques, Ogé (ACM, 2014)
      Comunicació de congrés
      Accés obert
      This paper introduces Click’n’Cut, a novel web tool for inter- active object segmentation designed for crowdsourcing tasks. Click’n’Cut combines bounding boxes and clicks generated by workers to obtain accurate object ...
    • Contextless Object Recognition with Shape-enriched SIFT and Bags of Features 

      Tella Amo, Marcel (Universitat Politècnica de Catalunya, 2014-08-28)
      Projecte/Treball Final de Carrera
      Accés obert
      Currently, there are highly competitive results in the field of object recognition based on the aggregation of point-based features [4, 26, 5, 6]. The aggregation process, typically with an average or max-pooling of the ...