Skip to main content

and
  1. No Access

    Article

    From global image annotation to interactive object segmentation

    This paper presents a graphical environment for the annotation of still images that works both at the global and local scales. At the global scale, each image can be tagged with positive, negative and neutral ...

    Xavier Giró-i-Nieto, Manuel Martos, Eva Mohedano in Multimedia Tools and Applications (2014)

  2. No Access

    Chapter and Conference Paper

    Adversarially Robust Panoptic Segmentation (ARPaS) Benchmark

    We propose the Adversarially Robust Panoptic Segmentation (ARPaS) benchmark to assess the general robustness of panoptic segmentation techniques. To account for the differences between instance and semantic se...

    Laura Daza, Jordi Pont-Tuset, Pablo Arbeláez in Computer Vision – ECCV 2022 Workshops (2023)