1 code implementation • 31 Oct 2022 • Simone Rossetti, Damiano Zappia, Marta Sanzari, Marco Schaerf, Fiora Pirri
On the other hand, WSSS methods based on Vision Transformers (ViT) have not yet explored valid alternatives to CAM.
no code implementations • 7 Feb 2019 • Lorenzo Mauro, Edoardo Alati, Marta Sanzari, Valsamis Ntouskos, Gianluca Massimiani, Fiora Pirri
We consider a novel approach to high-level robot task execution for a robot assistive task.
no code implementations • 7 Feb 2019 • Lorenzo Mauro, Francesco Puja, Simone Grazioso, Valsamis Ntouskos, Marta Sanzari, Edoardo Alati, Fiora Pirri
Visual search of relevant targets in the environment is a crucial robot skill.
no code implementations • 29 Sep 2017 • Marta Sanzari, Valsamis Ntouskos, Fiora Pirri
Given new video data and given the estimated pose of the subject appearing on the video, the motion is segmented into primitives, which are recognized with a probability given according to the parameters of the learned models.
1 code implementation • 29 Sep 2017 • Francesco Puja, Simone Grazioso, Antonio Tammaro, Valsmis Ntouskos, Marta Sanzari, Fiora Pirri
Execution monitor of high-level robot actions can be effectively improved by visual monitoring the state of the world in terms of preconditions and postconditions that hold before and after the execution of an action.
no code implementations • CVPR 2016 • Fabrizio Natola, Valsamis Ntouskos, Fiora Pirri, Marta Sanzari
A methodology for 3D surface modeling from a single image is proposed.
no code implementations • ICCV 2015 • Fabrizio Natola, Valsamis Ntouskos, Marta Sanzari, Fiora Pirri
We propose a novel approach to human action recognition, with motion capture data (MoCap), based on grouping sub-body parts.
no code implementations • ICCV 2015 • Valsamis Ntouskos, Marta Sanzari, Bruno Cafaro, Federico Nardi, Fabrizio Natola, Fiora Pirri, Manuel Ruiz
We introduce a novel framework for modeling articulated objects based on the aspects of their components.