publications

2023

1. ArXiv

   Positional Diffusion: Ordering Unordered Sets with Diffusion Probabilistic Models

   Francesco Giuliari, Gianluca Scarpellini, Stuart James, Yiming Wang, and Alessio Del Bue

   In ArXiv 2023

   arXiv Bib Website

   @inproceedings{giuliari2023positional,
     title = {Positional Diffusion: Ordering Unordered Sets with Diffusion Probabilistic Models},
     author = {Giuliari, Francesco and Scarpellini, Gianluca and James, Stuart and Wang, Yiming and Bue, Alessio Del},
     year = {2023},
     eprint = {2303.11120},
     selected = {true},
     booktitle = {ArXiv},
     abbr = {ArXiv},
     bibtex_show = {true},
     website = {https://github.com/IIT-PAVIS/Positional_Diffusion},
     arxiv = {2303.11120},
     primaryclass = {cs.CV}
   }

2. Pattern Recognition

   Under the hood of transformer networks for trajectory forecasting

   Luca Franco, Leonardo Placidi,  Francesco Giuliari, Irtiza Hasan, Marco Cristani, and Fabio Galasso

   Pattern Recognition 2023

   Abs Bib

   Transformer Networks have established themselves as the de-facto state-of-the-art for trajectory forecasting but there is currently no systematic study on their capability to model the motion patterns of people, without interactions with other individuals nor the social context. There is abundant literature on LSTMs, CNNs and GANs on this subject. However methods adopting Transformer techniques achieve great performances by complex models and a clear analysis of their adoption as plain sequence models is missing. This paper proposes the first in-depth study of Transformer Networks (TF) and the Bidirectional Transformers (BERT) for the forecasting of the individual motion of people, without bells and whistles. We conduct an exhaustive evaluation of the input/output representations, problem formulations and sequence modelling, including a novel analysis of their capability to predict multi-modal futures. Out of comparative evaluation on the ETH+UCY benchmark, both TF and BERT are top performers in predicting individual motions and remain within a narrow margin wrt more complex techniques, including both social interactions and scene contexts. Source code will be released for all conducted experiments.

   @article{FRANCO2023109372,
     title = {Under the hood of transformer networks for trajectory forecasting},
     journal = {Pattern Recognition},
     volume = {138},
     pages = {109372},
     year = {2023},
     issn = {0031-3203},
     doi = {https://doi.org/10.1016/j.patcog.2023.109372},
     url = {https://www.sciencedirect.com/science/article/pii/S0031320323000730},
     author = {Franco, Luca and Placidi, Leonardo and Giuliari, Francesco and Hasan, Irtiza and Cristani, Marco and Galasso, Fabio},
     keywords = {Trajectory forecasting, Human behavior, Transformer networks, BERT, Multi-modal future prediction},
     bibtex_show = {true},
     abbr = {Pattern Recognition}
   }

2022

1. CVPR

   Spatial Commonsense Graph for Object localisation in Partial Scenes

   Francesco Giuliari, Geri Skenderi, Marco Cristani, Yiming Wang, and Alessio Del Bue

   In CVPR 2022

   arXiv Website

2021

1. IROS

   POMP++: Pomcp-based Active Visual Search in unknown indoor environments

   Francesco Giuliari, Alberto Castellini, Riccardo Berra, Alessio Del Bue, Alessandro Farinelli, Marco Cristani, Francesco Setti, and Yiming Wang

   In 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2021

   arXiv Bib

   @inproceedings{giuliari2021pomp++,
     title = {POMP++: Pomcp-based Active Visual Search in unknown indoor environments},
     author = {Giuliari, Francesco and Castellini, Alberto and Berra, Riccardo and Del Bue, Alessio and Farinelli, Alessandro and Cristani, Marco and Setti, Francesco and Wang, Yiming},
     booktitle = {2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
     pages = {1523--1530},
     organization = {IEEE},
     year = {2021},
     selected = {true},
     bibtex_show = {true},
     arxiv = {2107.00914},
     abbr = {IROS}
   }

2020

1. BMVC

   POMP: Pomcp-based Online Motion Planning for active visual search in indoor environments

   Yiming Wang,  Francesco Giuliari, Riccardo Berra, Alberto Castellini, Alessio Del Bue, Alessandro Farinelli, Marco Cristani, and Francesco Setti

   In BMVC 2020

   arXiv Bib

   @inproceedings{wang2020pomp,
     title = {POMP: Pomcp-based Online Motion Planning for active visual search in indoor environments},
     author = {Wang, Yiming and Giuliari, Francesco and Berra, Riccardo and Castellini, Alberto and Del Bue, Alessio and Farinelli, Alessandro and Cristani, Marco and Setti, Francesco},
     booktitle = {BMVC},
     year = {2020},
     bibtex_show = {true},
     arxiv = {2009.08140},
     abbr = {BMVC}
   }

2. ICPR

   Transformer networks for trajectory forecasting

   Francesco Giuliari, Irtiza Hasan, Marco Cristani, and Fabio Galasso

   In 2020 25th International Conference on Pattern Recognition (ICPR) 2020

   arXiv Bib

   @inproceedings{giuliari2021transformer,
     title = {Transformer networks for trajectory forecasting},
     author = {Giuliari, Francesco and Hasan, Irtiza and Cristani, Marco and Galasso, Fabio},
     booktitle = {2020 25th International Conference on Pattern Recognition (ICPR)},
     pages = {10335--10342},
     year = {2020},
     organization = {IEEE},
     selected = {true},
     bibtex_show = {true},
     arxiv = {2003.08111},
     abbr = {ICPR}
   }

2018

1. BMVC

   Understanding Deep Architectures by Visual Summaries

   Marco Godi, Marco Carletti, Maya Aghaei,  Francesco Giuliari, and Marco Cristani

   In BMVC 2018

   arXiv Bib

   @inproceedings{Godi2018UnderstandingDA,
     title = {Understanding Deep Architectures by Visual Summaries},
     author = {Godi, Marco and Carletti, Marco and Aghaei, Maya and Giuliari, Francesco and Cristani, Marco},
     booktitle = {BMVC},
     year = {2018},
     bibtex_show = {true},
     arxiv = {1801.09103},
     abbr = {BMVC}
   }