Publications

@inproceedings{nokey,

title = {Enhanced Model Robustness to Input Corruptions by Per-corruption Adaptation of Normalization Statistics},

author = {Elena Camuffo and Umberto Michieli and Simone Milani and Ji Joong Moon and Mete Ozay},

editor = {IEEE},

url = {https://arxiv.org/abs/2407.06450},

year  = {2024},

date = {2024-06-30},

urldate = {2024-06-30},

booktitle = { IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},

journal = {IEEE},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{barbato2023continualb,

title = {Continual Road-Scene Semantic Segmentation via Feature-Aligned Symmetric Multi-Modal Network},

author = {Francesco Barbato and Elena Camuffo and Simone Milani and Pietro Zanuttigh},

url = {https://arxiv.org/pdf/2308.04702.pdf},

year  = {2024},

date = {2024-06-25},

urldate = {2023-01-01},

booktitle = {IEEE International Conference on Image Processing (ICIP)},

journal = {arXiv preprint arXiv:2308.04702},

abstract = {State-of-the-art multimodal semantic segmentation approaches combining LiDAR and color data are usually designed on top of asymmetric information-sharing schemes and assume that both modalities are always available. Regrettably, this strong assumption may not hold in real-world scenarios, where sensors are prone to failure or can face adverse conditions (night-time, rain, fog, etc.) that make the acquired information unreliable. Moreover, these architectures tend to fail in continual learning scenarios. In this work, we re-frame the task of multimodal semantic segmentation by enforcing a tightly-coupled feature representation and a symmetric information-sharing scheme, which allows our approach to work even when one of the input modalities is missing. This makes our model reliable even in safetycritical settings, as is the case of autonomous driving. We evaluate our approach on the SemanticKITTI dataset, comparing it with our closest competitor. We also introduce an ad-hoc continual learning scheme and show results in a class-incremental continual learning scenario that prove the effectiveness of the approach also in this setting.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{jung2024housecat6d,

title = {HouseCat6D-A Large-Scale Multi-Modal Category Level 6D Object Perception Dataset with Household Objects in Realistic Scenarios},

author = {HyunJun Jung and Shun-Cheng Wu and Patrick Ruhkamp and Hannah Schieber and Pengyuan Wang and Giulia Rizzoli and Hongcheng Zhao and Sven Damian Meier and Daniel Roth and Nassir Navab and others},

year  = {2024},

date = {2024-06-19},

urldate = {2024-06-19},

booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},

journal = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},

pages = {22498--22508},

note = {Highlight},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Camuffo2023d,

title = {FFT-based Selection And Optimization Of Statistics For Robust Recognition Of Severely Corrupted Images},

author = {Elena Camuffo and Umberto Michieli and Ji Joong Moon and Daehyun Kim and Mete Ozay},

url = {https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10447639},

year  = {2024},

date = {2024-01-26},

urldate = {2024-01-26},

booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},

abstract = {Improving model robustness in case of corrupted images is among the key challenges to enable robust vision systems on smart devices, such as robotic agents. Particularly, robust test-time performance is imperative for most of the applications. This paper presents a novel approach to improve robustness of any classification model, especially on severely corrupted images. Our method (FROST) employs high-frequency features to detect input image corruption type, and select layer-wise feature normalization statistics. FROST provides the state-of-the-art results for different models and datasets, outperforming competitors on ImageNet-C by up to 37.1% relative gain, improving baseline of 40.9% mCE on severe corruptions.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{rizzoli2024source,

title = {Source-Free Domain Adaptation for RGB-D Semantic Segmentation with Vision Transformers},

author = {Giulia Rizzoli and Donald Shenaj and Pietro Zanuttigh},

url = {https://openaccess.thecvf.com/content/WACV2024W/Pretrain/html/Rizzoli_Source-Free_Domain_Adaptation_for_RGB-D_Semantic_Segmentation_With_Vision_Transformers_WACVW_2024_paper.html},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},

pages = {615–624},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{10.1145/3625468.3647623,

title = {A Modular System for Enhanced Robustness of Multimedia Understanding Networks via Deep Parametric Estimation},

author = {Francesco Barbato and Umberto Michieli and Mehmet Kerim Yucel and Pietro Zanuttigh and Mete Ozay},

url = {https://doi.org/10.1145/3625468.3647623},

doi = {10.1145/3625468.3647623},

isbn = {9798400704123},

year  = {2024},

date = {2024-01-01},

booktitle = {Proceedings of the 15th ACM Multimedia Systems Conference},

pages = {190–201},

publisher = {Association for Computing Machinery},

address = {, Bari, Italy,},

series = {MMSys '24},

abstract = {Performance degradation caused by corrupted multimedia samples is a critical challenge for machine learning models. Previously, three groups of approaches have been proposed to tackle this issue: i) enhancer and denoiser modules to improve the quality of the noisy data, ii) data augmentation approaches, and iii) domain adaptation strategies. All have drawbacks limiting applicability; the first requires paired clean-corrupted data for training and has an high computational cost, while the others can only be used on the same task they were trained on. In this paper, we propose SyMPIE to solve these shortcomings, designing a small, modular, and efficient system to enhance input data for robust downstream multimedia understanding with minimal computational cost. Our SyMPIE is pre-trained on an upstream task/network that should not match the downstream ones and does not need paired clean-corrupted samples. Our key insight is that most input corruptions found in real-world tasks can be modeled through global operations on color channels of images or spatial filters with small kernels. We validate our approach on multiple datasets and tasks, such as image classification (on ImageNetC, ImageNetC-Bar, VizWiz, and a newly proposed mixed corruption benchmark named ImageNetC-mixed) and semantic segmentation (on Cityscapes, ACDC, and DarkZurich) with consistent improvements of about 5% relative accuracy gain across the board1.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{martinturrero2024alerttransformer,

title = {ALERT-Transformer: Bridging Asynchronous and Synchronous Machine Learning for Real-Time Event-based Spatio-Temporal Data},

author = {Carmen Martin-Turrero and Maxence Bouvier and Manuel Breitenstein and Pietro Zanuttigh and Vincent Parret},

year  = {2024},

date = {2024-01-01},

booktitle = {Proceedings of the International Conference on Machine Learning (ICML)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{baldoni2024questset,

title = {Questset: A VR Dataset for Network and Quality of Experience Studies},

author = {Sara Baldoni and Federica Battisti and Federico Chiariotti and Fabio Mistrorigo and Alfi Baqiatus Shofi and Paolo Testolina and Alessandro Traspadini and Andrea Zanella and Michele Zorzi},

url = {https://dl.acm.org/doi/abs/10.1145/3625468.3652187},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

booktitle = {Proceedings of the 15th ACM Multimedia Systems Conference},

pages = {408–414},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{liu2024learning,

title = {Learning from the Web: Language Drives Weakly-Supervised Incremental Learning for Semantic Segmentation},

author = {Chang Liu and Giulia Rizzoli and Pietro Zanuttigh and Fu Li and Yi Niu},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

booktitle = {European Conference on Computer Vision},

organization = {Springer},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{10598293,

title = {On the identification of the leading sensory cue in mulsemedia VR applications},

author = {Anna Ferrarotti and Sara Baldoni and Marco Carli and Federica Battisti},

doi = {10.1109/QoMEX61742.2024.10598293},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

booktitle = {2024 16th International Conference on Quality of Multimedia Experience (QoMEX)},

pages = {36-42},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{10.1145/3639701.3661089,

title = {Interaction goes virtual: towards collaborative XR},

author = {Anna Ferrarotti and Sara Baldoni and Marco Carli and Federica Battisti},

url = {https://doi.org/10.1145/3639701.3661089},

doi = {10.1145/3639701.3661089},

isbn = {9798400705038},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

booktitle = {Proceedings of the 2024 ACM International Conference on Interactive Media Experiences},

pages = {443–446},

publisher = {Association for Computing Machinery},

address = {Stockholm, Sweden},

series = {IMX '24},

abstract = {This demo presents an interactive communication system based on immersive media for analyzing the users’ Quality of Experience in collaborative tasks. The interaction between users is studied in an asymmetric scenario where a peer-to-peer communication has been set up between a PC and a Virtual Reality headset. Two application scenarios have been considered: a Block Building task and a Treasure Hunt game. The two users will cooperate to perform the two tasks. The goal is to study the relation between the type of transmitted information (i.e., audio and video or audio only) and the quality and quantity of interaction. During the demo, participants will have the opportunity to try one of the designed applications.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Lincetto2023,

title = {Exploiting Multiple Priors for Neural 3D Indoor Reconstruction},

author = {Federico Lincetto and Gianluca Agresti and Mattia Rossi and Pietro Zanuttigh},

doi = {https://doi.org/10.48550/arXiv.2309.07021},

year  = {2023},

date = {2023-11-20},

booktitle = {34th British Machine Vision Conference},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Camuffo2023c,

title = {Fully Automated Scan-to-BIM via Point Cloud Instance Segmentation},

author = {Campagnolo* Devid and Camuffo* Elena and Michieli Umberto and Borin Paolo and Milani Simone and Giordano Andrea

},

url = {https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10222064},

year  = {2023},

date = {2023-09-13},

urldate = {2023-09-13},

booktitle = {International Conference on Image Processing (ICIP)},

organization = {IEEE},

abstract = {Digital reconstruction through Building Information Models (BIM) is a valuable methodology for documenting and analyzing existing buildings. Its pipeline starts with geometric acquisition. (e.g., via photogrammetry or laser scanning) for accurate point cloud collection. However, the acquired data are noisy and unstructured, and the creation of a semanticallymeaningful BIM representation requires a huge computational effort, as well as expensive and time-consuming human annotations. In this paper, we propose a fully automated scan-to-BIM pipeline. The approach relies on: (i) our dataset (HePIC), acquired from two large buildings and annotated at a point-wise semantic level based on existent BIM models; (ii) a novel ad hoc deep network (BIM-Net++) for semantic segmentation, whose output is then processed to extract instance information necessary to recreate BIM objects; (iii) novel model pretraining and class re-weighting to eliminate the need for a large amount of labeled data and human intervention.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Camuffo2023b,

title = {Continual Learning for LiDAR Semantic Segmentation: Class-Incremental and Coarse-to-Fine strategies on Sparse Data},

author = {Elena Camuffo and Simone Milani},

url = {https://arxiv.org/abs/2304.03980},

doi = {https://doi.org/10.48550/arXiv.2304.03980},

year  = {2023},

date = {2023-04-10},

urldate = {2023-04-10},

booktitle = {International Conference of Computer Vision and Pattern Recognition Workshops},

abstract = {During the last few years, continual learning (CL) strategies for image classification and segmentation have been widely investigated designing innovative solutions to tackle catastrophic forgetting, like knowledge distillation and self-inpainting. However, the application of continual learning paradigms to point clouds is still unexplored and investigation is required, especially using architectures that capture the sparsity and uneven distribution of LiDAR data. The current paper analyzes the problem of class incremental learning applied to point cloud semantic segmentation, comparing approaches and state-of-the-art architectures. To the best of our knowledge, this is the first example of class-incremental continual learning for LiDAR point cloud semantic segmentation. Different CL strategies were adapted to LiDAR point clouds and tested, tackling both classic fine-tuning scenarios and the Coarse-to-Fine learning paradigm. The framework has been evaluated through two different architectures on SemanticKITTI, obtaining results in line with state-of-the-art CL strategies and standard offline learning.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Baldoni_ISPA_2023,

title = {An Ablation Study on 360-Degree Saliency Estimation},

author = {Sara Baldoni and Ortisa Poci and Giancarlo Calvagno and Federica Battisti},

url = {https://ieeexplore.ieee.org/abstract/document/10279300},

doi = {10.1109/ISPA58351.2023.10279300},

year  = {2023},

date = {2023-01-01},

urldate = {2023-01-01},

booktitle = {2023 International Symposium on Image and Signal Processing and Analysis (ISPA)},

pages = {1-6},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{baldoni2023ablation,

title = {An ablation study on 360-degree saliency estimation},

author = {Sara Baldoni and Ortisa Poci and Giancarlo Calvagno and Federica Battisti},

year  = {2023},

date = {2023-01-01},

booktitle = {2023 International Symposium on Image and Signal Processing and Analysis (ISPA)},

pages = {1–6},

organization = {IEEE},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{jesus2023subjective,

title = {Subjective evaluation of dynamic point clouds: impact of compression and exploration behaviour},

author = {Gutiérrez Jesus and Gulzhanat Dandyyeva and Matteo Dal Magro and Carlos Cortés and Michele Brizzi and Marco Carli and Federica Battisti and others},

url = {https://ieeexplore.ieee.org/document/10290086},

year  = {2023},

date = {2023-01-01},

urldate = {2023-01-01},

booktitle = {Proceedings of the 31st European Signal Processing Conference},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{barbato2023depthformer,

title = {DepthFormer: Multimodal Positional Encodings and Cross-Input Attention for Transformer-Based Segmentation Networks},

author = {Francesco Barbato and Giulia Rizzoli and Pietro Zanuttigh},

year  = {2023},

date = {2023-01-01},

booktitle = {ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{shenaj2023asynchronous,

title = {Asynchronous Federated Continual Learning},

author = {Donald Shenaj and Marco Toldo and Alberto Rigon and Pietro Zanuttigh},

year  = {2023},

date = {2023-01-01},

urldate = {2023-01-01},

booktitle = {CVPR FedVision Workshop},

journal = {arXiv preprint arXiv:2304.03626},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{amann2023material,

title = {Material Characterization using a Compact Computed Tomography Imaging Spectrometer with Super-resolution Capability},

author = {Simon Amann and Mazen Mel and Pietro Zanuttigh and Tobias Haist and Markus Kamm and Alexander Gatto and others},

year  = {2023},

date = {2023-01-01},

urldate = {2023-01-01},

booktitle = {Proceedings of the 6th International Conference on Optical Characterization of Materials, OCM 2023},

pages = {139–148},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Shenaj2023,

title = {Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learning},

author = {Donald Shenaj and Eros Fan`i and Marco Toldo and Debora Caldarola and Antonio Tavera and Umberto Michieli and Marco Ciccone and Pietro Zanuttigh and Barbara Caputo},

year  = {2023},

date = {2023-01-01},

booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2023},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{rizzoli2023syndrone,

title = {SynDrone-Multi-Modal UAV Dataset for Urban Scenarios},

author = {Giulia Rizzoli and Francesco Barbato and Matteo Caligiuri and Pietro Zanuttigh},

year  = {2023},

date = {2023-01-01},

booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},

pages = {2210–2220},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Casarin2022,

title = {Unsupervised Network Anomaly Detection by Learning on 2D Data Representations},

author = {Sofia Casarin and Sara Baldoni and Marco Carli and Pietro Zanuttigh and Federica Battisti},

year  = {2022},

date = {2022-01-01},

urldate = {2022-01-01},

booktitle = {2022 9th Swiss Conference on Data Science (SDS)},

pages = {53--58},

organization = {IEEE},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Mari2022a,

title = {Features Denoising for Learned Image Coding},

author = {Daniele Mari and Simone Milani},

year  = {2022},

date = {2022-01-01},

urldate = {2022-01-01},

booktitle = {2022 10th European Workshop on Visual Information Processing (EUVIP)},

pages = {1--6},

organization = {IEEE},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Caligiuri2022,

title = {A Bayesian Game of Multisource Energy Harvesting for Batteryless IoT Devices},

author = {Matteo Caligiuri and Daniele Galizio and Federico Lincetto and Elvina Gindullina and Leonardo Badia},

year  = {2022},

date = {2022-01-01},

urldate = {2022-01-01},

booktitle = {2022 International Conference on Electrical and Information Technology (IEIT)},

pages = {414--419},

organization = {IEEE},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Baldoni2022a,

title = {A Semantic Segmentation-based Approach for Train Positioning},

author = {Sara Baldoni and Federica Battisti and Michele Brizzi and Michael Neri and Alessandro Neri},

year  = {2022},

date = {2022-01-01},

booktitle = {Proceedings of the 2022 International Technical Meeting of The Institute of Navigation},

pages = {1380--1391},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Baldoni2022b,

title = {On the Design of High Accuracy Rail Digital Maps based on Sensor Fusion},

author = {Sara Baldoni and Federica Battisti and Michele Brizzi and Giusy Emmanuele and Alessandro Neri and Luca Pallotta and Agostino Ruggeri and Alessia Vennarini},

year  = {2022},

date = {2022-01-01},

booktitle = {Proceedings of the 2022 International Technical Meeting of The Institute of Navigation},

pages = {1420--1431},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}