2020
Cermelli, Fabio; Mancini, Massimiliano; Bulò, Samuel Rota; Ricci, Elisa; Caputo, Barbara
Modeling the Background for Incremental Learning in Semantic Segmentation Proceedings Article
In: Computer Vision and Pattern Recognition (CVPR), 2020.
BibTeX | Tags: Computer Science – Computer Vision and Pattern Recognition, Incremental learning, Semantic segmentation
@inproceedings{cermelli2020modeling,
title = {Modeling the Background for Incremental Learning in Semantic Segmentation},
author = {Fabio Cermelli and Massimiliano Mancini and Samuel Rota Bulò and Elisa Ricci and Barbara Caputo},
year = {2020},
date = {2020-06-01},
booktitle = {Computer Vision and Pattern Recognition (CVPR)},
keywords = {Computer Science - Computer Vision and Pattern Recognition, Incremental learning, Semantic segmentation},
pubstate = {published},
tppubtype = {inproceedings}
}
Loghmani, Mohammad Reza; Robbiano, Luca; Planamente, Mirco; Park, Kiru; Caputo, Barbara; Vincze, Markus
Unsupervised Domain Adaptation Through Inter-Modal Rotation for RGB-D Object Recognition Journal Article
In: IEEE Robotics and Automation Letters, vol. 5, no. 4, pp. 6631-6638, 2020.
Links | BibTeX | Tags: IEEE Robotics and Automation Letters, Object recognition, RGB-D perception
@article{loghmani_intermodal_rot_2020,
title = {Unsupervised Domain Adaptation Through Inter-Modal Rotation for RGB-D Object Recognition},
author = {Mohammad Reza Loghmani and Luca Robbiano and Mirco Planamente and Kiru Park and Barbara Caputo and Markus Vincze},
doi = {10.1109/LRA.2020.3007092},
year = {2020},
date = {2020-01-01},
journal = {IEEE Robotics and Automation Letters},
volume = {5},
number = {4},
pages = {6631-6638},
keywords = {IEEE Robotics and Automation Letters, Object recognition, RGB-D perception},
pubstate = {published},
tppubtype = {article}
}
Senese, Matteo A; Benincasa, Alberto; Caputo, Barbara; Rizzo, Giuseppe
A Response Retrieval Approach for Dialogue Using a Multi-Attentive Transformer Journal Article
In: arXiv preprint arXiv:2012.08148, 2020.
BibTeX | Tags: Transformers
@article{senese2020response,
title = {A Response Retrieval Approach for Dialogue Using a Multi-Attentive Transformer},
author = {Matteo A Senese and Alberto Benincasa and Barbara Caputo and Giuseppe Rizzo},
year = {2020},
date = {2020-01-01},
journal = {arXiv preprint arXiv:2012.08148},
keywords = {Transformers},
pubstate = {published},
tppubtype = {article}
}
Fontanel, Dario; Cermelli, Fabio; Mancini, Massimiliano; Rota, Bulò Samuel; Ricci, Elisa; Caputo, Barbara
Boosting Deep Open World Recognition by Clustering Journal Article
In: IEEE Robotics and Automation Letters, vol. 5, pp. 5985-5992, 2020.
BibTeX | Tags: IEEE Robotics and Automation Letters, Object recognition
@article{Fontanel2020BoostingDO,
title = {Boosting Deep Open World Recognition by Clustering},
author = {Dario Fontanel and Fabio Cermelli and Massimiliano Mancini and Bulò Samuel Rota and Elisa Ricci and Barbara Caputo},
year = {2020},
date = {2020-01-01},
journal = {IEEE Robotics and Automation Letters},
volume = {5},
pages = {5985-5992},
keywords = {IEEE Robotics and Automation Letters, Object recognition},
pubstate = {published},
tppubtype = {article}
}
Berton, Gabriele Moreno; Paolicelli, Valerio; Masone, Carlo; Caputo, Barbara
Adaptive-Attentive Geolocalization from few queries: a hybrid approach Journal Article
In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 2918–2927, 2020, (arXiv:2010.06897).
Links | BibTeX | Tags: CVF Winter Conference on Applications of Computer Vision
@article{berton_adaptive-attentive_2020,
title = {Adaptive-Attentive Geolocalization from few queries: a hybrid approach},
author = {Gabriele Moreno Berton and Valerio Paolicelli and Carlo Masone and Barbara Caputo},
url = {http://arxiv.org/abs/2010.06897},
year = {2020},
date = {2020-01-01},
urldate = {2020-11-11},
journal = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},
pages = {2918--2927},
note = {arXiv:2010.06897},
keywords = {CVF Winter Conference on Applications of Computer Vision},
pubstate = {published},
tppubtype = {article}
}
Planamente, Mirco; Bottino, Andrea; Caputo, Barbara
Self-Supervised Joint Encoding of Motion and Appearance for First Person Action Recognition Journal Article
In: arXiv:2002.03982 [cs], 2020, (arXiv: 2002.03982).
Links | BibTeX | Tags: Computer Science – Computer Vision and Pattern Recognition, First Person Action Recognition
@article{planamente_self-supervised_2020,
title = {Self-Supervised Joint Encoding of Motion and Appearance for First Person Action Recognition},
author = {Mirco Planamente and Andrea Bottino and Barbara Caputo},
url = {http://arxiv.org/abs/2002.03982},
year = {2020},
date = {2020-01-01},
urldate = {2020-12-15},
journal = {arXiv:2002.03982 [cs]},
note = {arXiv: 2002.03982},
keywords = {Computer Science - Computer Vision and Pattern Recognition, First Person Action Recognition},
pubstate = {published},
tppubtype = {article}
}
Bucci, Silvia; Loghmani, Mohammad Reza; Tommasi, Tatiana
On the Effectiveness of Image Rotation for Open Set Domain Adaptation Proceedings Article
In: European Conference on Computer Vision, pp. 422–438, Springer 2020.
BibTeX | Tags: Domain adaptation, European Conference on Computer Vision
@inproceedings{bucci2020effectiveness,
title = {On the Effectiveness of Image Rotation for Open Set Domain Adaptation},
author = {Silvia Bucci and Mohammad Reza Loghmani and Tatiana Tommasi},
year = {2020},
date = {2020-01-01},
booktitle = {European Conference on Computer Vision},
pages = {422--438},
organization = {Springer},
keywords = {Domain adaptation, European Conference on Computer Vision},
pubstate = {published},
tppubtype = {inproceedings}
}
D’Innocente, Antonio; Borlino, Francesco Cappio; Bucci, Silvia; Caputo, Barbara; Tommasi, Tatiana
One-Shot Unsupervised Cross-Domain Detection Proceedings Article
In: European Conference on Computer Vision — ECCV 2020, pp. 732–748, Springer International Publishing, Cham, 2020, ISBN: 978-3-030-58517-4.
Abstract | BibTeX | Tags: European Conference on Computer Vision
@inproceedings{10.1007/978-3-030-58517-4_43,
title = {One-Shot Unsupervised Cross-Domain Detection},
author = {Antonio D'Innocente and Francesco Cappio Borlino and Silvia Bucci and Barbara Caputo and Tatiana Tommasi},
isbn = {978-3-030-58517-4},
year = {2020},
date = {2020-01-01},
booktitle = {European Conference on Computer Vision -- ECCV 2020},
pages = {732--748},
publisher = {Springer International Publishing},
address = {Cham},
abstract = {Despite impressive progress in object detection over the last years, it is still an open challenge to reliably detect objects across visual domains. All current approaches access a sizable amount of target data at training time. This is a heavy assumption, as often it is not possible to anticipate the domain where a detector will be used, nor to access it in advance for data acquisition. Consider for instance the task of monitoring image feeds from social media: as every image is uploaded by a different user it belongs to a different target domain that is impossible to foresee during training. Our work addresses this setting, presenting an object detection algorithm able to perform unsupervised adaptation across domains by using only one target sample, seen at test time. We introduce a multi-task architecture that one-shot adapts to any incoming sample by iteratively solving a self-supervised task on it. We further enhance this auxiliary adaptation with cross-task pseudo-labeling. A thorough benchmark analysis against the most recent cross-domain detection methods and a detailed ablation study show the advantage of our approach.},
keywords = {European Conference on Computer Vision},
pubstate = {published},
tppubtype = {inproceedings}
}
Borlino, Francesco Cappio; D’Innocente, Antonio; Tommasi, Tatiana
Rethinking Domain Generalization Baselines Proceedings Article
In: International Association for Pattern Recognition (ICPR), 2020.
Links | BibTeX | Tags: International Association for Pattern Recognition
@inproceedings{borlino2021rethinking,
title = {Rethinking Domain Generalization Baselines},
author = {Francesco Cappio Borlino and Antonio D'Innocente and Tatiana Tommasi},
url = {https://ailb-web.ing.unimore.it/icpr/author/1593},
year = {2020},
date = {2020-01-01},
booktitle = {International Association for Pattern Recognition (ICPR)},
journal = {International Association for Pattern Recognition (ICPR)},
keywords = {International Association for Pattern Recognition},
pubstate = {published},
tppubtype = {inproceedings}
}
Alliegro, Antonio; Boscaini, Davide; Tommasi, Tatiana
Joint Supervised and Self-Supervised Learning for 3D Real-World Challenges Proceedings Article
In: International Association for Pattern Recognition (ICPR), 2020.
BibTeX | Tags: International Association for Pattern Recognition
@inproceedings{Alliegro2020JointSA,
title = {Joint Supervised and Self-Supervised Learning for 3D Real-World Challenges},
author = {Antonio Alliegro and Davide Boscaini and Tatiana Tommasi},
year = {2020},
date = {2020-01-01},
booktitle = {International Association for Pattern Recognition (ICPR)},
journal = {International Association for Pattern Recognition (ICPR) - Oral},
volume = {abs/2004.07392},
keywords = {International Association for Pattern Recognition},
pubstate = {published},
tppubtype = {inproceedings}
}
Borlino, Francesco Cappio; D’Innocente, Antonio; Tommasi, Tatiana
Domain Generalization vs Data Augmentation: An Unbiased Perspective Proceedings Article
In: European Conference on Computer Vision Workshop, pp. 726–730, Springer 2020.
BibTeX | Tags:
@inproceedings{borlino2020domain,
title = {Domain Generalization vs Data Augmentation: An Unbiased Perspective},
author = {Francesco Cappio Borlino and Antonio D’Innocente and Tatiana Tommasi},
year = {2020},
date = {2020-01-01},
booktitle = {European Conference on Computer Vision Workshop},
pages = {726--730},
organization = {Springer},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Fontanel, Dario; Cermelli, Fabio; Mancini, Massimiliano; Caputo, Barbara
On the Challenges of Open World Recognition Under Shifting Visual Domains Journal Article
In: IEEE Robotics and Automation Letters, vol. 6, no. 2, pp. 604–611, 2020.
BibTeX | Tags: Cross-domain, IEEE Robotics and Automation Letters, Open-world
@article{fontanel2020challenges,
title = {On the Challenges of Open World Recognition Under Shifting Visual Domains},
author = {Dario Fontanel and Fabio Cermelli and Massimiliano Mancini and Barbara Caputo},
year = {2020},
date = {2020-01-01},
journal = {IEEE Robotics and Automation Letters},
volume = {6},
number = {2},
pages = {604--611},
publisher = {IEEE},
keywords = {Cross-domain, IEEE Robotics and Automation Letters, Open-world},
pubstate = {published},
tppubtype = {article}
}
Cermelli, Fabio; Mancini, Massimiliano; Xian, Yongqin; Akata, Zeynep; Caputo, Barbara
Prototype-based Incremental Few-Shot Semantic Segmentation Journal Article
In: arXiv preprint arXiv:2012.01415, 2020.
BibTeX | Tags:
@article{cermelli2020prototype,
title = {Prototype-based Incremental Few-Shot Semantic Segmentation},
author = {Fabio Cermelli and Massimiliano Mancini and Yongqin Xian and Zeynep Akata and Barbara Caputo},
year = {2020},
date = {2020-01-01},
journal = {arXiv preprint arXiv:2012.01415},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Duan, Anqing; Camoriano, Raffaello; Ferigo, Diego; Huang, Yanlong; Calandriello, Daniele; Rosasco, Lorenzo; Pucci, Daniele
Learning to Avoid Obstacles with Minimal Intervention Control Journal Article
In: Frontiers in Robotics and AI, vol. 7, 2020, ISSN: 2296-9144, (Publisher: Frontiers).
Abstract | Links | BibTeX | Tags: humanoid robots, minimal intervention control, obstacle avoidance, Programming by Demonstration, Robotics
@article{duan_learning_2020,
title = {Learning to Avoid Obstacles with Minimal Intervention Control},
author = {Anqing Duan and Raffaello Camoriano and Diego Ferigo and Yanlong Huang and Daniele Calandriello and Lorenzo Rosasco and Daniele Pucci},
url = {https://www.frontiersin.org/articles/10.3389/frobt.2020.00060/abstract},
doi = {10.3389/frobt.2020.00060},
issn = {2296-9144},
year = {2020},
date = {2020-01-01},
urldate = {2020-01-01},
journal = {Frontiers in Robotics and AI},
volume = {7},
abstract = {Programming by demonstration has received much attention as it offers a general framework which allows robots to efficiently acquire novel motor skills from a human teacher. While traditional imitation learning that only focuses on either Cartesian or joint space might become inappropriate in situations where both spaces are equally important (e.g. writing or striking task), hybrid imitation learning of skills in both Cartesian and joint spaces simultaneously has been studied recently. However, an important issue which often arises in dynamical or unstructured environments is overlooked, namely how can a robot avoid obstacles? In this paper, we aim to address the problem of avoiding obstacles in the context of hybrid imitation learning. Specifically, we propose to tackle three subproblems: (i) designing a proper potential field so as to bypass obstacles, (ii) guaranteeing joint limits are respected when adjusting trajectories in the process of avoiding obstacles, and (iii) determining proper control commands for robots such that potential human-robot interaction is safe. By solving the aforementioned subproblems, the robot is capable of generalizing observed skills to new situations featuring obstacles in a feasible and safe manner. The effectiveness of the proposed method is validated through a toy example as well as a real transportation experiment on the iCub humanoid robot.},
note = {Publisher: Frontiers},
keywords = {humanoid robots, minimal intervention control, obstacle avoidance, Programming by Demonstration, Robotics},
pubstate = {published},
tppubtype = {article}
}
2019
Cermelli, Fabio; Mancini, Massimiliano; Ricci, Elisa; Caputo, Barbara
The RGB-D Triathlon: Towards Agile Visual Toolboxes for Robots Journal Article
In: 2019.
BibTeX | Tags: RGB-D perception
@article{cermelli2019rgb,
title = {The RGB-D Triathlon: Towards Agile Visual Toolboxes for Robots},
author = {Fabio Cermelli and Massimiliano Mancini and Elisa Ricci and Barbara Caputo},
year = {2019},
date = {2019-11-01},
booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
keywords = {RGB-D perception},
pubstate = {published},
tppubtype = {article}
}
Loghmani, Mohammad Reza; Planamente, Mirco; Caputo, Barbara; Vincze, Markus
Recurrent Convolutional Fusion for RGB-Đ Object Recognition Journal Article
In: IEEE Robotics and Automation Letters, vol. 4, no. 3, pp. 2878–2885, 2019, ISSN: 2377-3766, (Conference Name: IEEE Robotics and Automation Letters).
Links | BibTeX | Tags: Clutter, Data mining, Feature extraction, IEEE Robotics and Automation Letters, Object recognition, Object recognition, RGB-D perception, Robot sensing systems, Task analysis, Visual learning
@article{loghmani_recurrent_2019,
title = {Recurrent Convolutional Fusion for RGB-Đ Object Recognition},
author = {Mohammad Reza Loghmani and Mirco Planamente and Barbara Caputo and Markus Vincze},
doi = {10.1109/LRA.2019.2921506},
issn = {2377-3766},
year = {2019},
date = {2019-01-01},
journal = {IEEE Robotics and Automation Letters},
volume = {4},
number = {3},
pages = {2878--2885},
note = {Conference Name: IEEE Robotics and Automation Letters},
keywords = {Clutter, Data mining, Feature extraction, IEEE Robotics and Automation Letters, Object recognition, Object recognition, RGB-D perception, Robot sensing systems, Task analysis, Visual learning},
pubstate = {published},
tppubtype = {article}
}
Carlucci, Fabio M; D’Innocente, Antonio; Bucci, Silvia; Caputo, Barbara; Tommasi, Tatiana
Domain generalization by solving jigsaw puzzles Proceedings Article
In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2229–2238, 2019.
BibTeX | Tags: CVF Winter Conference on Applications of Computer Vision, Domain adaptation
@inproceedings{carlucci2019domain,
title = {Domain generalization by solving jigsaw puzzles},
author = {Fabio M Carlucci and Antonio D'Innocente and Silvia Bucci and Barbara Caputo and Tatiana Tommasi},
year = {2019},
date = {2019-01-01},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
pages = {2229--2238},
keywords = {CVF Winter Conference on Applications of Computer Vision, Domain adaptation},
pubstate = {published},
tppubtype = {inproceedings}
}
Bucci, Silvia; D’Innocente, Antonio; Tommasi, Tatiana
Tackling partial domain adaptation with self-supervision Proceedings Article
In: International Conference on Image Analysis and Processing, pp. 70–81, Springer 2019.
BibTeX | Tags: Domain adaptation
@inproceedings{bucci2019tackling,
title = {Tackling partial domain adaptation with self-supervision},
author = {Silvia Bucci and Antonio D’Innocente and Tatiana Tommasi},
year = {2019},
date = {2019-01-01},
booktitle = {International Conference on Image Analysis and Processing},
pages = {70--81},
organization = {Springer},
keywords = {Domain adaptation},
pubstate = {published},
tppubtype = {inproceedings}
}
Tommasi, Tatiana; Mallya, Arun; Plummer, Bryan; Lazebnik, Svetlana; Berg, Alexander C; Berg, Tamara L
Combining Multiple Cues for Visual Madlibs Question Answering Journal Article
In: International Journal of Computer Vision, vol. 127, no. 1, pp. 38–60, 2019, ISSN: 0920-5691.
@article{ttommasi_ijcv2019,
title = {Combining Multiple Cues for Visual Madlibs Question Answering},
author = {Tatiana Tommasi and Arun Mallya and Bryan Plummer and Svetlana Lazebnik and {Alexander C } Berg and {Tamara L } Berg},
doi = {10.1007/s11263-018-1096-0},
issn = {0920-5691},
year = {2019},
date = {2019-01-01},
journal = {International Journal of Computer Vision},
volume = {127},
number = {1},
pages = {38--60},
publisher = {Springer Netherlands},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Planamente, Mirco; Russo, Paolo; Caputo, Barbara
Leveraging over depth in egocentric activity recognition Proceedings Article
In: First Italian Conference on Robotics and Intelligent Machines, 2019.
BibTeX | Tags: Action Recognition
@inproceedings{planamente2019leveraging,
title = {Leveraging over depth in egocentric activity recognition},
author = {Mirco Planamente and Paolo Russo and Barbara Caputo},
year = {2019},
date = {2019-01-01},
booktitle = {First Italian Conference on Robotics and Intelligent Machines},
keywords = {Action Recognition},
pubstate = {published},
tppubtype = {inproceedings}
}
Mancini, Massimiliano; Porzi, Lorenzo; Cermelli, Fabio; Caputo, Barbara
Discovering latent domains for unsupervised domain adaptation through consistency Proceedings Article
In: International Conference on Image Analysis and Processing, pp. 390–401, Springer, Cham 2019.
BibTeX | Tags:
@inproceedings{mancini2019discovering,
title = {Discovering latent domains for unsupervised domain adaptation through consistency},
author = {Massimiliano Mancini and Lorenzo Porzi and Fabio Cermelli and Barbara Caputo},
year = {2019},
date = {2019-01-01},
booktitle = {International Conference on Image Analysis and Processing},
pages = {390--401},
organization = {Springer, Cham},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
2018
Masone, Carlo; Mohammadi, Mostafa; Giordano, Paolo Robuffo; Franchi, Antonio
Shared planning and control for mobile robots with integral haptic feedback Journal Article
In: The International Journal of Robotics Research, vol. 37, no. 11, pp. 1395–1420, 2018.
BibTeX | Tags:
@article{masone2018shared,
title = {Shared planning and control for mobile robots with integral haptic feedback},
author = {Carlo Masone and Mostafa Mohammadi and Paolo Robuffo Giordano and Antonio Franchi},
year = {2018},
date = {2018-01-01},
journal = {The International Journal of Robotics Research},
volume = {37},
number = {11},
pages = {1395--1420},
publisher = {SAGE Publications Sage UK: London, England},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2016
Tommasi, Tatiana; Mallya, Arun; Plummer, Bryan; Lazebnik, Svetlana; Berg, Alexander; Berg, Tamara
Solving VIsual Madlibs with Multiple Cues Proceedings Article
In: Wilson, Edwin Hancock R Richard C.; Smith, William A P (Ed.): Proceedings of the British Machine Vision Conference (BMVC), pp. 77.1-77.13, BMVA Press, 2016, ISBN: 1-901725-59-6.
@inproceedings{BMVC2016_77,
title = {Solving VIsual Madlibs with Multiple Cues},
author = {Tatiana Tommasi and Arun Mallya and Bryan Plummer and Svetlana Lazebnik and Alexander Berg and Tamara Berg},
editor = {Edwin Hancock R Richard C. Wilson and William A P Smith},
url = {https://dx.doi.org/10.5244/C.30.77},
doi = {10.5244/C.30.77},
isbn = {1-901725-59-6},
year = {2016},
date = {2016-09-01},
booktitle = {Proceedings of the British Machine Vision Conference (BMVC)},
pages = {77.1-77.13},
publisher = {BMVA Press},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Masone, Carlo; Bülthoff, Heinrich H; Stegagno, Paolo
Cooperative transportation of a payload using quadrotors: A reconfigurable cable-driven parallel robot Proceedings Article
In: 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1623–1630, IEEE 2016.
BibTeX | Tags:
@inproceedings{masone2016cooperative,
title = {Cooperative transportation of a payload using quadrotors: A reconfigurable cable-driven parallel robot},
author = {Carlo Masone and Heinrich H Bülthoff and Paolo Stegagno},
year = {2016},
date = {2016-01-01},
booktitle = {2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
pages = {1623--1630},
organization = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}