Massimiliano Mancini

Contact and personal infos: Advisor:  Barbara Caputo
Research Area:
Deep Learning, Domain Adaptation, Incremental Learning
Interests:
Deep Neural Networks, Computer Vision

Activities
Participation to PhD school
DescriptionExternal siteYear
Regularization Methods for Machine Learning (DIBRIS, University of Genoa)Link2016
International Computer Vision Summer SchoolLink2017
Participation to conferences/workshops
DescriptionExternal siteYear
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)Link2017
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)Link2018
IEEE International Conference on Computer Vision (ICCV)Link2017
European Conference on Computer Vision (ECCV)Link2018
Workshop on Transferring and Adapting Source Knowledge in Computer Vision (TASK-CV)Link2018
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)Link2019
IEEE International Conference on Robotics and Automation (ICRA)Link2019
Long stay visiting research periods
DescriptionExternal siteYear
Visiting Ph.D. student at the Department of Robotics, Perception and Learning, KTH Royal Institute of Technology in StockholmLink2018

Publications
Title Autor(s) Published in Year
1Knowledge is Never Enough: Towards Web Aided Deep Open World RecognitionM Mancini, H Karaoguz, E Ricci, P Jensfelt, B CaputoIEEE International Conference on Robotics and Automation (ICRA)2019
2AdaGraph: Unifying Predictive and Continuous Domain Adaptation through GraphsM Mancini, S. Rota Bul?, B Caputo, E RicciIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)2019
3Inferring Latent Domains for Unsupervised Deep Domain AdaptationM Mancini, L Porzi, S. Rota Bulo, B Caputo, E RicciIEEE transactions on Pattern Analysis and Machine Intelligence2019
4The RGB-D Triathlon: Towards Agile Visual Toolboxes for RobotsF Cermelli, M Mancini, E Ricci, B CaputoIEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)2019
5Robust Place Categorization with Deep Domain GeneralizationM. Mancini, S. Rota Bulo', B. Caputo, E. RicciIEEE Robotics and Automation Letters2018
6Boosting Domain Adaptation by Discovering Latent DomainsM. Mancini, L. Porzi, S. Rota Bulo', B. Caputo, E. RicciIEEE Conference on Computer Vision and Pattern Recognition (CVPR)2018
7Best sources forward: domain generalization through source-specific netsM. Mancini, S. Rota Bulo', B. Caputo, E. RicciIEEE International Conference on Image Processing2018
8Kitting in the Wild through Online Domain AdaptationM. Mancini, H. Karaoguz, E. Ricci, P. Jensfelt, B. CaputoIEEE/RSJ International Conference on Intelligent Robots and Systems2018
9Adding New Tasks to a Single Network with Weight Transformations using Binary MasksM. Mancini, E. Ricci, B. Caputo, S. Rota Bulo'Workshop on Transferring and Adapting Source Knowledge in Computer Vision2018
10Learning Deep NBNN Representations for Robust Place CategorizationM. Mancini, S. Rota Bulo', E. Ricci, B. CaputoIEEE Robotics and Automation Letters (presented at IROS 2017)2017
11Embedding Words and Sense Together via Joint Knowledge-Enhanced TrainingM. Mancini, J. Camacho-Collados, I. Iacobacci, R. NavigliConference on Computational Natural Language Learning (CoNLL)2017