top of page


Schermata del 2023-05-18 11-17-48.png
Schermata del 2023-01-21 00-40-12.png

"CrimeNet: Neural Structured Learning using Vision Transformer for
violence detection

F. Cappio Borlino, S. Polizzotto, B. Caputo, T. Tommasi F. J. Rendón-Segador, J. A. Álvarez-García , J. L. Salazar-González, T. Tommasi

Neural Networks, 2022


"Self-supervision & meta-learning for one-shot unsupervised cross-domain detection"

F. Cappio Borlino, S. Polizzotto, B. Caputo, T. Tommasi

Computer Vision and Image Understanding, 2022

DOI: (arXiv) (code)

Schermata del 2023-01-21 00-14-22.png

"End-to-end learning to grasp via sampling from object point clouds"

A. Alliegro, M. Rudorfer, F. Frattin, A. Leonardis, T. Tommasi

IEEE Robotics and Automation Letters 7 (4), 9865-9872, 2022

DOI: 10.1109/LRA.2022.3191183 (arXiv) (code) (video)


"Self-Supervised Learning Across Domains"

S. Bucci, A. D'Innocente, Y. Liao, F. M. Carlucci, B. Caputo, T. Tommasi

IEEE Transaction on Pattern Analysis and Machine Intelligence, 2021

DOI: 10.1109/TPAMI.2021.3070791 (arXiv)


"Positive-Unlabeled Learning for Open Set Domain Adaptation"

M. R. Loghmani, M. Vincze, T. Tommasi

Pattern Recognition Letters (PRL), 2020

DOI: 10.1016/j.patrec.2020.06.003 

"Combining Multiple Cues for Visual Madlibs Question Answering"

T. Tommasi, A. Mallya, B. Plummer, S. Lazebnik, A. C. Berg, T. L. Berg

accepted at International Journal of Computer Vision (IJCV), 2018

DOI: 10.1007/s11263-018-1096-0   (arXiv Version here)

"What Would They Say? Predicting User’s Comments in Pinterest"

J. C. Gomez, T. Tommasi, S. Zoghbi and M. F. Moens

IEEE Latin America Transactions 14(4):2013-2019, 2016.DOI: 10.1109/TLA.2016.7483548

"Joint cross-domain classification and subspace learning for unsupervised adaptation"

B. Fernando, T. Tommasi, T. Tuytelaars, Pattern Recognition Letters, July 2015. DOI: 10.1016/j.patrec.2015.07.009. 

(arXiv Version here)

"Location Recognition Over Large Time Lags"

B. Fernando, T. Tommasi, T. Tuytelaars. Computer Vision and Image Understanding, June 2015. DOI: 10.1016/j.cviu.2015.05.016. 

(arXiv Version here)

"Learning Categories from few Examples with Multi Model Knowledge Transfer" T. Tommasi, F. Orabona, B. Caputo, IEEE Transactions on Pattern Analysis and Machine Intelligence,  36(5): 928-941, 2014.

"Improving Control of Dexterous Hand Prostheses Using Adaptive Learning"

 T. Tommasi, F. Orabona, C. Castellini, B. Caputo, IEEE Transactions on Robotics, 29(1):207–219, 2012.

"Using Object Affordances to Improve Object Recognition",

C. Claudio, T. Tommasi, N. Noceti, F. Odone, B. Caputo, IEEE Transactions on Autonomous Mental Development, 3(3):207–215, 2011.

"Learning Methods for Melanoma Recognition",

E. La Torre, B. Caputo, T. Tommasi, International Journal of Imaging Systems and Technology, 20(4):316–322, 2010.

"Discriminative Cue Integration for Medical Image Annotation",

T. Tommasi, F. Orabona, B. Caputo, Pattern Recognition Letters, 29(15):1996–2002, 2008. Winner of the Idiap Best Paper Award 2008.


"Contrastive Learning for Cross-Domain Open World Recognition"

F. Cappio Borlino, S. Bucci, T. Tommasi

IEEE IROS 2022 (code) (video)


"Denoise and Contrast for Category Agnostic Shape Completion"

A. Alliegro, D. Valsesia, G. Fracastoro, E. Magli, T. Tommasi

CVPR 2021 (arXiv)

Schermata del 2020-09-05 18-19-52.png

"One-Shot Unsupervised Cross-Domain Detection"

A. D'Innocente, F. C. Borlino, S. Bucci, B. Caputo, T. Tommasi

ECCV 2020

Schermata del 2020-09-05 18-26-50.png

"Rethinking Domain Generalization Baselines"

F. Cappio Borlino, A. D'Innocente, T. Tommasi

ICPR 2020


"Joint Supervised and Self-Supervised Learning for 3D Real World Challenges"

A. Alliegro, D. Boscaini, T. Tommasi

ICPR 2020 (Oral)

Screen Shot 2021-01-14 at 2.24.06 AM.png

"Bridging the gap between natural and medical images through deep colorization"

L. Morra, L. Piano, F. Lamberti, T. Tommasi

ICPR 2020  (arXiv)

Schermata del 2020-09-05 18-08-38.png

"Towards Multi-source Adaptive Semantic Segmentation"

P. Russo, T. Tommasi, B. Caputo

ICIAP 2019


"Tackling Partial Domain Adaptation with Self-Supervision"

S. Bucci, A. D'Innocente, T. Tommasi

Oral at ICIAP 2019.  (arXivWinner of the Best Paper Award!


"Domain Generalization by Solving Jigsaw Puzzles"

F. M. Carlucci, A. D'Innocente, S. Bucci, B. Caputo, T. Tommasi

Oral at CVPR 2019 (arXiv)

"From source to target and back: Symmetric Bi-Directional Adaptive GAN"

P. Russo, F. M. Carlucci, T. Tommasi, B. Caputo

CVPR 2018.  (arXiv)

"Adaptive Deep Learning Through Visual Domain Localization"

G. Angeletti, B. Caputo, T. Tommasi

ICRA 2018 (arXiv)

"Learning Deep Visual Object Models From Noisy Web Data: How to Make it Work"

N. Massouh, F. Babiloni, T. Tommasi, J. Young, N. Hawes and B. Caputo

IROS 2017 (arXiv)

"Solving Visual Madlibs with Multiple Cues"

T. Tommasi, A. Mallya, B. Plummer, S. Lazebnik, A. C. Berg, T. L. Berg,

BMVC 2016.  (arXiv)

"Active Transfer Learning with Zero-Shot Priors: Reusing Past Datasets for Future Tasks"

E. Gavves, T. Mensink, T. Tommasi, C. G. M. Snoek and T. Tuytelaars

To appear in ICCV 2015 (arXiv, spotlight, poster)

"A Deeper Look at Dataset Bias"

T. Tommasi, N. Patricia, B. Caputo, T. Tuytelaars, GCPR 2015.  (suppl, arXiv)

"Multi-Souce Adaptive Learning for Fast Control of Prosthetics Hand"

 N. Patricia, T. Tommasi, B. Caputo, ICPR 2014.

"Frustratingly Easy NBNN Domain Adaptation"

T. Tommasi, B. Caputo, ICCV 2013.

"Beyond Dataset Bias: Multi-task Unaligned Shared Knowledge Transfer"

T. Tommasi, N. Quadrianto, B. Caputo, C.H. Lampert, ACCV 2012.

"Leveraging over Prior Knowledge for Online Learning of Visual

Categories"  T. Tommasi, F. Orabona, M. Kaboli, B. Caputo, BMVC 2012.

"Multiclass Transfer Learning from Unconstrained Priors"

L. Jie*, T. Tommasi*, B. Caputo, ICCV 2011. (* equal authors listed in alphabetic order)

"Object Recognition using Visuo-Affordance Maps"

A. Gijsberts, T. Tommasi, G. Metta, B. Caputo, IROS 2010

"Kernel Methods for Melanoma Recognition",

E. La Torre, T. Tommasi, B. Caputo, G.E. Gigante, MIE 2006.

Workshop Papers & Minor Conferences

"Online vs. Offline Adaptive Domain Randomization Benchmark"

G. Tiboni, K. Arndt, G. Averta, V. Kyrki, T. Tommasi

International Workshop on Human-Friendly Robotics, 2022


Schermata del 2023-01-21 01-42-56.png

"Transient-Fault-Aware Design and Training to Enhance DNNs Reliability with Zero-Overhead"

N. Cavagnero, F. dos Santos, M. Ciccone, G. Averta, T. Tommasi, P. Rech

International Symposium on On-Line Testing and Robust System Design (IOLTS), 2022. (arXiv)

Schermata del 2023-01-21 01-34-52.png

"Multi-Modal RGB-D Scene Recognition Across Domains"

A. Ferreri, S. Bucci, T. Tommasi

Deep Multi-Task Learning in Computer Vision (DeepMTL) workshop, ICCV 2021


"Hallucinating Agnostic Images to Generalize Across Domains"

F. M. Carlucci, P. Russo, T. Tommasi, B. Caputo,

TASK-CV Workshop at ICCV 2019

(arXiv Version)


"Domain Generalization by Solving Jigsaw Puzzles"

S. Bucci, T. Tommasi

Poster at the Women in Computer Vision Workshop, CVPR 2019


"Learning the Roots of Visual Domain Shift"

T. Tommasi, M. Lanzi, P. Russo, B. Caputo, TASK-CV Workshop at ECCV 2016.

(arXiv Version)

"A Testbed for Cross-Dataset Analysis"

T. Tommasi, T. Tuytelaars, TASK-CV Workshop at ECCV 2014.

Project Page

"Beyond Metadata: Searching your Archive based on its Audio-Visual Content", T. Tommasi, R. Aly, K. McGuinness, K. Chatfield, R. Arandjelovic, O. Parkhi, R. Ordelman, A. Zisserman, T. Tuytelaars, IBC 2014.

AXES Project Page

"Does Evolution cause a Domain Shift?",

K. Rematas, B. Fernando, T. Tommasi, T. Tuytelaars, VisDA Workshop at ICCV 2013.

Project Page

"Transferring Activities: Updating Human Behavior Analysis",

F. Nater*, T. Tommasi*, H. Grabner, L. Van Gool, B. Caputo, VS Workshop at ICCV 2011. (* equal authors listed in alphabetic order)

"Towards a quantitative measure of rareness",

T. Tommasi, B. Caputo, DIRAC Workshop at ECML 2010. (Included in "Detection and Identification of Rare Audiovisual Cues", volume 384 of Studies in Computational Intelligence, Springer, (2012)

"Overview of the CLEF 2009 Medical Image Annotation Track",

T. Tommasi, B. Caputo, P. Welter , Mark Oliver Güld and Thomas M. Deserno, CLEF workshop 2009.   ImageCLEF Webpage

"An SVM Confidence-Based Approach to Medical Image Annotation",

T. Tommasi, F. Orabona, B. Caputo, CLEF workshop 2008.

"Cue Integration for Medical Image Annotation",

T. Tommasi, F. Orabona, B. Caputo, CLEF workshop 2007.

Book Chapters

Schermata del 2023-01-21 01-52-06.png

"Visual Domain Adaptation in the Deep Learning Era",

G.Csurka, T. M Hospedales, M. Salzmann, T. Tommasi

Morgan & Claypool Publishers

Springer Link

"A deeper Look at Dataset Bias",

T. Tommasi, N. Patricia, B. Caputo, T. Tuytelaars

Domain Adaptation in Computer Vision Applications, 37-55, September 2017.

Link to the Springer Series "Advances in Computer Vision and Pattern Recognition"

"Learning to learn new models of human activities in indoor settings",

F. Nater, T. Tommasi, L. Van Gool, and B. Caputo, Multimodal Interactive Systems Management, 156-172, September 2013.

Link to the EPFL-Press Book Chapter

"The Medical Image Classification Task",

T. Tommasi, T. Deselaers, ImageCLEF: The Information Retrieval Series, Volume 32, Part 2, 221-238, 2010.

"Idiap on Medical Image Classification",

T. Tommasi, F. Orabona, ImageCLEF: The Information Retrieval Series, Volume 32, Part 3, 453-465, 2010.

bottom of page