Submission accepted at NVIDIA GTC 2021 (04/12/2021)

Our submission "More Efficient and Accurate Video Networks: A New Approach to Maximize the Accuracy/Computation Tradeoff" has been accepted for oral presentation at NVIDIA GTC 2021, which will take place online on April 12 -16. Watch the talk.

Area Chair ACM Multimedia 2021 (02/28/2021)

I will participate as Area Chair to the 29th ACM International Conference on Multimedia. The deadline for paper submission is Apr. 10, 2021.

Interview with La Repubblica (09/23/2020)

I have been interviewed by Jaime D'Alessandro on Rep: Scienze, about Gpt-3 and Transformed-based language models. You can read the article here.

The first Workshop on Computational Aspects of Deep Learning at ICPR 2020 (07/01/2020)

Together with NVAITC, we are organizing the first Workshop on Computational Aspects of Deep Learning (CADL), which will be hosted at ICPR 2020. See the website for more.

Call for Demo and Exhibit at ICPR 2020 (06/22/2020)

ICPR invites researchers to present live demonstration of their research results and systems. Demos are intended as real, practical, and possibly interactive proofs of the presenters’ research ideas and scientific or engineering contributions. They should provide the audience the opportunity to discuss working systems, applications and prototypes based on leading edge research, and to discuss and interact in first person with the researchers presenting the demo. See the call.

Presenting our Meshed-Memory Transformer at CVPR 2020 (06/20/2020)

We are presenting our work on image captioning at CVPR 2020. Take a look at the video presentation, read the paper and share code!


Associate Editor of Pattern Recognition Letters (02/14/2020)

I have been appointed as Associate Editor at Pattern Recognition Letters.

Our Meshed-Memory Transformer ranks first on the COCO Image Captioning Leaderboard! 🏆 (12/18/2019)

With a CIDEr-D of 1.321, our architecture for image captioning is first on COCO Captioning. See the leaderboard.

Invited talk at Modena Smart Life (09/27/2019)

On September 27th I will give an invited talk at the "Modena Smart Life" festival, on Vision, Language and Embodied AI. See the program of the event for further details.

Interview at Smart City on Radio24 (09/11/2019)

I have been interviewed by Maurizio Melis on Radio24. You can hear the podcast of the interview here.

PersonArt - an interactive demo at Gallerie Estensi (08/09/2019)

From September, 13th to 29th you can discover your doppelgänger in art with our interactive face similarity demo.
See the Gallerie Estensi website for more.

LAMV is being used at Facebook to detect harmful content (08/05/2019)

Our solution for matching and detecting copied videos, published in CVPR 2018, is now being used in production scale at Facebook to detect harmful content.

See the official announcement on the Facebook newsroom website, and the Github repository with the source code.

Tutorial at ICIAP 2019 - "Vision, Language and Action: from Captioning to Embodied AI" (08/04/2019)

See the abstract and program on the tutorial page.

I am co-organizing the first NVIDIA Inception Event in Italy (07/05/2019)

More details at the event page.

One paper accepted as oral at BMVC (with F. Landi and M. Corsini) (07/01/2019)

Two papers (with M. Cornia and M. Tomei) accepted at CVPR 2019! (02/25/2019)

Our paper on Human Eye Fixations Prediction has been accepted at Transactions on Image Processing (TIP)! (06/29/2018)

Our paper on Temporal Match Kernels (with M. Douze and H. Jégou) has been accepted at CVPR 2018! (02/19/2018)

I successfully defended my thesis. (02/13/2018)

I did an internship at FAIR (Facebook AI Research) Paris from July to October 2017 (04/28/2017)

Our paper "Hierarchical Boundary-Aware Neural Encoder for Video Captioning" has been accepted at CVPR 2017 (03/01/2017)

Imagelab will receive a GPU-based server as part of the Facebook AI Research Partnership (08/30/2016)