12/18/2019 · Our Meshed-Memory Transformer ranks first on the COCO Image Captioning Leaderboard! 🏆
With a CIDEr-D of 1.321, our architecture for image captioning is first on COCO Captioning. See the leaderboard.
08/05/2019 · LAMV is being used at Facebook to detect harmful content
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.
07/16/2019 · The call for Demo and Exhibit for ICPR 2020 is online
We are looking for exciting demos and demonstrations by June 15th 2020. See the call.
09/27/2019 · Invited talk at Modena Smart Life
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.
09/11/2019 · Interview at Smart City on Radio24
I have been interviewed by Maurizio Melis on Radio24. You can hear the podcast of the interview here.
Older news can be found in the news archive.
Complete list is available in the publications page.
Vision and Cognitive Systems (2019/2020)
Laurea Magistrale in Ingegneria Informatica
Rita Cucchiara, Lorenzo Baraldi
- Fundamentals of Computer Science I, Assistant (2018)
- Computer Vision, Laboratory lecturer (2018)
- Fundamentals of Computer Science I, Tutor (2017)
- Computer Vision, Laboratory lecturer (2017)
- Fundamentals of Computer Science I, Tutor (2016)
- Computer Vision, Laboratory lecturer (2016)
- Visual Computing and Multimedia Technologies, Laboratory lecturer (2015)
- Machine Learning and Patter Recognition, Teaching assistant (2015) - three lectures on Deep Learning and Convolutional Neural Networks [Lab notes]
- Fundamentals of Computer Science I, Tutor (2015)
- Computer Vision, Laboratory lecturer (2015)