Alberto Baldrati
PhD student at the University of Florence and University of Pisa, Italy
Hello! 👋
I am Alberto Baldrati, a third-year PhD student enrolled in the AI Italian National Doctorate program based at the University of Pisa. In practice, I am hosted by the University of Florence and work at the Media Integration and Communication Center (MICC) under the supervision of Prof. Marco Bertini. I also closely collaborate with Lorenzo Agnolucci and Davide Morelli.
Previously, I obtained my MSc in Computer Science and Engineering magna cum laude at the University of Florence under the supervision of Prof. Marco Bertini and Prof. Alberto Del Bimbo with a thesis titled “Deep Learning techniques for image retrieval using joint textual and visual encoders”.
My main research interests revolve around vision and language, with a particular focus on vision and language pretraining and composed image retrieval, and fashion image generation, with a particular focus on multimodal fashion image editing and virtual try-on.
Currently interning as a Computer Vision Research Scientist at Huawei Finland Research Center.
If you wish to learn more about my research or explore potential collaborations, please feel free to reach out via email!
News
Mar 21, 2024 | One paper about multimodal fashion image editing released on arXiv. |
---|---|
Mar 18, 2024 | Joined Huawei as a Research Scientist Intern, based in Helsinki, Finland. |
Aug 16, 2023 | Two papers about prompt learning and hateful meme classification accepted at the CLVL workshop at ICCV 2023. |
Jul 26, 2023 | One paper about virtual try-on accepted at ACM Multimedia 2023. |
Jul 13, 2023 | Two papers accepted at ICCV 2023: one about composed image retrieval and the other one about multimodal fashion image editing |