Mattia Soldan is a Ph.D. student at King Abdullah University of Science and Technology (KAUST). Under the supervision of Bernard Ghanem, Mattia is part of the Image and Video Understanding Lab (IVUL). Mattia received his MSc degree in Telecommunication Engineering and his BSc degree in Information Engineering from the University of Padova. His research interests include Computer Vision and Natural Language Processing. Mattia aims at leveraging Deep Learning techniques to solve relevant multidisciplinary problems as Natural Language Video Grounding. See the list of publications for a glimpse at his work.
PhD in Electrical and Computer Engineering
King Abdullah University of Science and Technology, Thuwal (Saudi Arabia)
MSc in Telecommunication Engineering, 2017
University of Padova, Padova (Italy)
BSc in Information Engineering, 2015
University of Padova, Padova (Italy)
[2022-09-14] EgoVLP accepted at NeurIPS. (preprint, code).[2022-08-17] Completed another Ph.D. milestone by succesfully defending my Ph.D. proposal and earning the title of Ph.D. Candidate.[2022-07-29] I gave a talk about my research at the Machine Learning and Computer Vision Group lead by Professor Dima Damen at the University of Bristol.[2022-07-11] Started my internship at Samsung AI - Cambridge (website).[2022-06-30] EgoVLP code release (GitHub).[2022-06-21] EgoVLP won 1st place in Multi-Instance Retrieval @ EPIC-Kitchens Challenge 2022, hosted by CVPR 2022.[2022-06-20] EgoVLP won 1st place in OSCC, 2nd place in NLQ & 3rd place in PNR @ Ego4D Challenge 2022, hosted by CVPR 2022.[2022-06-19] Attended my first (in-person) CVPR paper where I presented MAD.[2022-06-03] Published a new preprint: “EgoVLP: Egocentric Video-Language Pretraining” (preprint).[2022-03-15] I gave a talk about my research at the Rising Stars in AI Symposium @ KAUST. See my talk here.[2022-03-02] “MAD: A Scalable Dataset for Language Grounding in Videos from Movie Audio Descriptions” accepted in CVPR22 (preprint).[2022-02-23] Updated version of “Finding Moments in Video Collections Using Natural Language” is on ArXiv (preprint).