About
I'm a 22-year-old Computer Science Master's student at the Department of Mathematics and Computer Science of the University of Catania and a member of the LIVE research group within the Image Processing Laboratory (IPLAB). My work is focused on Deep Learning and Computer Vision, with particular interest in Vision-Language Models for egocentric video understanding and in intelligent assistive systems designed to support users during complex procedural tasks.
Interests Egocentric vision · Vision-language models · Human-object interaction anticipation · Procedural task assistance
News
-
Sep 2026
Won the Best Poster Award at VISMAC 2026
Awarded at the International Summer School on Machine Vision, in Siena.
-
Sep 2026
Attending VISMAC 2026
I'll be attending the International Summer School on Machine Vision, organized by CVPL, from 21 to 25 September in Siena.
-
Aug 2026
Attended ICPR 2026
Took part in the 28th International Conference on Pattern Recognition, in Lyon, where our work on gaze and Set-of-Mark prompting was presented.
-
Aug 2026
ICPR 2026 paper published by Springer Nature
My first official publication is now out in the conference proceedings, in the Lecture Notes in Computer Science series.
-
Jul 2026
Archimede Prize for best B.Sc. graduate
Awarded the 22nd edition Archimede Prize (Premio Archimede) as the top Computer Science bachelor's graduate at UniCT, class of 2024-25.
-
Jul 2026
Attending ICVSS 2026
Taking part in the 20th International Computer Vision Summer School, in Punta Sampieri, Sicily.
-
May 2026
EgoInteract preprint released on arXiv
Synthetic Egocentric Videos Generation for Interaction Understanding and Anticipation, in collaboration with Meta Reality Labs.
-
Apr 2026
Paper accepted at ICPR 2026
Leveraging Gaze and Set-of-Mark in VLLMs for Human-Object Interaction Anticipation from Egocentric Videos, the outcome of my bachelor thesis. I'll present it in Lyon in August.
-
Apr 2026
Started a Research Scholarship at UniCT
On multimodal LLMs for procedural task assistance and mistake detection, within the LIVE@IPLAB group at DMI.
-
Jul 2025
Graduated B.Sc. in Computer Science
With a thesis titled "Predicting Next-Active Objects with Vision Large Language Models in Egocentric Scenarios", supervised by Prof. Francesco Ragusa and Prof. Giovanni Maria Farinella.
Publications
-
EgoInteract: Synthetic Egocentric Videos Generation for Interaction Understanding and Anticipation
arXiv preprint 2605.18214 Under Review
@article{leonardi2026egointeract, title={EgoInteract: Synthetic Egocentric Videos Generation for Interaction Understanding and Anticipation}, author={Leonardi, Rosario and Ragusa, Francesco and Materia, Daniele and Passanisi, Alessandro and Fort, James and Engel, Jakob and Farinella, Giovanni Maria}, journal={arXiv preprint arXiv:2605.18214}, year={2026} } -
Leveraging Gaze and Set-of-Mark in VLLMs for Human-Object Interaction Anticipation from Egocentric Videos
ICPR 2026 · Springer LNCS Published
@inproceedings{materia2026leveraging, author = {Materia, Daniele and Ragusa, Francesco and Farinella, Giovanni Maria}, editor = {De Marsico, Maria and Ho, Tin Kam and Jurie, Frederic and Liu, Cheng-Lin and Lopresti, Daniel and Nystr{\"o}m, Ingela and Ogier, Jean-Marc and Ross, Arun and Wang, Liang}, title = {Leveraging Gaze and Set-of-Mark in VLLMs for Human-Object Interaction Anticipation from Egocentric Videos}, booktitle = {Pattern Recognition}, series = {Lecture Notes in Computer Science}, publisher = {Springer Nature Switzerland}, address = {Cham}, year = {2026}, pages = {139--154}, isbn = {978-3-032-31404-8}, doi = {10.1007/978-3-032-31404-8_10} }
Awards & honors
- Sep 2026 Best Poster Award VISMAC 2026, International Summer School on Machine Vision
- Jul 2026 Archimede Prize University of Catania Top Computer Science bachelor's graduate, class of 2024-25.
Background
- Apr 2026 – now Research Scholar LIVE@IPLAB, University of Catania Multimodal learning for procedural task assistance and mistake detection.
- Current M.Sc. in Computer Science University of Catania
- Jul 2025 B.Sc. in Computer Science University of Catania 110/110 cum laude. Thesis: Predicting Next-Active Objects with Vision Large Language Models in Egocentric Scenarios.
- Feb – Jun 2025 Student Researcher (internship) Next Vision s.r.l. Multimodal LLM-based computer vision, with a focus on object anticipation in egocentric vision.
Contact
I'm always glad to discuss research, collaborations, or new opportunities. Email is the best way to reach me, and I read every message.
- University
- daniele.materia@studium.unict.it
- Personal
- danielemateria14@gmail.com