A computer vision software able to analyze images and videos taken from the Galleria Estense Museum in Modena. The final result is intended to guarantee total hardware accessibility, thus imposing a low use of resources as main technical constraint
G. Mancusi's blog Articles.
About me
I am a PhD candidate at the University of Modena and Reggio Emilia (Italy), focusing on Deep Learning and its applications, particularly in fine-tuning large transformer-based models for tracking. My research makes use of Parameter-Efficient Fine-Tuning (PEFT) techniques and Modular Deep Learning strategies to boost the zero-shot capabilities of query-based models for Multiple Object Tracking.