Paper: https://arxiv.org/pdf/2401.03191.pdf In the rapidly evolving landscape of computer vision, the pursuit of accurate per-object distance estimation stands as a cornerstone for safety-critical applications, ranging from autonomous driving to surveillance and robotics. The nuances of long-range object detection, occlusion challenges, …
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.