The CiTIUS celebrates another year of recognition for another thesis from the center in the Extraordinary Doctorate Awards of the University of Santiago de Compostela. After the granting of this award to two doctoral works in the previous edition, the thesis of CiTIUS graduate researcher Lorenzo Vaquero joins this trajectory of excellence and also receives backing for his doctoral work, developed at CiTIUS of the University of Santiago de Compostela, a center co-financed by the European Union through the Galicia Feder Program 2021-2027. The award, of an annual nature, is intended for those doctoral works rated with the highest score by the tribunal, and that have also received the "Cum Laude" mention and a sum of 12 points or higher in evaluations issued by its members. Under the title Visual Multi-Object Tracking through Deep Learning, and under the supervision of CiTIUS researchers Manuel Mucientes Molina and Víctor Manuel Brea Sánchez, the thesis presents deep learning solutions for real-time tracking of multiple objects in videos, an essential component in applications like robotics or video surveillance.

The work proposes innovative approaches to improve traditional detection systems, which rely on frame-by-frame systems ('frame a frame') and geometric attributes, which are not suitable for real-time environments, nor for open set scenarios. To address the limitations of these conventional systems, Lorenzo Vaquero's doctoral work gave rise to SiamMT, an architecture that adapts single-object tracking techniques to handle multiple targets. This idea was later refined with the introduction of SiamMOTION, which improves performance by managing actors and accommodating objects of diverse sizes. Finally, a Transformer-based architecture was introduced to complement a lightweight detector, improving the recovery of undetected objects and overall tracking performance.

It all started with a summer scholarship...

Lorenzo Vaquero's research career began with his participation in the CiTIUS Summer Fellowships, which allowed him to delve into the research field that eventually led to his thesis. Previously, during his Bachelor's and Master's training, Lorenzo specialized in the fields of Computer Vision and Artificial Intelligence, receiving two more awards during this formative stage: the highest state award in mobility and accessibility from the Renault Foundation and the ‘Club de Excelencia en Sostenibilidad’ (Best STEM Final Degree Project) and the DXC Spain award for the best Master's Final Project (TFM) from the Interuniversity Master's in Big Data. Currently, Lorenzo remains linked to CiTIUS as an external associate researcher and works as a postdoctoral researcher at the Fondazione Bruno Kessler in Trento, Italy, where he manages various international projects focusing on human-centered computer vision.

The researcher highlighted "the impetus this award represents for continuing to explore new frontiers in the world of technology and science," expressing his satisfaction with this recognition. "I feel immense excitement and gratitude," he added, "for continuing to collaborate with the wonderful CiTIUS community." Reflections full of praise, which also included words of thanks to his supervisors: "I want to express my deep gratitude to USC, CiTIUS, my thesis directors, Manuel Mucientes and Víctor Brea, as well as all the colleagues and friends who made this journey possible." The award will be presented by the International Doctorate School of USC (EDIUS) during a ceremony scheduled for next June.