As a Ph.D. candidate specializing in machine learning and computer vision, my research endeavors focus on advancing the capabilities of surveillance systems through the application of cutting-edge computer vision mechanisms and models. At the heart of my work lies the quest to enhance scene object detection and scene understanding, integral components of modern surveillance technology. The overarching goal of my doctoral project is to contribute to the refinement of surveillance systems, enabling them to operate with increased precision, efficiency, and adaptability.