From Lab to Street：Transferable and Privacy-friendly Deep Learning for Urban Surveillance
My PhD dissertation at Ghent University, organized as three method-level directions that share a common deployment setting. The directions emerged from the SenseCity deployment study and address two structural problems revealed there - context drift across sites, and the impossibility of enumerating in advance.
Jun 30, 2025
Embedding-based pair generation for contrastive representation learning in audio-visual surveillance data
To address the challenges of false negatives and information bottlenecks in audio-visual contrastive learning for smart city surveillance, this work proposes a novel method that generates semantically synchronized pairs via cross-modal embedding distance, yielding general-purposes representations that achieve competitive performance on multiple downstream tasks.
Jan 13, 2025