2022/12/06 by Orcun Cetintas, Cetintas, Orcun, Guillem Brasó +3 · 9 citations
Computer Science · #Video Surveillance and Tracking Methods #Human Pose and Action Recognition #Multimodal Machine Learning Applications
paper · pdf · doi:10.48550/arxiv.2212.03038
Tracking objects over long videos effectively means solving a spectrum of problems, from short-term association for un-occluded objects to long-term association for objects that are occluded and then reappear in the scene. Methods tackling these two tasks are often disjoint and crafted for specific scenarios, and top-performing approaches are often a mix of techniques, which yields engineering-heavy solutions that lack generality. In this work, we question the need for hybrid approaches and introduce SUSHI, a unified and scalable multi-object tracker. Our approach processes long clips by splitting them into a hierarchy of subclips, which enables high scalability. We leverage graph neural networks to process all levels of the hierarchy, which makes our model unified across temporal scales and highly general. As a result, we obtain significant improvements over state-of-the-art on four diverse datasets. Our code and models are available at bit.ly/sushi-mot.