Showing cs.CVShow all
2 papers · 1 filter
cs.CV2024★ 1 cited
FlowCLAS: Enhancing Normalizing Flow Via Contrastive Learning For Anomaly Segmentation
Chang Won Lee, Selina Leveugle, Svetlana Stolpner +4
Anomaly segmentation is an essential capability for safety-critical robotics applications that must be aware of unexpected events. Normalizing flows (NFs), a class of generative mo…
cs.CV2024
UncertaintyTrack: Exploiting Detection and Localization Uncertainty in Multi-Object Tracking
Chang Won Lee, Steven L. Waslander
Multi-object tracking (MOT) methods have seen a significant boost in performance recently, due to strong interest from the research community and steadily improving object detectio…