Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
Semantics-Guided Multimodal Masked Autoencoder Pretraining for 3D BEV Object Detection
Prabuddhi Wariyapperuma, Rajitha de Silva, Marc Hanheide +2
Accurate 3D bird's-eye view (BEV) object detection is essential for autonomous driving, and depends strongly on effective multimodal representations from complementary sensors such…
cs.CV2026
Getting the Numbers Right$\unicode{x2014}$Modelling Multi-Class Object Counting in Dense and Varied Scenes
Villanelle O'Reilly, Jonathan Cox, Georgios Leontidis +3
Density map estimation enables accurate object counting in heavily occluded, and densely packed scenes where detection-based counting fails. In multi-class density estimation, clas…