Showing cs.CVShow all
2 papers · 1 filter
cs.CV2019
StampNet: unsupervised multi-class object discovery
Joost Visser, Alessandro Corbetta, Vlado Menkovski +1
Unsupervised object discovery in images involves uncovering recurring patterns that define objects and discriminates them against the background. This is more challenging than imag…
cs.CV2018
Accurate pedestrian localization in overhead depth images via Height-Augmented HOG
Werner Kroneman, Alessandro Corbetta, Federico Toschi
We tackle the challenge of reliably and automatically localizing pedestrians in real-life conditions through overhead depth imaging at unprecedented high-density conditions. Levera…