no code implementations • CVPR 2017 • Donghun Yeo, Jeany Son, Bohyung Han, Joon Hee Han
We propose a simple but effective tracking-by-segmentation algorithm using Absorbing Markov Chain (AMC) on superpixel segmentation, where target state is estimated by a combination of bottom-up and top-down approaches, and target segmentation is propagated to subsequent frames in a recursive manner.
no code implementations • NeurIPS 2014 • Woonhyun Nam, Piotr Dollar, Joon Hee Han
In fact, orthogonal trees with our locally decorrelated features outperform oblique trees trained over the original features at a fraction of the computational cost.
Ranked #32 on Pedestrian Detection on Caltech
no code implementations • 4 Jun 2014 • Woonhyun Nam, Piotr Dollár, Joon Hee Han
In fact, orthogonal trees with our locally decorrelated features outperform oblique trees trained over the original features at a fraction of the computational cost.
no code implementations • CVPR 2013 • Suha Kwak, Bohyung Han, Joon Hee Han
We present a joint estimation technique of event localization and role assignment when the target video event is described by a scenario.