1. Slic superpixels compared to state-of-the-art superpixel methods;Achanta;IEEE Trans. Pattern Anal. Mach. Intell.,2012
2. Computing the stereo matching cost with a convolutional neural network;Åbontar,2015
3. Crowdnet: a deep convolutional network for dense crowd counting;Boominathan,2016
4. Dynamic scene understanding for behavior analysis based on string kernels;Brun;IEEE Trans. Circuits Syst. Video Technol.,2014
5. Privacy preserving crowd monitoring: counting people without people models or tracking;Chan,2008