%0 Conference Proceedings
%T Leveraging Unlabeled Data for Crowd Counting by Learning to Rank
%A Xialei Liu
%A Joost Van de Weijer
%A Andrew Bagdanov
%B 31st IEEE Conference on Computer Vision and Pattern Recognition
%D 2018
%F Xialei Liu2018
%O LAMP; 600.109; 600.106; 600.120
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=3159), last updated on Tue, 08 Feb 2022 14:03:24 +0100
%X We propose a novel crowd counting approach that leverages abundantly available unlabeled crowd imagery in a learning-to-rank framework. To induce a ranking ofcropped images , we use the observation that any sub-image of a crowded scene image is guaranteed to contain the same number or fewer persons than the super-image. This allows us to address the problem of limited size of existingdatasets for crowd counting. We collect two crowd scene datasets from Google using keyword searches and queryby-example image retrieval, respectively. We demonstrate how to efficiently learn from these unlabeled datasets by incorporating learning-to-rank in a multi-task network which simultaneously ranks images and estimates crowd density maps. Experiments on two of the most challenging crowd counting datasets show that our approach obtains state-ofthe-art results.
%K Task analysis
%K Training
%K Computer vision
%K Visualization
%K Estimation
%K Head
%K Context modeling
%U http://refbase.cvc.uab.es/files/LWB2018.pdf
%U http://dx.doi.org/10.1109/CVPR.2018.00799
%P 7661-7669