PT Unknown
AU Xialei Liu
   Joost Van de Weijer
   Andrew Bagdanov
TI Leveraging Unlabeled Data for Crowd Counting by Learning to Rank
BT 31st IEEE Conference on Computer Vision and Pattern Recognition
PY 2018
BP 7661
EP 7669
DI 10.1109/CVPR.2018.00799
DE Task analysis; Training; Computer vision; Visualization; Estimation; Head; Context modeling
AB 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.
ER