no code implementations • 27 May 2018 • Xinfeng Zhang, Su Yang, Xinjian Zhang, Weishan Zhang, Jiulong Zhang
In crowded scenes, detection and localization of abnormal behaviors is challenging in that high-density people make object segmentation and tracking extremely difficult.
no code implementations • 28 Feb 2018 • Wenshan Wang, Su Yang, Weishan Zhang, Jiulong Zhang
Through multi-task learning, the proposed models can rate aesthetic images as well as produce comments in an end-to-end manner.