1 code implementation • CVPR 2019 • Zhen He, Jian Li, Daxue Liu, Hangen He, David Barber
To achieve both label-free and end-to-end learning of MOT, we propose a Tracking-by-Animation framework, where a differentiable neural model first tracks objects from input frames and then animates these objects into reconstructed frames.
no code implementations • NeurIPS 2017 • Zhen He, Shao-Bing Gao, Liang Xiao, Daxue Liu, Hangen He, David Barber
The capacity of an LSTM network can be increased by widening and adding layers.
no code implementations • 29 Sep 2017 • Keyu Lu, Jianhui Chen, James J. Little, Hangen He
Vision based player detection is important in sports applications.
no code implementations • 30 Oct 2016 • Keyu Lu, Jian Li, Xiangjing An, Hangen He
This paper presents a generalized Haar filter based deep network which is suitable for the object detection tasks in traffic scene.
no code implementations • 6 May 2016 • Jian Li, Martin Levine, Xiangjing An, Xin Xu, Hangen He
First, we consider saliency detection as a frequency domain analysis problem.