1. Institute of Advanced Study of Mathematics, Harbin Institute of Technology, 47822 Harbin, Heilongjiang, China, (e-mail: huan.xiong.math@gmail.com)
2. Computer Vision Research Group, Inception Institute of Artificial Intelligence, Abu Dhabi, Abu Dhabi, United Arab Emirates, (e-mail: mengyang.yu@inceptioniai.org)
3. Computer Vision Research Group, Inception Institute of Artificial Intelligence, Abu Dhabi, Abu Dhabi, United Arab Emirates, (e-mail: liuli1213@gmail.com)
4. Computer Vision Research Group, Inception Institute of Artificial Intelligence, Abu Dhabi, Abu Dhabi, United Arab Emirates, (e-mail: fan.zhu@inceptioniai.org)
5. Computer Vision Research Group, Inception Institute of Artificial Intelligence, Abu Dhabi, Abu Dhabi, United Arab Emirates, (e-mail: qinjiebuaa@gmail.com)
6. School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China, 611731 (e-mail: fumin.shen@gmail.com)
7. Computer Vision Research Group, Inception Institute of Artificial Intelligence, Abu Dhabi, Abu Dhabi, United Arab Emirates, (e-mail: ling.shao@ieee.org)