no code implementations • 19 Jul 2021 • Na Li, Xinbo Zhao
We collect a new gait recognition database called OG RGB+D database, which breaks through the limitation of other gait databases and includes multimodal gait data of various occlusions (self-occlusion, active occlusion, and passive occlusion) by our multiple synchronous Azure Kinect DK sensors data acquisition system (multi-Kinect SDAS) that can be also applied in security situations.
no code implementations • 17 May 2021 • Weiquan Huang, Yan Bai, Qiuyu Ren, Xinbo Zhao, Ming Feng, Yin Wang
In particular, most existing unsupervised and domain adaptation ReID methods utilize only the public datasets in their experiments, with labels removed.
no code implementations • 26 Apr 2021 • Aiqing Fang, Xinbo Zhao, Jiaqi Yang, Yanning Zhang
In addition, a dynamic degradation kernel is proposed to improve the robustness of image restoration and fusion.
no code implementations • 5 Oct 2020 • Aiqing Fang, Xinbo Zhao, Jiaqi Yang, Beibei Qin, Yanning Zhang
Finally, we explore the commonness and characteristics of different image fusion tasks, which provides a research basis for further research on the continuous learning characteristics of human brain in the field of image fusion.
no code implementations • 17 Jul 2020 • Aiqing Fang, Xinbo Zhao, Jiaqi Yang, Shihao Cao, Yanning Zhang
Firstly, the relationship between human brain cognitive mechanism and image fusion task is analyzed and a physical model is established to simulate human brain cognitive mechanism.
no code implementations • 27 Apr 2020 • Na Li, Xinbo Zhao, Chong Ma
However, appearance features suffer from external factors which can cause drastic appearance variations, e. g. clothing.
no code implementations • 23 Dec 2019 • Aiqing Fang, Xinbo Zhao, Yanning Zhang
In order to improve the robustness and contextual awareness of image fusion tasks, we proposed a multi-task auxiliary learning image fusion theory guided by subjective attention.
no code implementations • 23 Dec 2019 • Aiqing Fang, Xinbo Zhao, Jiaqi Yang, Yanning Zhang
The human visual perception system has strong robustness in image fusion.
no code implementations • 18 Dec 2019 • Aiqing Fang, Xinbo Zhao, Jiaqi Yang, Yanning Zhang
The characteristics of feature selection, nonlinear combination and multi-task auxiliary learning mechanism of the human visual perception system play an important role in real-world scenarios, but the research of image fusion theory based on the characteristics of human visual perception is less.