1 code implementation • 3 Aug 2024 • Yuxiang Yang, Yingqi Deng, Jing Zhang, Hongjie Gu, Zhekang Dong
We also introduce a Box-aware Feature Encoding module to encode object size priors into motion estimation.
no code implementations • 29 Apr 2022 • Jiahao Nie, Han Wu, Zhiwei He, Yuxiang Yang, Mingyu Gao, Zhekang Dong
In this paper, to alleviate this misalignment, we propose a novel tracking paradigm, called SiamLA.
1 code implementation • 16 Dec 2021 • Junfan Wang, Yi Chen, Mingyu Gao, Zhekang Dong
Moreover, in practical application, it is difficult for common methods to improve the detection accuracy of multi-scale traffic signs while ensuring real-time detection.