no code implementations • 5 Feb 2023 • Tao Wang, Kean Chen, Weiyao Lin, John See, Zenghui Zhang, Qian Xu, Xia Jia
As such, we propose a novel framework that can effectively predict and mask-out the noisy and confusing detection results before associating the objects into trajectories.
1 code implementation • ICCV 2021 • Tao Wang, Ning Xu, Kean Chen, Weiyao Lin
Specifically, graph nodes representing instance features are used for detection and segmentation while graph edges representing instance relations are used for tracking.
1 code implementation • 17 Aug 2020 • Kean Chen, Weiyao Lin, Jianguo Li, John See, Ji Wang, Junni Zou
This paper alleviates this issue by proposing a novel framework to replace the classification task in one-stage detectors with a ranking task, and adopting the Average-Precision loss (AP-loss) for the ranking problem.
1 code implementation • ECCV 2020 • Zhiming Chen, Kean Chen, Weiyao Lin, John See, Hui Yu, Yan Ke, Cong Yang
The experimental results show that PIoU loss can dramatically improve the performance of OBB detectors, particularly on objects with high aspect ratios and complex backgrounds.
1 code implementation • CVPR 2019 • Kean Chen, Jianguo Li, Weiyao Lin, John See, Ji Wang, Ling-Yu Duan, Zhibo Chen, Changwei He, Junni Zou
For this purpose, we develop a novel optimization algorithm, which seamlessly combines the error-driven update scheme in perceptron learning and backpropagation algorithm in deep networks.