1 code implementation • 26 Feb 2024 • Yuhao Wang, Lingjuan Miao, Zhiqiang Zhou, Lei Zhang, Yajun Qiao
A language-driven fusion model is then constructed in the embedding space, by establishing the relationship among the embedded vectors to represent the fusion objective and input image modalities.
no code implementations • 10 Feb 2024 • Yifan Zhu, Lingjuan Miao, Haitao Wu, Zhiqiang Zhou, Weiyi Chen, Longwen Wu
Due to the improvement of CNN-based object detection algorithm, the robustness of visual relocalization is greatly enhanced especially in viewpoints where classical methods fail.
1 code implementation • CVPR 2023 • Qi Ming, Lingjuan Miao, Zhe Ma, Lin Zhao, Zhiqiang Zhou, Xuhui Huang, Yuanpei Chen, Yufei Guo
In this paper, we propose a Gradient-Corrected IoU (GCIoU) loss to achieve fast and accurate 3D bounding box regression.
1 code implementation • 22 Mar 2021 • Qi Ming, Lingjuan Miao, Zhiqiang Zhou, Xue Yang, Yunpeng Dong
In this paper, we propose a Representation Invariance Loss (RIL) to optimize the bounding box regression for the rotating objects.
Ranked #27 on Object Detection In Aerial Images on DOTA (using extra training data)
1 code implementation • 18 Jan 2021 • Qi Ming, Lingjuan Miao, Zhiqiang Zhou, Yunpeng Dong
The proposed framework creates more powerful semantic representations for objects in remote sensing images and achieves high-performance real-time object detection.
Ranked #44 on Object Detection In Aerial Images on DOTA (using extra training data)
2 code implementations • 8 Dec 2020 • Qi Ming, Zhiqiang Zhou, Lingjuan Miao, Hongwei Zhang, Linhao Li
With the newly introduced DAL, we achieve superior detection performance for arbitrary-oriented objects with only a few horizontal preset anchors.
Ranked #1 on Multi-Oriented Scene Text Detection on ICDAR2015 (using extra training data)
1 code implementation • 15 Apr 2020 • Linhao Li, Zhiqiang Zhou, Bo wang, Lingjuan Miao, Hua Zong
By contrast, we are able to predict the orientation and other variables independently, and yet more effectively, with a novel dual-branch regression network, based on the observation that the ship targets are nearly rotation-invariant in remote sensing images.