no code implementations • 17 Mar 2024 • Guangze Zheng, ShiJie Lin, Haobo Zuo, Changhong Fu, Jia Pan
Most methods that solely depend on coarse-grained object cues, such as boxes and the overall appearance of the object, are susceptible to degradation due to distorted internal relationships of dynamic objects.
1 code implementation • 3 Jul 2023 • Changhong Fu, Liangliang Yao, Haobo Zuo, Guangze Zheng, Jia Pan
However, the state-of-the-art (SOTA) DA still lacks the potential object with accurate pixel-level location and boundary to generate the high-quality target domain training sample.
1 code implementation • 20 Mar 2023 • Junjie Ye, Changhong Fu, Ziang Cao, Shan An, Guangze Zheng, Bowen Li
To realize reliable UAV tracking at night, a spatial-channel Transformer-based low-light enhancer (namely SCT), which is trained in a novel task-inspired manner, is proposed and plugged prior to tracking approaches.
1 code implementation • 8 Mar 2023 • Liangliang Yao, Changhong Fu, Sihang Li, Guangze Zheng, Junjie Ye
The proposed method designs a new task-specific object saliency mining network to refine the cross-correlation operation and effectively discriminate foreground and background information.
1 code implementation • 26 Nov 2022 • Guangze Zheng, Changhong Fu, Junjie Ye, Bowen Li, Geng Lu, Jia Pan
The key to the visual UAM approaching lies in object tracking, while current UAM tracking typically relies on costly model-based methods.
1 code implementation • 14 Aug 2022 • Changhong Fu, Haolin Dong, Junjie Ye, Guangze Zheng, Sihang Li, Jilin Zhao
Pixel-level range mask is introduced to make HighlightNet more focused on the enhancement of the tracking object and regions without light sources.
1 code implementation • 9 May 2022 • Changhong Fu, Kunhan Lu, Guangze Zheng, Junjie Ye, Ziang Cao, Bowen Li, Geng Lu
Unmanned aerial vehicle (UAV)-based visual object tracking has enabled a wide range of applications and attracted increasing attention in the field of intelligent transportation systems because of its versatility and effectiveness.
2 code implementations • CVPR 2022 • Junjie Ye, Changhong Fu, Guangze Zheng, Danda Pani Paudel, Guang Chen
Previous advances in object tracking mostly reported on favorable illumination circumstances while neglecting performance at nighttime, which significantly impeded the development of related aerial robot applications.
1 code implementation • 30 Jul 2021 • Junjie Ye, Changhong Fu, Guangze Zheng, Ziang Cao, Bowen Li
Recent years have witnessed the fast evolution and promising performance of the convolutional neural network (CNN)-based trackers, which aim at imitating biological visual systems.
1 code implementation • 15 Jun 2021 • Guangze Zheng, Changhong Fu, Junjie Ye, Fuling Lin, Fangqiang Ding
However, prevalent discriminative correlation filter (DCF) based trackers are insensitive to target mutations due to a predefined label, which concentrates on merely the centre of the training region.