1 code implementation • 28 Dec 2024 • You Wu, Yongxin Li, Mengyuan Liu, Xucheng Wang, Xiangyang Yang, Hengzhou Ye, Dan Zeng, Qijun Zhao, Shuiwang Li
Specifically, we maximize the MI between the softened feature representations from the multi-teacher models and the student model, leading to improved generalization and performance of the student model, particularly in noisy conditions.
no code implementations • 1 Dec 2024 • You Wu, Xiangyang Yang, Xucheng Wang, Hengzhou Ye, Dan Zeng, Shuiwang Li
Our ACL is composed of two levels of curriculum schedulers: (1) sampling scheduler that transforms the data distribution from imbalanced to balanced, as well as from easier (daytime) to harder (nighttime) samples; (2) loss scheduler that dynamically assigns weights based on data frequency and the IOU.
no code implementations • 25 Aug 2024 • XIAOYU GUO, Pengzhi Zhong, Hao Zhang, Defeng Huang, Huikai Shao, Qijun Zhao, Shuiwang Li
Visual tracking has seen remarkable advancements, largely driven by the availability of large-scale training datasets that have enabled the development of highly accurate and robust algorithms.
1 code implementation • 21 Aug 2024 • Pengzhi Zhong, XIAOYU GUO, Defeng Huang, Xiaojun Peng, Yian Li, Qijun Zhao, Shuiwang Li
We hope that our benchmark and H-DCPT will stimulate the development of novel and accurate methods for tracking objects in low-light conditions.
no code implementations • 8 Jul 2024 • Zhongtian Wang, You Wu, Hui Zhou, Shuiwang Li
Our Reflected Object Detection Dataset (RODD) features a diverse collection of images showcasing reflected objects in various contexts, providing standard annotations for both real and reflected objects.
no code implementations • 7 Jul 2024 • XIAOYU GUO, Pengzhi Zhong, Lizhi Lin, Hao Zhang, Ling Huang, Shuiwang Li
To address this gap, we introduce TRO, a benchmark specifically for Tracking Reflected Objects.
no code implementations • 7 Jul 2024 • You Wu, Xucheng Wang, Dan Zeng, Hengzhou Ye, Xiaolan Xie, Qijun Zhao, Shuiwang Li
Another significant enhancement introduced in this paper is the improved effectiveness of ViTs in handling motion blur, a common issue in UAV tracking caused by the fast movements of either the UAV, the tracked objects, or both.
no code implementations • 12 Jun 2024 • Xiangyang Yang, Dan Zeng, Xucheng Wang, You Wu, Hengzhou Ye, Qijun Zhao, Shuiwang Li
Empowered by transformer-based models, visual tracking has advanced significantly.
1 code implementation • 28 Apr 2024 • You Wu, Yuelong Wang, Yaxin Liao, Fuliang Wu, Hengzhou Ye, Shuiwang Li
We provide carefully hand-annotated bounding boxes for each frame within these sequences, making DTTO the pioneering benchmark dedicated to tracking transforming objects.
no code implementations • 22 Aug 2023 • Dan Zeng, Mingliang Zou, Xucheng Wang, Shuiwang Li
Lightweight Deep learning (DL)-based trackers can achieve a good balance between efficiency and precision but performance gains are limited by the compression rate.
no code implementations • 20 Aug 2023 • Xucheng Wang, Xiangyang Yang, Hengzhou Ye, Shuiwang Li
Efficiency has been a critical problem in UAV tracking due to limitations in computation resources, battery capacity, and unmanned aerial vehicle maximum load.
1 code implementation • ICCV 2023 • Shuiwang Li, Yangxiang Yang, Dan Zeng, Xucheng Wang
In this paper, we propose an efficient ViT-based tracking framework, Aba-ViTrack, for UAV tracking.
no code implementations • 9 Sep 2022 • Zhewen Zhang, Fuliang Wu, Yuming Qiu, Jingdong Liang, Shuiwang Li
The evaluation results exhibit that more effort are required to improve tracking small and fast moving objects.
no code implementations • 5 Jul 2022 • Xucheng Wang, Dan Zeng, Qijun Zhao, Shuiwang Li
Model compression is a promising way to narrow the gap (i. e., effciency, precision) between DCF- and deep learning- based trackers, which has not caught much attention in UAV tracking.
2 code implementations • 4 Jul 2021 • Mingbo Hong, Shuiwang Li, Yuchao Yang, Feiyu Zhu, Qijun Zhao, Li Lu
With the increasing demand for search and rescue, it is highly demanded to detect objects of interest in large-scale images captured by Unmanned Aerial Vehicles (UAVs), which is quite challenging due to extremely small scales of objects.
no code implementations • 1 May 2021 • Shuiwang Li, Qijun Zhao, Ziliang Feng, Li Lu
On the surface, correlation filter and convolution filter are usually used for different purposes.
1 code implementation • 7 Apr 2021 • Shuiwang Li, YuTing Liu, Qijun Zhao, Ziliang Feng
Unmanned aerial vehicle (UAV)-based tracking is attracting increasing attention and developing rapidly in applications such as agriculture, aviation, navigation, transportation and public security.
1 code implementation • 16 Sep 2020 • Xuehui Yu, Zhenjun Han, Yuqi Gong, Nan Jiang, Jian Zhao, Qixiang Ye, Jie Chen, Yuan Feng, Bin Zhang, Xiaodi Wang, Ying Xin, Jingwei Liu, Mingyuan Mao, Sheng Xu, Baochang Zhang, Shumin Han, Cheng Gao, Wei Tang, Lizuo Jin, Mingbo Hong, Yuchao Yang, Shuiwang Li, Huan Luo, Qijun Zhao, Humphrey Shi
The 1st Tiny Object Detection (TOD) Challenge aims to encourage research in developing novel and accurate methods for tiny object detection in images which have wide views, with a current focus on tiny person detection.