Search Results for author: Shuiwang Li

Found 18 papers, 7 papers with code

Learning Adaptive and View-Invariant Vision Transformer with Multi-Teacher Knowledge Distillation for Real-Time UAV Tracking

1 code implementation28 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.

Knowledge Distillation Visual Tracking

MambaNUT: Nighttime UAV Tracking via Mamba and Adaptive Curriculum Learning

no code implementations1 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.

Domain Adaptation Image Enhancement +1

Camouflaged Object Tracking: A Benchmark

no code implementations25 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.

Object Object Tracking +1

Low-Light Object Tracking: A Benchmark

1 code implementation21 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.

Object Visual Object Tracking +1

Towards Reflected Object Detection: A Benchmark

no code implementations8 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.

Object object-detection +1

Tracking Reflected Objects: A Benchmark

no code implementations7 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.

Autonomous Driving Visual Tracking

Learning Motion Blur Robust Vision Transformers with Dynamic Early Exit for Real-Time UAV Tracking

no code implementations7 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.

Visual Tracking

Tracking Transforming Objects: A Benchmark

1 code implementation28 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.

Towards Discriminative Representations with Contrastive Instances for Real-Time UAV Tracking

no code implementations22 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.

Contrastive Learning

Learning Disentangled Representation with Mutual Information Maximization for Real-Time UAV Tracking

no code implementations20 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.

Model Compression Representation Learning

Tracking Small and Fast Moving Objects: A Benchmark

no code implementations9 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.

Visual Tracking

Rank-Based Filter Pruning for Real-Time UAV Tracking

no code implementations5 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.

Deep Learning Model Compression

SSPNet: Scale Selection Pyramid Network for Tiny Person Detection from UAV Images

2 code implementations4 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.

Human Detection

Equivalence of Correlation Filter and Convolution Filter in Visual Tracking

no code implementations1 May 2021 Shuiwang Li, Qijun Zhao, Ziliang Feng, Li Lu

On the surface, correlation filter and convolution filter are usually used for different purposes.

Edge Detection Visual Tracking

Learning Residue-Aware Correlation Filters and Refining Scale Estimates with the GrabCut for Real-Time UAV Tracking

1 code implementation7 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.

The 1st Tiny Object Detection Challenge:Methods and Results

1 code implementation16 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.

Human Detection Object +2

Cannot find the paper you are looking for? You can Submit a new open access paper.