88 citations · 209 across the 21 of their papers we have counts for
21 papers
Bio-Inspired Simple Neural Network for Low-Light Image Restoration: A Minimalist Approach
Junjie Ye, Jilin Zhao
In this study, we explore the potential of using a straightforward neural network inspired by the retina model to efficiently restore low-light images. The retina model imitates th…
Tracker Meets Night: A Transformer Enhancer for UAV Tracking
Junjie Ye, Changhong Fu, Ziang Cao +3
Most previous progress in object tracking is realized in daytime scenes with favorable illumination. State-of-the-arts can hardly carry on their superiority at night so far, thereb…
Out-of-distribution Detection with Implicit Outlier Transformation
Qizhou Wang, Junjie Ye, Feng Liu +5
Outlier exposure (OE) is powerful in out-of-distribution (OOD) detection, enhancing detection capability via model fine-tuning with surrogate OOD data. However, surrogate data typi…
SGDViT: Saliency-Guided Dynamic Vision Transformer for UAV Tracking
Liangliang Yao, Changhong Fu, Sihang Li +2
Vision-based object tracking has boosted extensive autonomous applications for unmanned aerial vehicles (UAVs). However, the dynamic changes in flight maneuver and viewpoint encoun…
Exploit CAM by itself: Complementary Learning System for Weakly Supervised Semantic Segmentation
Jiren Mai, Fei Zhang, Junjie Ye +5
Weakly Supervised Semantic Segmentation (WSSS) with image-level labels has long been suffering from fragmentary object regions led by Class Activation Map (CAM), which is incapable…
Siamese Object Tracking for Vision-Based UAM Approaching with Pairwise Scale-Channel Attention
Guangze Zheng, Changhong Fu, Junjie Ye +3
Although the manipulating of the unmanned aerial manipulator (UAM) has been widely studied, vision-based UAM approaching, which is crucial to the subsequent manipulating, generally…
PVT++: A Simple End-to-End Latency-Aware Visual Tracking Framework
Bowen Li, Ziyuan Huang, Junjie Ye +4
Visual object tracking is essential to intelligent robots. Most existing approaches have ignored the online latency that can cause severe performance degradation during real-world…
HighlightNet: Highlighting Low-Light Potential Features for Real-Time UAV Tracking
Changhong Fu, Haolin Dong, Junjie Ye +3
Low-light environments have posed a formidable challenge for robust unmanned aerial vehicle (UAV) tracking even with state-of-the-art (SOTA) trackers since the potential image feat…
Local Perception-Aware Transformer for Aerial Tracking
Changhong Fu, Weiyu Peng, Sihang Li +2
Transformer-based visual object tracking has been utilized extensively. However, the Transformer structure is lack of enough inductive bias. In addition, only focusing on encoding…
Siamese Object Tracking for Unmanned Aerial Vehicle: A Review and Comprehensive Analysis
Changhong Fu, Kunhan Lu, Guangze Zheng +4
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 sy…
Unsupervised Domain Adaptation for Nighttime Aerial Tracking
Junjie Ye, Changhong Fu, Guangze Zheng +2
Previous advances in object tracking mostly reported on favorable illumination circumstances while neglecting performance at nighttime, which significantly impeded the development…
Ad2Attack: Adaptive Adversarial Attack on Real-Time UAV Tracking
Changhong Fu, Sihang Li, Xinnan Yuan +3
Visual tracking is adopted to extensive unmanned aerial vehicle (UAV)-related applications, which leads to a highly demanding requirement on the robustness of UAV trackers. However…
HiFT: Hierarchical Feature Transformer for Aerial Tracking
Ziang Cao, Changhong Fu, Junjie Ye +2
Most existing Siamese-based tracking methods execute the classification and regression of the target object based on the similarity maps. However, they either employ a single map f…
ARShoe: Real-Time Augmented Reality Shoe Try-on System on Smartphones
Shan An, Guangfu Che, Jinghao Guo +7
Virtual try-on technology enables users to try various fashion items using augmented reality and provides a convenient online shopping experience. However, most previous works focu…
SiamAPN++: Siamese Attentional Aggregation Network for Real-Time UAV Tracking
Ziang Cao, Changhong Fu, Junjie Ye +2
Recently, the Siamese-based method has stood out from multitudinous tracking methods owing to its state-of-the-art (SOTA) performance. Nevertheless, due to various special challeng…
DarkLighter: Light Up the Darkness for UAV Tracking
Junjie Ye, Changhong Fu, Guangze Zheng +2
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.…
Mutation Sensitive Correlation Filter for Real-Time UAV Tracking with Adaptive Hybrid Label
Guangze Zheng, Changhong Fu, Junjie Ye +2
Unmanned aerial vehicle (UAV) based visual tracking has been confronted with numerous challenges, e.g., object motion and occlusion. These challenges generally introduce unexpected…
ADTrack: Target-Aware Dual Filter Learning for Real-Time Anti-Dark UAV Tracking
Bowen Li, Changhong Fu, Fangqiang Ding +2
Prior correlation filter (CF)-based tracking methods for unmanned aerial vehicles (UAVs) have virtually focused on tracking in the daytime. However, when the night falls, the track…
Predictive Visual Tracking: A New Benchmark and Baseline Approach
Bowen Li, Yiming Li, Junjie Ye +2
As a crucial robotic perception capability, visual tracking has been intensively studied recently. In the real-world scenarios, the onboard processing time of the image streams ine…
All-Day Object Tracking for Unmanned Aerial Vehicle
Bowen Li, Changhong Fu, Fangqiang Ding +2
Visual object tracking, which is representing a major interest in image processing field, has facilitated numerous real world applications. Among them, equipping unmanned aerial ve…
Siamese Anchor Proposal Network for High-Speed Aerial Tracking
Changhong Fu, Ziang Cao, Yiming Li +2
In the domain of visual tracking, most deep learning-based trackers highlight the accuracy but casting aside efficiency. Therefore, their real-world deployment on mobile platforms…