OITrack: Multi-Object Tracking for Small Targets in Satellite Video via Online Trajectory Completion and Iterative Expansion over Union by Weishan Lu, Xueying Wang, Wei An, Chao Xiao, Qian Yin, Guoliang Zhang

“…Multi-object tracking (MOT) in satellite videos presents significant challenges, including small target sizes, dense distributions, and complex motion patterns. To address these issues, we propose OITrack, an improved tracking framework that integrates a Trajectory Completion Module (TCM), an Adaptive Kalman Filter (AKF), and an Iterative Expansion Intersection over Union Strategy (I-EIoU) strategy. …”
Get full text

A human pose estimation network based on YOLOv8 framework with efficient multi-scale receptive field and expanded feature pyramid network by Shaobin Cai, Han Xu, Wanchen Cai, Yuchang Mo, Liansuo Wei

“…First, the EMRF module is employed to further enhance the model’s feature representation capability. …”
Get full text

Breast Cancer Classification With Enhanced Interpretability: DALAResNet50 and DT Grad-CAM by Suxing Liu, Galib Muhammad Shahriar Himel, Jiahao Wang

“…This is achieved by employing skip connections to mitigate vanishing gradient issues, enabling the integration of low-level and high-level feature information. …”
Get full text

Traffic flow prediction based on spatial-temporal multi factor fusion graph convolutional networks by Ying-Ting Chen, An Liu, Cheng Li, Shuang Li, Xiao Yang

“…To address the above issues, we proposed a spatial-temporal multi factor fusion graph convolution network (STFGCN), which is composed of multi factor graph fusion module, the GCN based on the auto-regressive moving average (ARMA) filter and the gated recurrent unit (GRU). …”
Get full text

Knowledge distillation-enhanced marine optical remote sensing object detection with transformer and dual-path architecture by Yubin Yuan, Yiquan Wu, Langyue Zhao, Yuqi Liu, Jinlin Chen

“…The encoder integrates a Holistic Focal Feature Interwined (HFFI) module that employs parallel pathways to progressively refine local textures and global semantic representations, enabling adaptive feature fusion across spatial hierarchies. …”
Get full text

INFLUENCE OF THE SMALL HYDROPOWER STATIONS ON THE HYDROLOGIC PROCESSES IN THE SERET RIVER (LEFT TRIBUTARY OF THE DNISTER RIVER) by Olha Pylypovych, Andrii Mykhnovych, Yuriy Andreychuk, Uliana Morozovs’ka

Get full text

Accurate Detection and Tracking of Small-Scale Vehicles in High-Altitude Unmanned Aerial Vehicle Bird-View Imagery by Heshan Zhang, Xin Tan, Mengwei Fan, Cunshu Pan, Zhanji Zheng, Shuang Luo, Jin Xu

“…A convolutional block attention module (CBAM) is inserted in front of the neck network to select crucial information for vehicle detection tasks while suppressing noncritical ones. …”
Get full text

A compressed image encryption algorithm leveraging optimized 3D chaotic maps for secure image communication by Akshat Tiwari, Prachi Diwan, Tarun Dhar Diwan, Mahdal Miroslav, S. P. Samal

“…In this paper, a chaotic map-based encryption technique is presented as a solution to these issues. The proposed algorithm termed as OptiSecure-3D presents optimized parameter-based 3D chaotic maps for image encryption. …”
Get full text

Thermal analysis of lithium-ion batteries using forced-air cooling and circular fin systems: A numerical study by Allaa Abdulqadir Omar, Ahmed Mohammed Adham

“…A novel cooling technique utilizing circular fins and smooth pipe design is demonstrated to tackle the issues of temperature rise and uneven temperature uniformity in typical air-cooled battery thermal management systems. …”
Get full text

Detection of Crack Sealant in the Pretreatment Process of Hot In-Place Recycling of Asphalt Pavement via Deep Learning Method by Kai Zhao, Tianzhen Liu, Xu Xia, Yongli Zhao

“…However, during asphalt pavement hot in-place recycling (HIR), irregular shapes and random distribution of crack sealants can cause issues like agglomeration and ignition. To address these problems, it is necessary to mill large areas containing crack sealant or pre-mark locations for removal after heating. …”
Get full text

SPS-RCNN: Semantic-Guided Proposal Sampling for 3D Object Detection from LiDAR Point Clouds by Hengxin Xu, Lei Yang, Shengya Zhao, Shan Tao, Xinran Tian, Kun Liu

“…In the PRN, a cascade attention module (CAM) is employed to aggregate features from multiple subnets, progressively refining region proposals to improve detection accuracy for medium- and long-range objects. …”
Get full text

Knowledge of final-year medical students at the University of KwaZulu-Natal about family medicine, and long-term career choices by R. Omed Ali, A. J. Ross, T. C. Nkabinde

“…A key recommendation to address these issues is to introduce FM into the curriculum earlier, to cover the key roles of the FP, and provide teaching that highlights the relevance of FM to health system programmes.…”
Get full text

A novel knowledge distillation framework for enhancing small object detection in blurry environments with unmanned aerial vehicle-assisted images by Sayed Jobaer, Xue-song Tang, Yihong Zhang, Gaojian Li, Foysal Ahmed

“…Following this, we employ a technique known as self-supervised knowledge distillation, where we introduce a deblurring subnet module with the help of two attention modules, where both networks are trained in a fully-supervised manner. …”
Get full text

DWTMA-Net: Discrete Wavelet Transform and Multi-Dimensional Attention Network for Remote Sensing Image Dehazing by Xin Guan, Runxu He, Le Wang, Hao Zhou, Yun Liu, Hailing Xiong

“…Specifically, we design a wavelet transform-based downsampling module that effectively fuses frequency and spatial features. …”
Get full text

Multitarget Vehicle Tracking and Motion State Estimation Using a Novel Driving Environment Perception System of Intelligent Vehicles by Yuren Chen, Xinyi Xie, Bo Yu, Yi Li, Kunhui Lin

“…However, current multitarget tracking methods are inconvenient to deal with multivehicle issues due to the dynamically complex driving environment. …”
Get full text

Laser weld spot detection based on YOLO-weld by Jianxin Feng, Jiahao Wang, Xinyu Zhao, Zhiguo Liu, Yuanming Ding

“…Finally, a lightweight multi-scale feature processing module, MSBCSPELAN, is proposed to enhance multi-scale feature handling while reducing the number of model parameters. …”
Get full text

A UAV perspective based lightweight target detection and tracking algorithm for intelligent transportation by Quan Wang, Guangfei Ye, Qidong Chen, Songyang Zhang, Fengqing Wang

“…Furthermore, the C2f module is replaced by the FPW to reduce the pointless computation and memory utilization of the model. …”
Get full text

Research on Seamless Fabric Defect Detection Based on Improved YOLOv8n by Qin Sun, Bernd Noche, Zongyi Xie, Bingqiang Huang

“…An improved YOLOv8n seamless fabric defect detection model is proposed to solve the current issues in seamless fabric defects in factories in this paper. …”
Get full text

Loader Bucket Working Angle Identification Method Based on YOLOv5s and EMA Attention Mechanism by Xuedong Zhang, Bo Cui, Zhaoxu Wang, Wangting Zeng

“…In response to the issues of low recognition efficiency and large errors encountered in the process of identifying the working angle of the bucket during current automated loader construction operations, a method based on YOLOv5s and the EMA attention mechanism for loader bucket working angle identification is proposed. …”
Get full text

Fusion of Visual Attention and Scene Descriptions With Deep Reinforcement Learning for AAV Indoor Autonomous Navigation by Hussein Samma, Ahmed Abubaker, Mubarak Badamasi Aremu, Mohammed Abdel-Nasser, Sami El-Ferik

“…Autonomous indoor AAV navigation in GPS-denied environments is challenging. Issues include low lighting and obstacles. This work proposes a dual guidance framework to address these challenges. …”
Get full text