MPAR-RCNN: a multi-task network for multiple person detection with attribute recognition by S. Raghavendra, S. K. Abhilash, Venu Madhav Nookala, Jayashree Shetty, Praveen Gurunath Bharathi

“…Multi-label attribute recognition is a critical task in computer vision, with applications ranging across diverse fields. This problem often involves detecting objects with multiple attributes, necessitating sophisticated models capable of both high-level differentiation and fine-grained feature extraction. …”
Get full text

MW-UNet: Multi-Scale Weighted Connection UNet for Identification and Classification of Non-Meteorological Clutter over Big Radar Data by Mengmeng Cui, Chen Zeng, Xiaolong Xu, Muhammad Bilal, Xiaoyu Xia

“…Additionally, the channel-focused feature fusion mechanism is able to analyze the deep latent features of the input parameters and suppress the useless features, so that only six polarization parameters are required as inputs. …”
Get full text

SCTNet-NAS: efficient semantic segmentation via neural architecture search for cloud-edge collaborative perception by Ruyu Liu, Lin Wang, Zhihao Yu, Haoyu Zhang, Xiufeng Liu, Bo Sun, Xv Huo, Jianhua Zhang

“…Abstract Efficient semantic segmentation on edge devices is critical for cloud-edge perception, yet achieving high accuracy under resource constraints remains challenging. To alleviate this problem, this paper presents SCTNet-NAS, a novel framework for efficient edge segmentation via cloud-edge co-optimization. …”
Get full text

Rolling bearing fault diagnosis under small sample conditions based on WDCNN-BiLSTM Siamese network by Chenxu Bian, Chunni Jia, Jibo Li, Xiangjun Chen, Pei Wang

“…This model constructs a feature extraction system that combines WDCNN and BiLSTM to extract local spatial features and global temporal dependencies from vibration signals. …”
Get full text

DEMNet: A Small Object Detection Method for Tea Leaf Blight in Slightly Blurry UAV Remote Sensing Images by Yating Gu, Yuxin Jing, Hao-Dong Li, Juntao Shi, Haifeng Lin

“…DEMNet introduces a dynamic convolution mechanism into the HGNetV2 backbone to form DynamicHGNetV2, enabling adaptive convolutional weight generation and improving feature extraction for blurry objects. An efficient EMAFPN neck structure further facilitates deep–shallow feature interaction while reducing the computational cost. …”
Get full text

PECULIARITIES OF THE ESTABLISHMENT OF THE LEGAL STATUS OF NATIONALS AND FOREIGNERS IN RUSSIA AND IN GERMANY IN THE XIX CENTURY: HISTORICAL-COMPARATIVE ANALYSIS by T. Plokhotnyuk

“…The author analyzes the features of securing citizenship in two countries - Russia and Germany, where throughout the XIX century national and territorial structure underwent changes and migration was an immanent feature of society.…”
Get full text

Regulation of financial markets: russian and foreingh practice

“…The author considers characteristic features of the financial regulators functioning. Also role of the regulators and feature of their activities in the leading countries of the world and Russia are analysed in the article. …”
Get full text

An Instructional Optimization Method Based on Bidirectional Transformer and Reinforcement Learning by Ran Zhang, Xiaoping Wu, Xude Zhang, Li Xu

“…Transformer layers are employed for feature encoding, while BERT extracts deep semantic representations to form individualized feature vectors. …”
Get full text

Hydraulic System Fault Diagnosis Based on Dual-Channel Convolutional Neural Network and Improved D-S Evidence Theory by Jiyang Qi, Yue Qi, Shenghua Luo, Jiahao Zhang

“…To address the problem that the traditional convolutional neural network (CNN) cannot fully extract the fault feature information in a single channel and the accuracy of hydraulic system fault diagnosis based on a single signal is not high, a fault diagnosis method combining dual-channel CNN and improved D-S evidence theory is proposed. …”
Get full text

Research on Multi-Scale Point Cloud Completion Method Based on Local Neighborhood Dynamic Fusion by Yalun Liu, Jiantao Sun, Ling Zhao

“…However, in the current 3D completion task, it is difficult to effectively extract the local details of an incomplete one, resulting in poor restoration of local details and low accuracy of the completed point clouds. To address this problem, this paper proposes a multi-scale point cloud completion method based on local neighborhood dynamic fusion (LNDF: adaptive aggregation of multi-scale local features through dynamic range and weight adjustment). …”
Get full text

A Recommendation Algorithm Incorporating Adaptive Gating Mechanisms and Knowledge Graph Enhancements by Yi Yu, Teng Lv

“…First, GAKR uses a Multilayer Perceptron (MLP) in the recommendation module to process the user’s initial feature vector and extract potentially compressible features. …”
Get full text

MEIS-YOLO: Improving YOLOv11 for efficient aerial object detection with lightweight design by Yicheng Liu, Jinsong Wu, Li Chen

“…To further optimize multi-scale feature fusion, this paper introduces the asymptotic feature pyramid network. …”
Get full text

Towards understanding the tropical cyclone life cycle by Roger K. Smith, Michael T. Montgomery

“…This behaviour appears to be ruled out in the WISHE models by their assumption of global moist neutrality, but is a feature of the classical Eliassen model.…”
Get full text

Alternate encoder and dual decoder CNN-Transformer networks for medical image segmentation by Lin Zhang, Xinyu Guo, Hongkun Sun, Weigang Wang, Liwei Yao

“…To efficiently fuse different feature information from two sub-decoders during decoding, we introduce a channel attention module to reduce redundant feature information. …”
Get full text

The DEM Registration Method Without Ground Control Points for Landslide Deformation Monitoring by Yunchuan Wang, Jia Li, Ping Duan, Rui Wang, Xinrui Yu

“…Digital elevation model (DEM) time series data are usually used to monitor dynamic changes or surface damage. To solve the problem of landslide deformation monitoring without ground control points (GCPs), a multidimensional feature-based coregistration method (MFBR) was studied to achieve accurate registration of multitemporal DEMs without GCPs and obtain landslide deformation information. …”
Get full text

Adaptive malware identification via integrated SimCLR and GRU networks by Faisal S. Alsubaei, Abdulwahab Ali Almazroi, Walid Said Atwa, Abdulaleem Ali Almazroi, Nasir Ayub, N. Z. Jhanjhi

“…SimCLR-GRU provides a scalable and decisive answer to modern cyberspace’s changing malware detection problem.…”
Get full text

SHIFA: SBERT-Based Healthcare Information Focused Arabic Question Answering by Rahaf Alruwaithi, Sarah AlHumoud

“…The idea behind this research is to use the SBERT method for entities and context patterns to effectively capture the semantics between QA pairs in two different ways: the feature extractor and the transfer learning model. …”
Get full text

THERMOELECTRIC HEAT REMOVAL SYSTEM FOR THE OPERATIONAL STABILISATION OF HEAT PIPES IN A SYSTEM FOR PROVIDING THE THERMAL REGIME OF RADIO ELECTRONIC EQUIPMENT by S. A. Peredkov, R. K. Ramazanov, S. A. Yusufov

“…The three-dimensionality of the problem and mixed boundary conditions lead to the need to develop a calculation  of heat transfer in the elements of the construction of the  thermoelectric system. …”
Get full text

Improved printed circuit board defect detection scheme by Lufeng Bai, Wen Hao Xu

“…In addition, we draw on the advanced BiFPN structure, which enables the bidirectional flow of feature information between multiple layers and greatly improves the capture and integration of small target features. …”
Get full text

Histopathological Image Analysis Using Deep Learning Framework by Sudha Rani Vupulluri, Jogendra Kumar Munagala

“…Graph-segmented images retrieve relevant features. Using recursive feature removal, breast cancer photographs are categorized. …”
Get full text