Results 81 to 90 of about 1,673,879 (163)

FSSDD: Few‐shot steel defect detection based on multi‐scale semantic enhancement representation and mask category information mapping

IET Image Processing
Steel defect detection is important for industry production as it is tied to the product quality and production efficiency. However, previous steel defect detection methods based on deep convolutional neural networks heavily rely on large‐scale data for ...
Zhoufeng Liu, Zijing Guo, Chunlei Li, Ning Huang, Chengli Gao   +4 more
doaj   +1 more source

Exploring Dynamic Hierarchical Fusion for Multi-View Clustering

IEEE Access
Multi-view clustering is effective at uncovering the latent structures within different views or modalities. However, existing approaches often oversimplify the problem by treating the contribution and granularity of information from all views as uniform,
Zhenshan Chen, Xuran Tian, Lizhen Gao, Gengbin Liao, Yang Shen, Kainan Zheng, Jianglin Fang   +6 more
doaj   +1 more source

Image Quality Assessment Based on Multi-Scale Representation and Shifting Transformer

IEEE Access
In automatic control systems, sensors and cameras are often used to capture images of the environment or processes being monitored. The quality of these images is paramount as it directly affects the system’s ability to accurately interpret and ...
Geng Fu, Ziyu Wang, Cuijuan Zhang, Zerong Qi, Mingzheng Hu, Shujun Fu, Yunfeng Zhang   +6 more
doaj   +1 more source

Multi-scale tree-guided contrastive learning for structure-aware graph representation

Complex & Intelligent Systems
Existing graph contrastive learning (GCL) methods typically rely on random perturbations to generate augmented views. However, they often fail to explicitly model higher-order structural semantics.
Jiajie Du, Lu Peng, Mingyuan Li, Yanlin Yang, Lei Meng, Haixing Zhao, Zhonglin Ye, Yonghang Wang   +7 more
doaj   +1 more source

HMHGT: Hierarchical Multi-Scale Hypergraph Representation for Histopathology Whole Slide Images

IEEE Access
Cancer prognosis is a challenging task in computational pathology, requiring comprehensive representation of tissue features with context awareness to more accurately infer patient survival. However, existing deep learning methods, such as multi-instance
Shangce Wang, Lukai Jiang, Chenggong Qiu
doaj   +1 more source

Contrastive Representation Distillation via Multi-Scale Feature Decoupling

Knowledge distillation enhances the performance of compact student networks by transferring knowledge from more powerful teacher networks without introducing additional parameters. In the feature space, local regions within an individual global feature encode distinct yet interdependent semantic information.
Wang, Cuipeng, Wang, Haipeng
openaire   +2 more sources

A collaborative multi-attention network for real-time small object detection in UAV imagery. [PDF]

Sci Rep
Yang J, Yue X, Wu L.
europepmc   +1 more source

MobileSteelNet: A Lightweight Steel Surface Defect Classification Network with Cross-Interactive Efficient Multi-Scale Attention. [PDF]

Sensors (Basel)
Zou X, Liu Z, Xu C, Zhang J, Li Z.
europepmc   +1 more source

A BIM-Based Digital Twin Framework for Urban Roads: Integrating MMS and Municipal Geospatial Data for AI-Ready Urban Infrastructure Management. [PDF]

Sensors (Basel)
Scolamiero V, Boccardo P.
europepmc   +1 more source

Robust Tracker: Integrating CPM-YOLO and BOTSORT for Cross-Modal Vessel Tracking. [PDF]

Sensors (Basel)
Lv F, Zhang Y.
europepmc   +1 more source