NSTL国家科技图书文献中心

1. HieRelBERT: Enhanced Lexical Relation Embedding Based-On Hierarchical Contrast Learning NSTL国家科技图书文献中心

Liping Li | Yexuan Zhang ... - 《Computational and Experimental Simulations in Engineering,Volume 4》 - International Conference on Computational & Experimental Engineering and Sciences - 2025, - 795～815 - 共21页

摘要： learning. By integrating instance contrastive learning | and prototypical contrastive learning, our model | Understanding the lexical relationships | between word pairs is paramount for advancing | applications in natural language processing. However

关键词： Lexical relation | Contrast learning | Prompt learning

2. Color fourier ptychographic microscopy reconstruction based on double contrast learning NSTL国家科技图书文献中心

Wang, Yan | Wan, Shuo ... - 《Physica Scripta》 - 2025,100(4) - 共10页

摘要： propose an enhanced dual-contrast* learning virtual* | Fourier ptychographic microscopy (FPM), as an | advanced digital imaging technique, holds significant | potential in the pathology field. Color FPM images are | essential for accurate pathological analysis. Currently

关键词： FPM | digital pathology | double contrast learning | virtual staining | HWD downsampling module

3. Treasure in the background: Improve saliency object detection by self-supervised contrast learning NSTL国家科技图书文献中心

Haoji Dong | Jie Wu ... - 《Expert Systems with Application》 - 2025,267(Apr.1) - 126244.1～126244.11 - 共11页

摘要： details, we introduce self-supervised contrast learning | contrast learning and pixel-level contrast learning for | supervised learning* tends to focus on prominent regions but* | self-supervised learning* captures more comprehensive* | Salient object detection (SOD) is a critical

关键词： Salient object detection | Contrast learning | Self-supervised learning | Vision transformer | Vision Graph Neural Network

4. Dynamic graph consistency and self-contrast learning for semi-supervised medical image segmentation NSTL国家科技图书文献中心

Li, Gang | Xie, Jinjie ... - 《Neural Networks》 - 2025,184 - Article 107063～Article 107063 - 共14页

摘要： novel self-contrast* learning strategy, which performs* | engages in pixel-level contrast* learning based on pixel* | contrast learning challenges related to identifying | Semi-supervised medical image segmentation | endeavors to exploit a limited set of labeled data in

关键词： Semi-supervised learning | Dynamic graph consistency | Self-contrast learning | Medical image segmentation

5. Correction of medical image segmentation errors through contrast learning with multi-branch NSTL国家科技图书文献中心

Tianlei Gao | Lei Lyu ... - 《Engineering Applications of Artificial Intelligence》 - 2025,151(Jul.) - 110564.1～110564.10 - 共10页

摘要： Contrast Learning with Multi-Branch Network (MEC) to | contrastive learning* strategy that aligns the semantic* | Medical image segmentation plays a pivotal | role in computer-aided diagnosis. Despite the | considerable advancements achieved by convolutional neural

关键词： Convolutional neural network | Contrast learning | Medical image segmentation | Segmentation correction

6. A novel spatio-temporal feature interleaved contrast learning neural network from a robustness perspective NSTL国家科技图书文献中心

Liu P. | Zhu Y.... - 《Knowledge-based systems》 - 2025,309(Jan.30) - 1.1～1.13 - 共13页

摘要： contrast learning for daily traffic flow prediction.Our | interlace contrast* graph structure generator and a* | © 2024 Elsevier B.V.Accurate traffic | forecasting is critical to the effectiveness of intelligent | transportation systems (ITS) and the development of smart

关键词： Complex networks | Heterogeneity | Robustness analysis | Spatialtemporal data | Traffic prediction

7. Self-supervised contrast learning based UAV fault detection and interpretation with spatial-temporal information of multivariate flight data NSTL国家科技图书文献中心

Shengdong Wang | Zhen Jia ... - 《Expert Systems with Application》 - 2025,267(Apr.1) - 126156.1～126156.20 - 共20页

摘要： contrast learning and spatial-temporal information of | supervised learning* strategy. In this study, a novel UAV* | multivariate flight data is proposed. In the contrast | learning task, a series of specific sample | transformations is further introduced to facilitate the learning

关键词： UAV | Fault detection | Flight data analysis | Condition monitoring | Graph neural network

8. A Federated Learning Framework for Lightweight Model Contrast for Finger Vein Recognition NSTL国家科技图书文献中心

Guang Chen | Tianming Xie ... - 《Biometric Recognition,Part I》 - Chinese Conference on Biometric Recognition - 2025, - 68～78 - 共11页

摘要：. This study proposes a federal learning* framework for* | , a model of contrastive learning* among participants* | The training efficacy of finger vein models is | influenced by varied device image acquisition | characteristics, collector gestures, and contact modes. However

关键词： Federal learning | Finger veins | Contrast learning | Training framework

9. Artificial T1-Weighted Postcontrast Brain MRI A Deep Learning Method for Contrast Signal Extraction NSTL国家科技图书文献中心

Haase, Robert | Pinetz, Thomas ... - 《Investigative radiology.》 - 2025,60(2) - 105～113 - 共9页

摘要：Objectives: Reducing gadolinium-based contrast | -art deep learning* methods (settings A and B) and a* | proposed method for contrast* signal extraction (setting C* | scale (0 being the worst), they scored the contrast | contrast signal extraction showed significant

关键词： gadolinium-based contrast agent | low-dose | dose reduction | magnetic resonance imaging | deep learning | convolutional neural network | virtual contrast

10. Multilabel Classification of Intracranial Hemorrhages Using Deep Learning and Preprocessing Techniques on Non-contrast CT Images NSTL国家科技图书文献中心

Rodrigo Salas | Juan Sebastian Castr...... - 《Progress in Pattern Recognition,Image Analysis,Computer Vision,and Applications,Part II》 - Iberoamerican Congress on Pattern Recognition - 2025, - 175～190 - 共16页

摘要： that integrates a deep learning* model with advanced* | , subarachnoid, and subdural - using non-contrast* computed* | dataset of over 25,000 non-contrast* CT scans, each* | This study presents a comprehensive framework | image preprocessing techniques to improve the

摘要： learning. By integrating instance contrastive learning | and prototypical contrastive learning, our model | Understanding the lexical relationships | between word pairs is paramount for advancing | applications in natural language processing. However

关键词： Lexical relation | Contrast learning | Prompt learning

摘要： propose an enhanced dual-contrast* learning virtual* | Fourier ptychographic microscopy (FPM), as an | advanced digital imaging technique, holds significant | potential in the pathology field. Color FPM images are | essential for accurate pathological analysis. Currently

关键词： FPM | digital pathology | double contrast learning | virtual staining | HWD downsampling module

摘要： details, we introduce self-supervised contrast learning | contrast learning and pixel-level contrast learning for | supervised learning* tends to focus on prominent regions but* | self-supervised learning* captures more comprehensive* | Salient object detection (SOD) is a critical

关键词： Salient object detection | Contrast learning | Self-supervised learning | Vision transformer | Vision Graph Neural Network

摘要： novel self-contrast* learning strategy, which performs* | engages in pixel-level contrast* learning based on pixel* | contrast learning challenges related to identifying | Semi-supervised medical image segmentation | endeavors to exploit a limited set of labeled data in

关键词： Semi-supervised learning | Dynamic graph consistency | Self-contrast learning | Medical image segmentation

摘要： Contrast Learning with Multi-Branch Network (MEC) to | contrastive learning* strategy that aligns the semantic* | Medical image segmentation plays a pivotal | role in computer-aided diagnosis. Despite the | considerable advancements achieved by convolutional neural

关键词： Convolutional neural network | Contrast learning | Medical image segmentation | Segmentation correction

摘要： contrast learning for daily traffic flow prediction.Our | interlace contrast* graph structure generator and a* | © 2024 Elsevier B.V.Accurate traffic | forecasting is critical to the effectiveness of intelligent | transportation systems (ITS) and the development of smart

关键词： Complex networks | Heterogeneity | Robustness analysis | Spatialtemporal data | Traffic prediction

摘要： contrast learning and spatial-temporal information of | supervised learning* strategy. In this study, a novel UAV* | multivariate flight data is proposed. In the contrast | learning task, a series of specific sample | transformations is further introduced to facilitate the learning

关键词： UAV | Fault detection | Flight data analysis | Condition monitoring | Graph neural network

摘要：. This study proposes a federal learning* framework for* | , a model of contrastive learning* among participants* | The training efficacy of finger vein models is | influenced by varied device image acquisition | characteristics, collector gestures, and contact modes. However

关键词： Federal learning | Finger veins | Contrast learning | Training framework

摘要：Objectives: Reducing gadolinium-based contrast | -art deep learning* methods (settings A and B) and a* | proposed method for contrast* signal extraction (setting C* | scale (0 being the worst), they scored the contrast | contrast signal extraction showed significant

关键词： gadolinium-based contrast agent | low-dose | dose reduction | magnetic resonance imaging | deep learning | convolutional neural network | virtual contrast

摘要： that integrates a deep learning* model with advanced* | , subarachnoid, and subdural - using non-contrast* computed* | dataset of over 25,000 non-contrast* CT scans, each* | This study presents a comprehensive framework | image preprocessing techniques to improve the

关键词： Intracranial hemorrhage | Deep learning | Multilabel classification | Non-contrast computed tomography (CT) | Medical image processing

4008-161-200 800-990-8900

国家科技图书文献中心

摘要： learning. By integrating instance contrastive learning | and prototypical contrastive learning, our model | Understanding the lexical relationships | between word pairs is paramount for advancing | applications in natural language processing. However

关键词： Lexical relation | Contrast learning | Prompt learning

摘要： propose an enhanced dual-contrast learning virtual | Fourier ptychographic microscopy (FPM), as an | advanced digital imaging technique, holds significant | potential in the pathology field. Color FPM images are | essential for accurate pathological analysis. Currently

关键词： FPM | digital pathology | double contrast learning | virtual staining | HWD downsampling module

摘要： details, we introduce self-supervised contrast learning | contrast learning and pixel-level contrast learning for | supervised learning tends to focus on prominent regions but | self-supervised learning captures more comprehensive | Salient object detection (SOD) is a critical

关键词： Salient object detection | Contrast learning | Self-supervised learning | Vision transformer | Vision Graph Neural Network

摘要： novel self-contrast learning strategy, which performs | engages in pixel-level contrast learning based on pixel | contrast learning challenges related to identifying | Semi-supervised medical image segmentation | endeavors to exploit a limited set of labeled data in

关键词： Semi-supervised learning | Dynamic graph consistency | Self-contrast learning | Medical image segmentation

摘要： Contrast Learning with Multi-Branch Network (MEC) to | contrastive learning strategy that aligns the semantic | Medical image segmentation plays a pivotal | role in computer-aided diagnosis. Despite the | considerable advancements achieved by convolutional neural

关键词： Convolutional neural network | Contrast learning | Medical image segmentation | Segmentation correction

摘要： contrast learning for daily traffic flow prediction.Our | interlace contrast graph structure generator and a | © 2024 Elsevier B.V.Accurate traffic | forecasting is critical to the effectiveness of intelligent | transportation systems (ITS) and the development of smart

关键词： Complex networks | Heterogeneity | Robustness analysis | Spatialtemporal data | Traffic prediction

摘要： contrast learning and spatial-temporal information of | supervised learning strategy. In this study, a novel UAV | multivariate flight data is proposed. In the contrast | learning task, a series of specific sample | transformations is further introduced to facilitate the learning

关键词： UAV | Fault detection | Flight data analysis | Condition monitoring | Graph neural network

摘要：. This study proposes a federal learning framework for | , a model of contrastive learning among participants | The training efficacy of finger vein models is | influenced by varied device image acquisition | characteristics, collector gestures, and contact modes. However

关键词： Federal learning | Finger veins | Contrast learning | Training framework

摘要：Objectives: Reducing gadolinium-based contrast | -art deep learning methods (settings A and B) and a | proposed method for contrast signal extraction (setting C | scale (0 being the worst), they scored the contrast | contrast signal extraction showed significant

关键词： gadolinium-based contrast agent | low-dose | dose reduction | magnetic resonance imaging | deep learning | convolutional neural network | virtual contrast

摘要： that integrates a deep learning model with advanced | , subarachnoid, and subdural - using non-contrast computed | dataset of over 25,000 non-contrast CT scans, each | This study presents a comprehensive framework | image preprocessing techniques to improve the

关键词： Intracranial hemorrhage | Deep learning | Multilabel classification | Non-contrast computed tomography (CT) | Medical image processing

4008-161-200 800-990-8900

国家科技图书文献中心

摘要： propose an enhanced dual-contrast* learning virtual* | Fourier ptychographic microscopy (FPM), as an | advanced digital imaging technique, holds significant | potential in the pathology field. Color FPM images are | essential for accurate pathological analysis. Currently

摘要： details, we introduce self-supervised contrast learning | contrast learning and pixel-level contrast learning for | supervised learning* tends to focus on prominent regions but* | self-supervised learning* captures more comprehensive* | Salient object detection (SOD) is a critical

摘要： novel self-contrast* learning strategy, which performs* | engages in pixel-level contrast* learning based on pixel* | contrast learning challenges related to identifying | Semi-supervised medical image segmentation | endeavors to exploit a limited set of labeled data in

摘要： Contrast Learning with Multi-Branch Network (MEC) to | contrastive learning* strategy that aligns the semantic* | Medical image segmentation plays a pivotal | role in computer-aided diagnosis. Despite the | considerable advancements achieved by convolutional neural

摘要： contrast learning for daily traffic flow prediction.Our | interlace contrast* graph structure generator and a* | © 2024 Elsevier B.V.Accurate traffic | forecasting is critical to the effectiveness of intelligent | transportation systems (ITS) and the development of smart

摘要： contrast learning and spatial-temporal information of | supervised learning* strategy. In this study, a novel UAV* | multivariate flight data is proposed. In the contrast | learning task, a series of specific sample | transformations is further introduced to facilitate the learning

摘要：. This study proposes a federal learning* framework for* | , a model of contrastive learning* among participants* | The training efficacy of finger vein models is | influenced by varied device image acquisition | characteristics, collector gestures, and contact modes. However

摘要：Objectives: Reducing gadolinium-based contrast | -art deep learning* methods (settings A and B) and a* | proposed method for contrast* signal extraction (setting C* | scale (0 being the worst), they scored the contrast | contrast signal extraction showed significant

摘要： that integrates a deep learning* model with advanced* | , subarachnoid, and subdural - using non-contrast* computed* | dataset of over 25,000 non-contrast* CT scans, each* | This study presents a comprehensive framework | image preprocessing techniques to improve the