检索结果-内蒙古大学图书馆

3rd World Conference on intelligent and 3D Technologies, WCI3DT 2024

作者： Lei, Jianyun Tian, Wang Xia, Meng Ai, Yong Tian, Zuohan College of Computer Science South-Central Minzu University Wuhan430074 China Hubei Provincial Engineering Research Center for Intelligent Management of Manufacturing Enterprises Wuhan430074 China Hubei Provincial Engineering Research Center for Agricultural Blockchain and Intelligent Management Wuhan430074 China

ISBN: (纸本)9789819791279

The majority of existing few-shot object detection techniques depend on conventional deep learning architectures and can be categorized into either single-stage or two-stage approaches, both of which have demonstrated corresponding outcomes. In the context of two-stage object detection models, however, the challenge often lies in the generation of numerous irrelevant bounding boxes, largely due to the limited number of sample instances. To tackle this very problem, the current study presents a novel few-shot object detection algorithm christened Multi-attention for Few-Shot Object Detection (MuA-FSOD), which ingeniously integrates multiple attention mechanisms. This algorithm enhances the feature representation of new classes through feature fusion techniques and alleviates the adverse effects that may be introduced by feature fusion through the Cross Attention Redistributed (CAReD) attention mechanism, while maintaining the richness of features. Additionally, the algorithm employs the Query-Support Attention Module (QSAM) attention mechanism in the relationship matching phase, improving the quality of candidate boxes by assessing the mutual relationship within the interaction between support and query images. The experimental outcomes affirm that the proposed model exceeds the performance of the baseline Few-Shot Object Detection (FSOD) method on the MS COCO benchmark across the AP, AP50, AP75 metrics, with improvements of 0.9%, 1.2%, and 0.8% respectively. Additionally, it delivers commendable results when tested under the N-way K-shot setting on the PASCAL VOC dataset. These results collectively demonstrate that this method significantly uplifts the detection accuracy for scenarios involving few-shot object recognition tasks. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Face Frontalization Based on U-Net and Self-attention 3rd

Face Frontalization Based on U-Net and Self-attention

引用

3rd World Conference on intelligent and 3D Technologies, WCI3DT 2024

作者： Wu, Qianbao Zou, Zhenyu Tian, Juanjuan College of Computer Science South-Central Minzu University Wuhan430074 China Hubei Provincial Engineering Research Center for Intelligent Management of Manufacturing Enterprises Wuhan430074 China Hubei Provincial Engineering Research Center for Agricultural Block Chain and Intelligent Management Wuhan430074 China

ISBN: (纸本)9789819791279

Face frontalization, as an important and commonly used means of face recognition, generating a frontal face image with original identity information from a profile face image, avoiding the problem of facial features extraction difficulty and face recognition inability at large poses. Current face frontalization models based on generative adversarial network technology usually generate frontal face images with poor retention of identity information, low image quality, and low face recognition accuracy when profile facial images under a large pose. By introducing the U-net architecture and Self-Attention mechanism into the Generative Adversarial Network, a single-pathway U-Net Self-attention Generative Adversarial Network (UNSA-GAN) model is proposed to effectively integrate features of various scales and capture more detailed information, thus to enhance the quality of synthesized frontal facial images. During training phase, idendity(id) loss and pose loss are introduced to generate more accurate frontal faces that maintain identity consistency with the original profile faces. Experimental results demonstrate the effectiveness of the proposed model. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

research on Chinese Named Entity Recognition Based on Bidirectional Self-attention and Span 3rd

Research on Chinese Named Entity Recognition Based on Bidire...

引用

3rd World Conference on intelligent and 3D Technologies, WCI3DT 2024

作者： Li, Zimao Jiang, Hai Yin, Fan Xu, Ke Jia, Mengmeng Jin, Disheng College of Computer Science South-Central Minzu University Wuhan430074 China Hubei Provincial Engineering Research Center for Intelligent Management of Manufacturing Enterprises Wuhan430074 China Hubei Provincial Engineering Research Center for Agricultural Blockchain and Intelligent Management Wuhan430074 China School of Media & Communication Wuhan Textile University Hubei Wuhan430073 China

ISBN: (纸本)9789819791279

Named Entity Recognition is the basis for many Natural Language Processing technology applications. The traditional sequence labeling-based approach fails to recognize nested entities due to its decoding method of continuous label prediction. Currently, scholars have proposed a span-based named entity recognition method, which extracts bidirectional semantics through character embedding combined with BiLSTM (Bi-directional Long Short-Term Memory) networks and predicts entity boundaries, which realizes the work of recognizing multiple types of entities. However, this character-level approach is limited by the Chinese word-segmentation problem and the BiLSTM network cannot be parallelized. To address the above problems, a Chinese Named Entity Recognition model based on bidirectional self-attention and span is proposed. The model uses a positional embedding-optimized Transformer to construct a bidirectional semantic extraction structure and combines the bidirectional self-attention mechanism to fuse character embedding and external lexicon information to solve the word segmentation problem. Finally, the convolutional module and biaffine module are used for joint decoding. The proposed model experiments on ordinary entity datasets Weibo, Resume, and nested entity dataset Cnerta with F1 values of 73.57, 96.56, and 85.41%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Experimental Investigation of Cooling Plates with Different Channel Structures

Experimental Investigation of Cooling Plates with Different ...

引用

Smart Grid and Artificial Intelligence (SGAI), International Conference on

作者： Junjie Li Yang Hu Yiqiang Qin Yong Lee Hubei Provincial Engineering Research Center of Robotics & Intelligent Manufacturing School of Mechanical and Electronic Engineering Wuhan University of Technology Wuhan China Wuhan Second Ship Design and Research Institute Wuhan China

ISBN: (数字)9798331518806

ISBN: (纸本)9798331518813

Current research on the performance of liquid cooling plates has predominantly emphasized the simulation method for a single flow channel structure. Consequently, systematic analysis of different flow channel structures based on experimental data remains limited. This study investigated the cooling characteristics of plates with six different channel structures, providing some experimental data references for related applications and studies. By comparing the consistency between the simulation results and the experimental data, the comparative experiment verified the reliability of the experimental process. Then, range analysis was used in the orthogonal test to reveal the variation patterns of three general performance metrics: maximum temperature of the heat source, temperature difference, and pressure drop under the combined influence of the cooling plate channel structure, thermal load, and flow rate. Furthermore, a comprehensive cooling performance metric was constructed using the entropy weight method and the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) to evaluate the integrated cooling performance of different channel structures. The results demonstrate significant differences in the cooling performance between channel structures, with the grid-type channel exhibiting the best performance. Furthermore, a faster flow rate reduces the duration and efficiency of heat transfer, recommending an optimal flow rate of approximately 6 L/min under similar thermal conditions.

关键词： Heating systems Temperature distribution Liquid cooling Systematics Simulation Thermal analysis Smart grids Thermal loading Reliability Periodic structures

来源：评论

学校读者我要写书评

暂无评论

Aluminum Surface Defect Detection Method Based on DAS-YOLO Network

引用

IET Image Processing 2025年第1期19卷

作者： Tie, Jun Ma, Jiating Zheng, Lu Zhu, Chengao Wu, Mian Wang, HaiJiao Ruan, ChongWei Li, Shuangyang College of Computer Science South-Central Minzu University Hubei Wuhan China Hubei Provincial Engineering Research Center of Agricultural Blockchain and Intelligent Management Hubei Wuhan China Hubei Provincial Engineering Research Center for Intelligent Management of Manufacturing Enterprises Hubei Wuhan China Dong Feng Machine Tool Plant Co. Ltd. Hubei ShiYan China

To address the accuracy limitations of current methods in detecting aluminum surface defects, particularly those with small sizes and high variation, an aluminum surface defect detection algorithm named DAS-YOLO, based on an improved YOLOv8n, is proposed. The C2f module in YOLOv8's backbone is enhanced by incorporating DCNv2, which improves the model's ability to handle irregular shapes and geometric transformations during feature extraction. An auxiliary training head (Aux Head) is added to capture multi-scale and multi-level features, significantly boosting small defect detection. Additionally, the traditional CIoU loss function is replaced with the Wise-SIoU loss, accelerating convergence and enhancing both detection and regression accuracy. Experimental results on the Alibaba Tianchi aluminum surface defect dataset show that DAS-YOLO achieves a mean average precision (mAP) of 85.3%. Compared to YOLOv8n, mAP50 improves by 3%, while precision and recall increase by 1.1% and 4.6%, respectively. Furthermore, to validate the model's performance on small defects and its generalization ability, it achieves a detection accuracy of 94.8% on the PCB dataset, with an mAP increase of 3.1% compared to YOLOv8n. These results demonstrate that DAS-YOLO significantly enhances detection accuracy while maintaining speed and exhibits outstanding performance in small defect detection. © 2025 The Author(s). IET Image Processing published by John Wiley & Sons Ltd on behalf of The Institution of engineering and Technology.

关键词： Aluminum alloys

来源：评论

学校读者我要写书评

暂无评论

An Improved YOLOv8-Based Rice Pest and Disease Detection 41st

An Improved YOLOv8-Based Rice Pest and Disease Detection

引用

41st Computer Graphics International Conference, CGI 2024

作者： Yang, Yang Zhu, Jianlin Yang, Bo Zhang, Xiao Huang, Jin South-Central Minzu University a. College of Computer Scienceb. Hubei Provincial Engineering Research Center for Intelligent Management of Manufacturing Enterprises Wuhan430074 China School of Computer Science and Technology University of Science and Technology of China Hefei230026 China School of Computer Science and Artificial Intelligence Wuhan Textile University Wuhan430200 China

ISBN: (纸本)9783031820236

While rice pests and diseases significantly impact crop yields, existing deep learning methods for their detection face challenges with accuracy and deployment complexity. Addressing these issues, this study proposes the YOLOv8-HSFPN, an advanced detection framework. Firstly, it features an innovative High-level Select Feature Pyramid Network (HSFPN) neck network that effectively integrates high-level and low-level feature sets for enhanced feature fusion. Secondly, the addition of a deformable self-attention module further refines the model’s adaptability to the varying shapes and locations of targets, dynamically adjusting to the salient features. The proposed model has undergone comparative and ablation studies alongside YOLOv8, YOLOv9, and YOLOv5, confirming its improved accuracy and streamlined deployment. This integration results in a robust detection model that not only marks a significant leap in accuracy, evidenced by a 3% empirical increase over the standard YOLOv8, but is also remarkably compact. At a mere 3.97MB, this substantial 49.87% size reduction compared to its predecessors renders it exceptionally suitable for devices with limited computational resources, thereby enhancing its viability in practical, real-world applications. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Hand-Eye Calibration based on Variance Minimization Principle

引用

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Ding, Tao Tian, Dazhuang Wu, Hao Zhu, Dahu Li, Wenlog Wuhan University of Technology Hubei Key Laboratory of Advanced Technology for Automotive Components School of Automotive Engineering Wuhan430070 China Wuhan University of Technology Hubei Digital Manufacturing Key Laboratory School of Mechanical and Electronic Engineering Wuhan430070 China Wuhan University of Technology Hubei Key Laboratory of Advanced Technology for Automotive Components Hubei Provincial Engineering Research Center of Robot and Intelligent Manufacturing Wuhan430070 China Huazhong University of Science and Technology State Key Laboratory of Intelligent Manufacturing Equipment and Technology Wuhan430074 China

Hand-eye calibration in industrial scenarios greatly determines the efficiency and effectiveness of 3D vision-guided robotic tasks. Most of the existing hand-eye calibration methods, however, rely on collecting large-scale point cloud samples to guarantee high measurement accuracy, which is time-consuming and particularly influenced by measurement defects such as local missing, noise, and uneven density. To overcome this challenging problem, we present a novel two-stage hand-eye calibration method based on the variance minimization principle. In the first stage, a robust function weighted variance minimization (RFWVM) registration algorithm is proposed for fine registration of defective point clouds, aiming at solving the coarse hand-eye calibration matrix with few-shot point clouds. In the second stage, an objective function of the calibration error correction algorithm is established via the point-to-plane distance variance minimization, which is intended to suppress the influence of measurement defects. Through these two stages, the globally optimal hand-eye matrix is solved by iteratively correcting the coarse hand-eye calibration matrix. A series of experiments validate the universality, accuracy, and robustness of the proposed method. © 1963-2012 IEEE.

关键词： Error correction

来源：评论

学校读者我要写书评

暂无评论

Pedestrian Detection in Foggy Weather Through YOLOv8 Based on FEAttention 41st

Pedestrian Detection in Foggy Weather Through YOLOv8 Based ...

引用

41st Computer Graphics International Conference, CGI 2024

作者： Sun, Meng Zhu, Jianlin Yang, Bo Huang, Jin Zhang, Xiao College of Computer Science South-Central Minzu University Wuhan430074 China Hubei Provincial Engineering Research Center for Intelligent Management of Manufacturing Enterprises South-Central Minzu University Wuhan430074 China School of Computer Science and Technology University of Science and Technology of China Hefei230026 China School of Computer Science and Artificial Intelligence Wuhan Textile University Wuhan430200 China

ISBN: (纸本)9783031820236

Despite the high accuracy achieved by current pedestrian detection technologies, their performance is significantly hindered in foggy weather conditions due to image color distortion and an increased false alarm. This often leads to false positives, false negative, and other related issues. To address these limitations, we propose an enhanced FDW-YOLOv8 (Feature-Enhancing-Attention Dark Channel Prior Wise-IOU YOLOv8) model based on the YOLOv8 algorithm. This model incorporates FEAttention(Feature-Enhancing-Attention) mechanism into the original YOLOv8 network to improve the discriminability and robustness of extracted features, thus reducing the miss rate(MR). Furthermore, we employ the WiseIOU(WIoU) loss function to expedite model convergence and optimize the accuracy of anchor frames, effectively handling challenges posed by occlusions and scale variations in foggy environments. Prior to model prediction, we utilize the Dark Channel Prior(DCP) defogging algorithm to preprocess input images, effectively extracting pedestrian information while suppressing irrelevant details, thus minimizing the false positive rate (FPR). To evaluate the performance of our model, we create a specialized Foggy-Pedestrian dataset, focusing on pedestrian detection in foggy conditions. Our experiments demonstrate that the proposed FDW-YOLOv8 model significantly outperforms the benchmark model in terms of reducing FPR and MR, exhibiting high generalization and practical applicability for real-world applications in foggy environments. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

A Novel Composite Film with Superhydrophobic Graphene for Anti-Icing/Deicing Via Chemical-Assisted Magnetically Controllable Picosecond Laser Writing

SSRN

引用

SSRN 2025年

作者： Chang, Haozhe Zhang, Zhen Wang, Peng Zhang, Guojun School of Aerospace Engineering Huazhong University of Science and Technology Hubei Wuhan430074 China Guangdong Intelligent Robotics Institute Guangdong Dongguan523808 China Guangdong HUST Industrial Technology Research Institute Guangdong Provincial Key Laboratory of Digital Manufacturing Equipment Guangdong Dongguan523808 China Key Laboratory of Icing and Anti/De-icing China Aerodynamics Research and Development Center Sichuan Mianyang621000 China State Key Laboratory of Intelligent Manufacturing Equipment and Technology School of Mechanical Science and Engineering Huazhong University of Science and Technology Hubei Wuhan430074 China

Icing affects the safe operation of the aircraft and can also damage other outdoor equipment, causing safety hazards. Passive anti-icing of superhydrophobic surface helps to reduce the energy consumption of active thermal deicing. The magnetically controllable direct laser writing (MDLW) was used to fabricate the micro-scale tapered structure and nano-scale layered structure. The superhydrophobic was enhanced by the chemical modification assisted magnetically controllable direct laser writing (C-MDLW), and the graphene capillaries were wrapped to form nanoscale particles. The different material removal mechanisms during the two laser scans, including photochemical mechanism, photothermal mechanism, and ionizing plasma, were described. The differences in surface morphology and chemical elements were analyzed to illustrate their effects on superhydrophobicity. The 'fog' shaped nano graphene capillary structure and high content of polar molecules result in strong hydrophilicity, while the nano particles and non-polar molecules formed after chemical modification are the key reasons for the transformation into superhydrophobicity. The contact angle of C-MDLW was as high as 163.0 °, and the roll-off angle was 1.8 °. Droplets at different heights can bounce on surfaces with different inclination angles. Compared with the raw surface, the icing time was delayed by about 29.5 times. Combined with the electric heating film with a good Joule heating effect, the surface temperature increased. Because of the long icing time, the electric energy was saved by about 86% in the icing and deicing period. © 2025, The Authors. All rights reserved.

关键词： Picosecond lasers

来源：评论

学校读者我要写书评

暂无评论

Sensor packaging method based on the solid tire sole of wheel-legged robot 4

Sensor packaging method based on the solid tire sole of whee...

引用

4th International Conference on Artificial Intelligence, robotics, and Communication, ICAIRC 2024

作者： Huang, Chao Wang, Yaodong Guo, Min Hong, Meng Wuhan University of Technology Hubei Provincial Engineering Research Center of Robotics&Intelligent Manufacturing Wuhan China

ISBN: (纸本)9798331531225

For wheel-legged robots, the unique wheel-legged structure significantly influences the dynamics and kinematic behavior of the foot during ground contact. This paper presents a resistive strain gauge sensor integration scheme for solid tires, wherein sensors are embedded within the tires to actively monitor the touchdown information of the foot-end. A method is proposed for embedding the solid tires in circumferential arrays to capture the plantar strain state, which supports the control system of wheel-legged robots. To evaluate the effectiveness of this sensor package, a simulated impact experiment was conducted to simulate the wheel-legged ground contact. The experimental results demonstrate that the strain gauge embedding method effectively detects the strain response of solid tires under impact. Since ground contact information is crucial for the autonomous switching of the wheel-legged structure in robots, the successful implementation of this sensing system for ground contact monitoring holds significant potential for both research and practical engineering applications. © 2024 IEEE.

关键词： Strain gages

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：