检索结果-内蒙古大学图书馆

Video salient object detection using a virtual border and guided filter

Pattern Recognition 2020年 97卷

作者： Wang, Qiong Zhang, Lu Zou, Wenbin Kpalma, Kidiyo College of Computer Science and Technology Zhejiang University of Technology No.288 Road Liuhe Hangzhou310023 China - UMR 6164 RennesF-35000 France College of Electronic and Information Engineering Shenzhen Key Laboratory of Advanced Machine Learning and Applications Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China

In this paper, we present a novel method for salient object detection in videos. Salient object detection methods based on background prior may miss salient region when the salient object touches the frame borders. To solve this problem, we propose to detect the whole salient object via the adjunction of virtual borders. A guided filter is then applied on the temporal output to integrate the spatial edge information for a better detection of the salient object edges. At last, a global spatio-temporal saliency map is obtained by combining the spatial saliency map and the temporal saliency map together according to the entropy. The proposed method is assessed on three popular datasets (Fukuchi, FBMS and VOS) and compared to several state-of-the-art methods. The experimental results show that the proposed approach outperforms the tested methods. © 2019

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A convolutional generative adversarial framework for data augmentation based on a robust optimal transport metric 23

A convolutional generative adversarial framework for data au...

引用

23rd IEEE International Conference on High Performance Computing and Communications, 7th IEEE International Conference on Data Science and Systems, 19th IEEE International Conference on Smart City and 7th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and applications, HPCC-DSS-SmartCity-DependSys 2021

作者： Su, Liyilei Fu, Xianjun Hu, Qingmao Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China University of Chinese Academy of Sciences Beijing100049 China Zhejiang College of Security Technology Wenzhou325016 China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Cas Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen518055 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China

ISBN: (纸本)9781665494571

Enhancement of the vanilla generative adversarial network (GAN) to preserve data variability in the presence of real world noise is of paramount significance in deep learning. In this study, we proposed a new distance metric of cosine distance in the framework of optimal transport (OT), and presented and validated a convolutional neural network (CNN) based GAN framework. In comparison with state-of-the-art methods based on Graphics Processing Units (GPU), the proposed framework could maintain the data diversity and quality best in terms of inception score (IS), Fréchet inception distance (FID) and enhancing the classification network of bone age, and is robust to noise degradation. The proposed framework is independent of hardware and thus could also be extended to more advanced hardware such as specialized Tensor Processing Units (TPU), and could be a potential built-in component of a general deep learning networks for such applications as image classification, segmentation, registration, and object detection. © 2021 IEEE.

关键词： Measurement Deep learning Tensors Smart cities Neural networks Graphics processing units Object detection

来源：评论

学校读者我要写书评

暂无评论

A Multi-Scale Neighborhood Feature Interaction Network for Photovoltaic Cell Defect Detection

SSRN

引用

SSRN 2024年

作者： Liu, Yu Chen Hua, Qiang Chen, Lin Lin Dong, Chun Ru Zhang, Feng Zhang, Yong Hebei Key Laboratory of Machine Learning and Computational Intelligence Hebei University Baoding China Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China

Photovoltaic power generation is a key component of the industrial field, whose power generation efficiency is affected by surface defects of photovoltaic cells. The recent success in defect detection is largely attributed to the widespread application of deep learning detection models. However, because of the various sizes of defects on the photovoltaic cells, it is difficult to effectively detect multi-scale defects, especially small defects. Additionally, a large amount of noise information in images brings more difficulties in extracting distinguishable features. To address these issues, a novel one-stage Multi-Scale Neighborhood Feature Interaction Network (MNFI-Net) is proposed in this study to identify defects of various sizes in complex backgrounds. The MNFI-Net consists of the following components: 1) a Ghost Cross Stage Module (GCSM) that is devised to reduce redundant information;2) a Neighborhood Feature Interaction Model (NFIM), which is used to improve the capability of detecting defects with various size;3) a Global Attention Mechanism (GAM) that is devised to emphasize the key features of the fused feature maps. Furthermore, we introduce a novel Balanced Efficient (BE) loss function, which integrates the efficient iou loss and normalized weighted distance loss. Extensive comparison experiments and ablation studies on public photovoltaic electroluminescence images dataset are performed and the experimental results show that the defect classification and detection results of MNFI-Net in photovoltaic cell images achieve 94.0% precision and 95.5% mAP, outperforming the state-of-the-art methods. The code and proposed models in this study can be accessed at https://***/lyc686/MNFI-Net. © 2024, The Authors. All rights reserved.

关键词： Photovoltaics

来源：评论

学校读者我要写书评

暂无评论

In-Plane Dual-Gated Spin-Valve Device Based on the Zigzag Graphene Nanoribbon

引用

Physical Review Applied 2020年第4期13卷 044006-044006页

作者： Min Zhou Hao Jin Yanxia Xing Key Laboratory of Advanced Optoelectronic Quantum Architecture and Measurement Ministry of Education Micronano Centre Beijing Key Laboratory of Nanophotonics and Ultrafine Optoelectronic Systems Beijing Institute of Technology Beijing 100081 China Shenzhen Key Laboratory of Advanced Thin Films and Applications College of Physics and Optoelectronic Engineering Shenzhen University Shenzhen 518060 China

Using the nonequilibrium Green’s function combined with density-functional theory, we systematically study the transport properties of the zigzag graphene nanoribbon (ZGNR). When an external transverse electric field is applied, a ZGNR can exhibit half-metallic characteristics with its conductive channel localized at the edge positions. Accordingly, an in-plane dual-gated spin-valve device is proposed. Thanks to its unique design, the proposed device overcomes the bottleneck of current leakage and avoids contact issues. Remarkably, a 100% spin injection efficiency and a giant tunnel magnetoresistance of up to 107 are realized, which represent much better performance than that of traditional magnetic tunnel junctions. In addition, we also explore the effect of architecture reconstruction and impurity doping on spin-polarized transport. It is found that, in general, the tunneling process is hindered if disorder occurs at the conductive edge. By contrast, if we put the deformation or impurities away from the conductive edge, the transport properties may be barely degraded or even improved, depending on the type of disorder. It should be possible to apply these ubiquitous underlying principles to other materials, which could inspire the design of alternative spintronic devices with high performance.

关键词： Edge states Quantum transport Spintronics Graphene Nanoribbon Spin valves Density functional calculations Nonequilibrium Green's function

来源：评论

学校读者我要写书评

暂无评论

Global small solutions to heat conductive compressible nematic liquid crystal system: Smallness on a scaling invariant quantity

arXiv

引用

arXiv 2021年

作者： Li, Jinkai Tao, Qiang South China Research Center for Applied Mathematics and Interdisciplinary Studies School of Mathematical Sciences South China Normal University Guangzhou510631 China School of Mathematics and Statistics Shenzhen University Shenzhen518060 China Shenzhen Key Laboratory of Advanced Machine Learning and Applications Shenzhen University Shenzhen518060 China

In this paper, we consider the Cauchy problem to the three dimensional heat conducting compressible nematic liquid crystal system in the presence of vacuum and with vacuum far fields. Global well-posedness of strong solutions is established under the condition that the scaling invariant quantity (||ρ0||∞ + 1)[||ρ0||3 + (||ρ0||∞ + 1)2(||√ρ0u0||22 + ||∇d0||22)][||∇u0||22 + (||ρ0||∞ + 1)(||√ρ0E0||22 + ||∇2d0||22)] is sufficiently small with the smallness depending only on the parameters appeared in the system. Copyright © 2021, The Authors. All rights reserved.

关键词： Heat conduction

来源：评论

学校读者我要写书评

暂无评论

Skeleton-Embedded Network for action recognition

Skeleton-Embedded Network for action recognition

引用

2023 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2023

作者： Luo, Li Ren, Ziliang Qin, Yong Zhang, Qieshi Gao, Xiangyang Dongguan University of Technology Department of Computer Science Dongguan52300 China Chinese Academy of Sciences Cas Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology Shenzhen518055 China The Chinese University of HongKong Hong Kong Hong Kong

ISBN: (纸本)9798350327182

Multimodality-based human action recognition is becoming an increasingly attractive topic as different modalities can provide complementary information. RGB and skeleton data have their pros and limitations for action recognition because they describe the action from distinctive views. Therefore, the fusion of these two modalities using their complementarity is meaningful to action recognition. However, it is difficult to completely utilize the supplementarity of RGB and skeleton data. In this paper, to take advantage of their complementary at the semantic level, A skeleton-embedded network(SE-Net) is proposed by us. The architecture is based on integrating their feature in the network not only a post-hoc fusion. With a sparse sampling strategy, which is efficient for learning using the whole action video. To examine the performance of our method, we conducted experiments on the wildly used datasets, obtaining an accuracy of 86.4% in C-sub and 88.2% in C-view on NTU-RGB+D 60. For NTU-RGB+D 120, the accuracy of 81.3% in C-sub and 83.4% in C-set is obtained. © 2023 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Deep learning Techniques on Classifying Commercial Sensor-based Auditory Brainstem Response 16

Performance Evaluation of Deep Learning Techniques on Classi...

引用

16th International Conference on Sensing Technology, ICST 2023

作者： Huang, Kaiyang Wang, Xin He, Yuchao Ji, Junyu Xu, Yangjie Jia, Desheng Zhao, Chunrui Huang, Jinzhu Tao, Yuan Pan, Hongguang Li, Guanglin Chen, Shixiong Guangzhou University of Chinese Medicine School of Medical Information Engineering Guangzhou China Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Cas Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen China Reliability and Trust University of Luxembourg Interdisciplinary Centre for Security Luxembourg Luxembourg Shenzhen Children's Hospital Department of Otolaryngology Shenzhen China The First Dongguan Affiliated Hospital of Guangdong Medical University Department of Endocrine Dongguan China Peking University Shenzhen Hospital Department of Otorhinolaryngology Shenzhen China

ISBN: (纸本)9798350395341

To objectively evaluate the health condition of the auditory pathway, Auditory Brainstem Response (ABR) is used in the clinic. The clinical diagnosis is concluded by the audiologist according to the morphology and characteristic waves of ABR through manual screening. It is a time-consuming and subjective task that not only reduces the efficiency of the physicians but also introduces subjective error which might cause an incorrect diagnosis. Therefore, it is necessary to propose an objective method that can solve the abovementioned problems. Deep learning (DL) technique develops fast and is widely used in many fields, including biomedical engineering. Hence, DL might help with the objective classification of ABR and release the physicians from the heavy workload. In this paper, we evaluated the classification performance of three commonly used DL methods, namely EEGNet, DeepConvNet and ShallowConvNet, on several metrics. The results showed that on the task of classifying normal and abnormal ABR signals, EEGNet had the best performance, with the accuracy of 0.9995 ± 0.0011, the precision of 0.9995 ± 0.0011, the recall of 0.9995 ± 0.0011, the F1-score of 0.9995 ± 0.0011, and the AUC of 1.0000 ± 0.0000. It is believed that DL can help with objective ABR classification and release the physicians' workload. © 2023 IEEE.

关键词： Biomedical engineering

来源：评论

学校读者我要写书评

暂无评论

The effects of different training modes on the performance of silent speech recognition based on high-density sEMG

The effects of different training modes on the performance o...

引用

2021 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2021

作者： Pi, Yao Zhu, Mingxing Yang, Zijian Wang, Xin Wang, Cheng Zhang, Haoshi Wang, Mingjiang Wan, Feng Chen, Shixiong Li, Guanglin Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Guangdong Shenzhen518055 China School of Information Science and Engineering Wuhan University of Science and Technology Hubei Wuhan430081 China School of Electronics and Information Engineering Harbin Institute of Technology Guangdong Shenzhen518055 China University of Macau Department of Science and Technology China Shenzhen College of Advanced Technology University of Chinese Academy of Sciences Guangdong Shenzhen518055 China

ISBN: (纸本)9781665436786

The convolutional neural network (CNN) is frequenctly used in silent speech recognition (SSR) based on surface electromyography (sEMG). Currently, there are two different modes when training the CNN classifier, using the sEMG signals from a single subject as the training datasets and using the mixed signals from multiple subjects as the training datasets. However, it still remains unclear how different training modes affect the performance of the CNN classifier in different classification metrics. In this study, two different training modes were used for the CNN classifier of SSR based on high-density sEMG (HD sEMG) signals. HD sEMG signals collected from six subjects were used to build two different training datasets. The HD sEMG signals from either a single subject or multiple subjects were to train the same CNN model and the performance difference was thoroughly compared in different metrics. The results showed that the CNN model trained from the signals of a single subject showed superior performance with higher average precision, average recall, and average F1 score. It also converged faster and was more stable under different signal conditions. However, it was only suitable for the SSR of the same subject, while the CNN model trained from the signals of multiple subjects showed satisfactiroy performance across all the recruited subjects. This study revealed that the CNN models trained with different training modes performed differently, and therefore the training mode could be taken into consideration in different applications of SSR based on sEMG. © 2021 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

An Interlayer Strategy for Low-Voltage Thin-Film Organic Electrochemical Transistors

引用

Small Methods 2025年 e2500322页

作者： Zeng, Xi Peng, Chengyuan Shi, Wenpei Hu, Shengjie Cao, Yushi Wei, Huan Chen, Ping-An Xia, Jiangnan Ding, Jiaqi Zhang, Yu Gong, Zhenqi Chen, Huajie Lu, Naiyan Li, Rong Hu, Yuanyuan International Science and Technology Innovation Cooperation Base for Advanced Display Technologies of Hunan Province School of Physics and Electronics Hunan University Changsha 410082 China National Key Laboratory of Power Semiconductor and Integration Technology Engineering Research Center of Advanced Semiconductor Technology and Application of Ministry of Education College of Semiconductors (College of Integrated Circuits) Hunan University Changsha 410082 China Shenzhen Research Institute of Hunan University Shenzhen 518063 China School of Food Science and Technology Jiangnan University Wuxi 214122 China School of Biological Science and Medical Engineering Beihang University Xueyuan Street 37 Beijing 100191 China Key Laboratory of Environmentally Friendly Chemistry and Applications of Ministry of Education College of Chemistry Xiangtan University Xiangtan 411105 China Department of Stomatology The Second Xiangya Hospital Central South University Changsha 410013 China

Solid-state organic electrochemical transistors (SS-OECTs) are promising candidates for next-generation wearable and bioelectronic applications due to their high transconductance and low-voltage operation. However, conventional SS-OECTs rely on ion gels with high ionic liquid concentrations, which compromise mechanical robustness and scalability. This study addresses these limitations by developing thin-film OECTs (TF-OECTs) using solid electrolytes with significantly reduced ionic liquid concentrations and introducing a doped organic semiconductor film (DOSCF) as an interlayer between the gate and electrolyte. This strategy enables TF-OECTs to achieve film-like mechanical properties while maintaining high performance, including a maximum transconductance (g_m) of 5.05 mS, operational voltages below 1 V, and exceptional stability over 1000 switching cycles. The devices also exhibit superior flexibility, enduring over 2000 bending cycles with minimal performance degradation. Their potential is demonstrated in ferric ion sensing, achieving an ultralow detection limit of 15 nm with a high selectivity of 0.7 mA dec⁻¹, and in neuromorphic computing, where they emulate synaptic behaviors and achieve a 96.7% image recognition accuracy after training with artificial neural networks (ANN). These results highlight the transformative potential of TF-OECTs for integration into advanced, multifunctional electronic systems, combining high performance, mechanical robustness, and scalability. © 2025 Wiley-VCH GmbH.

关键词： flexibility ion sensors low voltage organic electrochemical transistors synaptic transistors

来源：评论

学校读者我要写书评

暂无评论

A Novel Multi-Stream Informer Used for Lower Extremity Joint Angle Estimation 12

A Novel Multi-Stream Informer Used for Lower Extremity Joint...

引用

12th International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2022

作者： Zhou, Xin Zhang, Liming Liu, Jiaqing Ye, Jiancong Wang, Can Wu, Xinyu Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Cas Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology China University of Science and Technology of China China University of Chinese Academy of Sciences China South China University of Technology China Department of Mechanical and Automation Engineering The Chinese University of Hong Kong Hong Kong

ISBN: (数字)9781665472678

ISBN: (纸本)9781665472678

In lower extremity exoskeleton rehabilitation systems, synergy and proportionality between the human lower extremity and the exoskeleton robot have been a critical goal to pursue. In recent years, changeable deep learning models based on multi-source signals have been used for lower limb continuous motion estimation. During the process, multimode signals are fed into the time processing model as time series. However, there are some deficiencies in this framework, on the one hand, what kind of multi-source combination can be more efficient;on the other hand, most of the existing models need several iterations or network stacking to complete the extraction of temporal information. This study set out to address the above problems, we put forward Multi-Stream Informer (MS-Informer), using Multi-Stream combination and sparse attention mechanisms for lower limb continuous motion estimation. In the experiment, we compare MS-Informer and Temporal Convolutional Network (TCN) and Long Short-term Memory (LSTM) under distinctive multi-source combinations. In summary, MS-informer performs well in multiple evaluations compared with other models. Experimental results illustrate that the MS-Informer is more efficacious in lower limb joint angle estimation and is a promising method for achieving coordinated control of lower limb exoskeletons. © 2022 IEEE.

关键词： Motion estimation

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：