检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Zhong, Xiaojing Huang, Xinyi Wu, Zhonghua Lin, Guosheng Wu, Qingyao School of Software Engineering South China University of Technology China School of Computer Science and Engineering Nanyang Technological University Singapore Key Laboratory of Big Data and Intelligent Robot Ministry of Education China Peng Cheng Laboratory China SenseTime Research China

Makeup transfer is a process of transferring the makeup style from a reference image to the source image, while preserving the source image’s identity. In addition to achieving fine-grained control over the makeup transfer, incorporating semantic alignment into the transformation is crucial, as the poses of the reference and source images are often inconsistent. We propose a novel Semantic-guided Alignment and Region-Adaptive normalization framework (SARA) to effectively transfer makeup styles under misaligned poses, offering flexible control to meet the demands of real-world applications, such as partial transfer, intensity adjustment, and makeup removal. Specifically, SARA comprises three modules: Firstly, we propose a semantic-guided alignment module to explicitly construct dense correspondence between the reference image and the target semantic map, employing unbalanced optimal transport matching to handle semantic region mismatches. Secondly, a region-adaptive normalization module is responsible for dynamically combining the warped style features with shape-independent style codes obtained by region-wise average pooling, mitigating feature loss during the alignment. Lastly, a makeup fusion module progressively fuses the identity features with the makeup styles to render the final output image. Furthermore, we combine optimal transport with histogram matching to generate the pseudo ground truth, which is used to facilitate the transfer in terms of both spatial alignment and color distribution. Experimental results show that our proposed SARA outperforms existing methods on two public datasets. © 2023, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

EnsembleFollower: A Hybrid Car-Following Framework Based on Hierarchical Planning and Reinforcement Learning

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Han, Xu Chen, Xianda Zhu, Meixin Cai, Pinlong Zhou, Jianshan Chu, Xiaowen Data Science and Analytics Thrust Information Hub Guangzhou China Intelligent Transportation Thrust Systems Hub Guangzhou China Sensing and Computation for Ubiquitous Internet of Things Guangdong Provincial Key Lab of Integrated Communication China Southeast University School of Transportation Nanjing211189 China Shanghai Artificial Intelligence Laboratory Shanghai China Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems & Safety Control State Key Laboratory of Intelligent Transportation Systems China Beihang University School of Transportation Science and Engineering Beijing100191 China

Car-following models have made significant contributions to our understanding of longitudinal driving behavior. However, they often exhibit limited accuracy and flexibility, as they cannot fully capture the complexity inherent in car-following processes, or may struggle in unseen scenarios due to their reliance on confined driving skills present in training data. It is worth noting that each car-following model possesses its own strengths and weaknesses depending on specific driving scenarios. Therefore, we propose EnsembleFollower, a closed-loop hierarchical planning framework for achieving human-like autonomous car-following. The EnsembleFollower framework involves a high-level Reinforcement Learning-based agent responsible for judiciously managing multiple low-level models (such as intelligent Driver Model and Gipps model) according to the current state, either by selecting an appropriate car-following model to perform an action or by allocating different weights across all primitive models. Moreover, we propose a jerk-constrained kinematic model for more convincing microscopic traffic simulations. We evaluate the proposed method based on real-world driving data from the HighD dataset. The experimental results illustrate that EnsembleFollower yields an improved accuracy of human-like behavior and achieves effectiveness in combining hybrid models, demonstrating that our proposed framework can handle diverse driving conditions by leveraging the strengths of various car-following models. © 1967-2012 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

The dynamics of tea plantation encroachment into forests and effect on forest landscape pattern during 1991–2021 through time series Landsat images

引用

Ecological Indicators 2022年第0期141卷

作者： Xiong, Yuan Kang, Qianwen Xu, Weiheng Huang, Shaodong Dai, Fei Wang, Leiguang Lu, Ning Kou, Weili College of Big Data and Intelligent Engineering Southwest Forestry University Kunming650233 China Institute of Big Data and Artificial Intelligence Southwest Forestry University Yunnan Kunming650233 China Key Laboratory of National Forestry and Grassland Administration on Forestry and Ecological Big Data Southwest Forestry University Yunnan Kunming650233 China

Tea plantations encroachment into forests has occurred in the major tea planting area of Yunnan province, China in the past decades. However, the dynamics of tea plantation encroachment into forests and the effect on forest landscape pattern is not clear. In this study, we proposed a method to evaluate the dynamic effects of tea plantation encroachment on forest landscape pattern change by using time series Landsat 5/7/8 data from 1991 to 2021 on the Google Earth Engine (GEE) platform. First, a pixel- and phenology-based algorithm was applied to generate tea plantations encroachment into forests maps for seven historical periods. Second, three indices including the tea plantations encroachment index (TPEI), the growth area of tea plantations encroachment into forests (GATEF), and the growth index of tea plantations encroachment into forests (GITEF) were used to quantify the tea plantations encroachment into forests of seven historical periods. Third, the effects of forests landscape pattern resulting from tea plantations encroachment were evaluated in class metrics and landscape metrics respectively. Our results show a total of 13,721 ha of GATEF from the early 1990s to the early 2020s. The GITEF increased from the early 1990s to the early 2010s and decreased from the early 2010s to the early 2020s in our study area. And the TPEI indicates that the edge encroachment mode dominated in our study period. Correlation analysis indicates that tea plantations encroachment level had significant correlation coefficients with landscape pattern indices (such as CONTAG (r = −0.91), ED (r = 0.95), DIVISION (r = 0.85), and SHEI (r = 0.86)), which indicates that the level of tea plantations encroachment affects significantly the forest landscape pattern. This study provides a promising approach to quantifying the effect of forest landscape pattern results from tea plantations encroachment. © 2022 The Authors

关键词： Deforestation

来源：评论

学校读者我要写书评

暂无评论

Road Crack Detection Algorithm Based on Improved YOLOv8

Road Crack Detection Algorithm Based on Improved YOLOv8

引用

IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)

作者： Peng Yanfei Ji Yue Liaoning Key Laboratory of Radio Frequency and Big Data for Intelligent Applications School of Electronic and Information Engineering Liaoning Technical University Huludao Liaoning China School of Electronic and Information Engineering Liaoning Technical University Huludao Liaoning China

Road crack detection is of great significance for maintaining road quality, improving road safety, optimizing resource allocation and protecting environment. Aiming at the problems of low recognition accuracy, high false detection rate and false detection rate of existing road crack detection, an improved road crack detection algorithm YOLOv8-YP based on YOLOv8 is proposed. Firstly, the attention mechanism GAM is introduced into the backbone network and neck network to enhance the ability of extracting features of different scales from fracture images. Secondly, SPDConv is used to replace Conv in the backbone network to improve the recognition rate of slender and tiny cracks in the backbone network. Finally, DIoU function is used to optimize the bounding box loss of the network, so that the network can converge quickly and provide finer detection results. The experimental results show that the improved algorithm model YOLOv8-YP and the original algorithm YOLOv8n are improved by 2.2% and 2.3% in mAP @ 0.5 and mAP @ 0.5: 0.95, respectively. The improved algorithm YOLOv8-YP has better detection effect on road cracks, and can identify and locate road cracks quickly and accurately.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised Learning with Nearest-Neighbor Label and Consistency Regularization 1

引用

4th International Conference on Machine Learning for Cyber Security, ML4CS 2022

作者： Zheng, Guolin Li, Zuoyong Hu, Wenkai Fan, Haoyi Ching, Fum Yew Yu, Zhaochai Chen, Kaizhi College of Computer and Data Science Fuzhou University Fuzhou350108 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Minjiang University Fuzhou350121 China School of Computer and Artificial Intelligence Zhengzhou University Zhengzhou450001 China School of Computer Sciences Universiti Sains Malaysia Penang11800 Malaysia Minjiang University Fuzhou350121 China

ISBN: (数字)9783031200991

ISBN: (纸本)9783031200984

Semi-supervised learning, a system dedicated to making networks less dependent on labeled data, has become a popular paradigm due to its strong performance. A common approach is to use pseudo-labels with unlabeled data for training, however, pseudo-labels cannot correct their own errors. In this paper, we propose a semi-supervised method that uses nearest neighbor samples to obtain pseudo-labels and combines consistency regularization for image classification. Our method obtains pseudo-labels by computing the similarity of the data distribution between the weakly-augmented version of the unlabeled data and the labeled data stored in the support set and combines the consistency of the strongly-augmented version and the weakly-augmented version of the unlabeled data. We compared with several standard semi-supervised learning benchmarks and achieved a competitive performance. For example, we achieved an accuracy of 94.02 % on CIFAR-10 with 250 labels and 97.50 % on SVNH with 250 labels. It even achieved 91.59 % accuracy with only 40 labels data in the CIFAR-10. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Multi-agent Collaboration for Vehicular Task Offloading Using Federated Deep Reinforcement Learning

引用

IEEE Transactions on Mobile Computing 2025年

作者： Chen, Xing Xiao, Bohuai Lin, Xinyu Chen, Zheyi Min, Geyong Fuzhou University College of Computer and Data Science Fuzhou350116 China Ministry of Education Engineering Research Center of Big Data Intelligence Fuzhou350002 China Fuzhou University Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou350116 China University of Exeter Department of Computer Science ExeterEX4 4QF United Kingdom

Mobile Edge Computing (MEC) distributes resources such as computing, storage, and bandwidth to the side close to users, which can provide low-latency services to in-vehicle users, thus promising a more efficient and safer driving environment. However, due to the dynamic scale of vehicle and the variability of resource requirements, it is a significant challenge to quickly obtain effective task offloading in large-scale vehicle scenarios. The existing studies generally adopt the centralized decision-making method, with long decision-making time and high computational overhead, which cannot effectively achieve good offloading decisions in large-scale scenarios. To address these problems, we propose a Multi-agent Collaborative Method for vehicular task offloading using Federated Deep Reinforcement Learning called MCM-FDRL. First, each vehicle as an agent, independently makes offloading decisions based on local information. Next, the offloading decision model of each vehicle is obtained through federated reinforcement learning training. At runtime, an effective vehicle offloading plan can be gradually developed through multi-agent collaboration. Using two real-world datasets, experiments show that the MCM-FDRL has good adaptability and scalability. Moreover, compared to the state-of-the-art methods, the task's average response time of the MCM-FDRL is reduced by 9.75%-64.90%, respectively. © 2002-2012 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

CrossDiff: Exploring Self-Supervised Representation of Pansharpening via Cross-Predictive Diffusion Model

arXiv

引用

arXiv 2024年

作者： Xing, Yinghui Qu, Litao Zhang, Shizhou Zhang, Kai Zhang, Yanning Ran, Lingyan Zhang, Xiuwei Yin, Hanlin The Shaanxi Provincial Key Laboratory of Speech and Image Information Processing The National Engineering Laboratory for Integrated Aerospace-GroundOcean Big Data Application Technology School of Computer Science Northwestern Polytechnical University Xi’an710072 China The Research Development Institute Northwestern Polytechnical University in Shenzhen Shenzhen518057 China

Fusion of a panchromatic (PAN) image and corresponding multispectral (MS) image is also known as pansharpening, which aims to combine abundant spatial details of PAN and spectral information of MS. Due to the absence of high-resolution MS images, available deep-learning-based methods usually follow the paradigm of training at reduced resolution and testing at both reduced and full resolution. When taking original MS and PAN images as inputs, they always obtain sub-optimal results due to the scale variation. In this paper, we propose to explore the self-supervised representation of pansharpening by designing a cross-predictive diffusion model, named CrossDiff. It has two-stage training. In the first stage, we introduce a cross-predictive pretext task to pre-train the UNet structure based on conditional DDPM, while in the second stage, the encoders of the UNets are frozen to directly extract spatial and spectral features from PAN and MS, and only the fusion head is trained to adapt for pansharpening task. Extensive experiments show the effectiveness and superiority of the proposed model compared with state-of-the-art supervised and unsupervised methods. Besides, the cross-sensor experiments also verify the generalization ability of proposed self-supervised representation learners for other satellite’s datasets. We will release our code for reproducibility. © 2024, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A K-Band Wideband Air-Filled Coaxial Transmission Line With CNC-Machined Gap Waveguide Package

A K-Band Wideband Air-Filled Coaxial Transmission Line With ...

引用

European Conference on Microwave

作者： Jin Li Zheming Li Sicheng Chen Zhihong Xu Tao Yuan Guangdong Provincial Mobile Terminal Microwave and Millimeter-Wave Antenna Engineering Research Center College of Electronics and Information Engineering Shenzhen University China Guangdong-Hong Kong Joint Laboratory for Big Data Imaging and Communication China State Key Laboratory of Millimeter Waves China

This paper reports on a new class of packaging scheme for air-filled self-suspended coaxial transmission lines (TLs) using gap waveguide technology. This scheme exploits a periodic electromagnetic bandgap (EBG) architecture of the gap waveguide and the EBG structure behaves as an alternative for the outer conductor of the coaxial TL. The coaxial TL packaged with the gap waveguide is capable of realizing single TEM-mode transmission in a wide bandwidth, without wave leakage from air gaps of the gap waveguide due to the attractive EBG characteristic. A gap-waveguide-packaged 50$-\Omega$ air-filled square coaxial TL operating at K band is designed and implemented. The TL is made out of copper by employing computer numerical controlled machining process. The manufactured TL demonstrates at 16-28 GHz an insertion loss (IL) of 0. 36-1.09dB (an estimated attenuation factor of lower than 0.35 dB/cm excluding the IL from RF connectors) and a group delay of 0.1-0.19 ns. The work indicates extensive applicability of the gap waveguide in the packaging of other air-filled coaxial TL-based passive components.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sequence-to-Sequence Multi-Hop Knowledge Reasoning Based on Retentive Network

Sequence-to-Sequence Multi-Hop Knowledge Reasoning Based on ...

引用

Computer Information Science and Application Technology (CISAT), International Conference on

作者： Ruilin Su Wanshan Zhang Dunhui Yu Hubei University Wuhan China Wuhan China School of Computer Science and Information Engineering Hubei University Wuhan China Hubei Key Laboratory of Big Data Intelligent Analysis and Application Hubei University Wuhan China Engineering and Technical Research Center of Hubei Province in Software Engineering Wuhan China

ISBN: (数字)9798350375107

ISBN: (纸本)9798350375114

Multi-hop Knowledge Reasoning is a task that involves generating an answer given a query and a knowledge graph. Existing sequence-to-sequence reasoning models use the Transformer to encode and decode sequences, but these models have some flaws, such as the inability to effectively handle long-sequence reasoning and susceptibility to exposure bias. To address these issues, we provides a sequence-to-sequence reasoning model named STSR, which is based on Retentive Network. Aiming at improving training efficiency through parallel training, this model leverages the advantages in Retentive Network, reduce time overhead, and enhance reasoning efficiency through iterative reasoning. It effectively mitigates the problems of high spatial overhead and low efficiency in long-sequence reasoning faced by the Transformer. Moreover, it retains and updates historical information during the encoding and decoding process, enhancing the model’s memory and generalization capabilities. Additionally, the Scheduled Sampling method is adopted to alleviate the exposure bias introduced during reasoning, which involves using the model’s own output as the input for the next moment with a certain probability during training, instead of using the true label. We conduct the experiment on six public datasets, with the results showing that the proposed model outperforms existing baseline models in terms of precision and generation quality. This paper provides a new solution for the task of sequence-to-sequence multihop knowledge reasoning and also demonstrates the potential application of the Retentive Network in natural language processing.

关键词： Training Knowledge engineering Accuracy Spread spectrum communication Knowledge graphs Transformers Sampling methods Cognition Natural language processing Iterative decoding

来源：评论

学校读者我要写书评

暂无评论

Improving Classroom Quality by Analyzing Student Behaviors Through Computer Vision

Improving Classroom Quality by Analyzing Student Behaviors T...

引用

Information Science and Education (ICISE-IE), International Conference on

作者： Xiaopan Chen Boyuan Li Xiaoke Zhu Tao Zhang School of Computer and Information Engineering Henan University Kaifeng China Henan Engineering Research Center of Intelligent Technology Henan University Kaifeng China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China

This paper aims to enhance the efficiency of teaching and learning by leveraging computer vision technology for automated analysis of student behavior in the classroom. We propose a feature-enhanced method for recognizing student behavior, which integrates an Upsampling module (UPS) and a convolutional block layer (CBL) module into the YOLOv5 model. This innovative approach significantly improves the detection and feature extraction capabilities for student targets, effectively addressing challenges associated with small-sized targets and lowresolution images. Through algorithm optimization, it achieves a balance in sample diversity, enhancing the model's adaptability and generalizability in complex classroom environments. Building upon these technological advancements, we have developed a Classroom Student Posture Perception System (CSP2S). This system integrates functions for data collection, student behavior detection, and result visualization. The CSP2S operates in realtime by capturing and analyzing students’ behavioral dynamics while providing teachers with immediate feedback. Experimental results demonstrate that this system substantially reduces teachers’ workload in student assessment, offering significant potential to improve teaching effectiveness. These robust technical advancements provide strong support for future applications in real educational environments.

关键词：

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：