检索结果-内蒙古大学图书馆

Chinese intelligent Automation Conference, CIAC 2023

作者： Qi, Yuting Wang, Bo Liu, Lei Fan, Huijin Wang, Yongji National Key Laboratory of Multispectral Information Intelligent Processing Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9789819961863

This paper proposes a new approach for solving trajectory optimization problems with uncertain system parameters, which is the generalized quasi-spectral version of unscented model predictive static programming. The proposed method combines two existing techniques, the generalized quasi-spectral model predictive static programming and the unscented optimal control, to generate control solutions that can meet multiple constraints, while minimizing the covariance of the terminal output. The technique has shown good robustness in simulations and has been demonstrated to be effective in solving ascent trajectory optimization problems of hypersonic vehicles, providing a reference trajectory for guidance. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2023.

关键词： Hypersonic vehicles

来源：评论

学校读者我要写书评

暂无评论

Face Forgery Detection Based on Fine-Grained Clues and Noise Inconsistency

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第1期6卷 144-158页

作者： Zhang, Dengyong He, Ruiyi Liao, Xin Li, Feng Chen, Jiaxin Yang, Gaobo Changsha University of Science and Technology Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation the School of Computer and Communication Engineering Changsha410114 China Hunan University Changsha410082 China

Deepfake detection has gained increasing research attention in media forensics, and a variety of works have been produced. However, subtle artifacts might be eliminated by compression, and the convolutional neural networks (CNNs)-based detectors are invalidated for fake face images with compression. In this work, we propose a two-stream network for deepfake detection. We observed that high-frequency noise features and spatial features are inherently complementary to each other. Thus, both spatial features and high-frequency noise features are exploited for face forgery detection. Specifically, we design a double-frequency transformer module (DFTM) to guide the learning of spatial features from local artifact regions. To effectively fuse spatial features and high-frequency noise features, a dual-domain attention fusion module (DDAFM) is designed. We also introduce a local relationship constraint loss, which requires only image-level labels, for model training. We evaluate the proposed approach on five large-scale benchmark datasets, and extensive experimental results demonstrate the proposed approach outperforms most SOTA works. © 2024 IEEE.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Lightweight Single Image Super-Resolution Network Integrating CNN and Transformer 27th

Lightweight Single Image Super-Resolution Network Integratin...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Zhu, Kai Chen, Li School of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Wuhan China

ISBN: (纸本)9783031781247

Recently, remarkable progress has been achieved in single image super-resolution using methods based on CNN and Transformer architectures. However, existing approaches often construct a substantial number of network layers, leading to a significant increase in performance requirement and memory consumption, thereby limiting the practical deployment and usability of the models. To address this issue, we propose an Alternating CNN Transformer Block and an Integrative CNN Efficient Transformer for single image super-resolution. We enhance feature extraction efficiency by combining CNN within and between Transformer modules. In addition, we propose two novel structures: Multi-branch Gated CNN and Parallel Channel Attention, aiming to efficiently extract local spatial information and global channel information from images. Extensive experiments demonstrate that our model achieves high performance while maintaining low model complexity. The proposed model attains PSNR values of 32.32 and 30.78 for the Set5 and Manga109 benchmark datasets, respectively, at a scale factor of ×4. Compared to other lightweight super-resolution models, our proposed model outperforms them at lower computational costs. The source codes are available at https://***/kylechuuuuu/ICTSRN. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： HTTP

来源：评论

学校读者我要写书评

暂无评论

Robust Attitude Control for Flying-Wing UAV Using Modified Incremental Nonlinear Dynamic Inversion

Robust Attitude Control for Flying-Wing UAV Using Modified I...

引用

2023 China Automation Congress, CAC 2023

作者： Li, Wangmian Xue, Chenlong Wang, Bo Liu, Lei Fan, Huijin Yang, Jiahao School of Artificial Intelligence and Automation Huazhong University of Science and Technology National Key Laboratory of Multispectral Information Intelligent Processing Technology Wuhan430074 China

ISBN: (纸本)9798350303759

This paper proposes a modified incremental nonlinear dynamic inversion (MINDI) control scheme for attitude tracking control of flying-wing unmanned aerial vehicles (UAV). Based on the incremental dynamic inversion formulation, the angular rate controller is designed to alleviate the nonlinearity and coupling characteristics of the flying-wing configuration. Then, in order to address the impact of factors such as angular acceleration measurement errors and actuator faults on the control performance, a super-twisting-like fixed-time convergence algorithm is introduced to replace the linear control law in the nominal INDI method, ensuring rapid convergence of tracking errors. The simulation results demonstrate that the proposed method effectively mitigates the impact of such errors and faults. Compared to the nominal INDI, the modified method exhibits stronger fault tolerance and robustness in the attitude tracking control of the flying-wing UAV. © 2023 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

EBVS: An Efficient Pseudonymous Batch Verification Scheme for Vehicular Networks 2nd

EBVS: An Efficient Pseudonymous Batch Verification Scheme fo...

引用

2nd International Conference on Data Security and Privacy Protection, DSPP 2024

作者： Wang, Ping Wang, Shuokang College of Electronics and Information Engineering Shenzhen University Guangdong Shenzhen518060 China Guangdong Provincial Key Laboratory of Intelligent Information Processing Guangdong Shenzhen518060 China

ISBN: (纸本)9789819785452

With the rapid development of intelligent transportation systems, the security of vehicular network communication architectures has become a focal point of research. This paper introduces a vehicular network communication system based on cloud computing and blockchain technology, aimed at enhancing the efficiency and security of vehicle privacy protection and message authentication. The system architecture comprises five core components: the Traffic Safety Management Center (TSMC), Cloud Node Servers (CNS), Roadside Units (RSU), Vehicles (V), and the Traffic Safety Blockchain (TSB). In the system initialization phase, public-private key pairs based on elliptic curves and bilinear mappings are generated to provide fundamental encryption and authentication mechanisms. During the identity registration stage, vehicles acquire a pseudonymous identity (PID), used for subsequent message authentication, ensuring vehicle privacy while maintaining identity legitimacy. Through vehicle message authentication and the traffic safety blockchain, the system facilitates efficient batch processing of messages and immutable data records, enhancing the transparency and credibility of traffic data. Furthermore, the system conducts a detailed analysis of potential external threats and malicious vehicle behaviors, proposing corresponding countermeasures such as enhanced data integrity monitoring, adaptive risk management, and collaborative governance strategies. These measures enable the system not only to effectively defend against external attacks but also to monitor and prevent malicious vehicle operations in real-time, thereby ensuring the safe and stable operation of intelligent transportation systems. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Risk management

来源：评论

学校读者我要写书评

暂无评论

Deep Multi-image Hiding with Random key 1

引用

1st International Conference on Artificial Intelligence Security and Privacy, AIS and P 2023

作者： Zhang, Wei Tang, Weixuan Rao, Yuan Li, Bin Huang, Jiwu Institute of Artificial Intelligence Guangzhou University Guangzhou China Guangdong Key Laboratory of Intelligent Information Processing and Shenzhen Key Laboratory of Media Security Shenzhen University Shenzhen China

ISBN: (数字)9789819997855

ISBN: (纸本)9789819997848

Multi-image hiding is the technique of hiding multiple secret images within one cover image. In most existing methods, it is possible for one receiver to reveal other receivers’ secret images. To improve the privacy and secrecy among different receivers, one possible solution is to introduce the key mechanism, wherein only the receiver with private key has the permission to reveal the corresponding secret image. In this paper, a multiple image hiding method called DEMIHAK (Deep Multiple Image Hiding with Random key) is proposed, which utilizes deep neural networks to implement a secure key verification. From the side of the sender, each secret image is assigned with a random key, according to which can sample a key map. Then, BindNet is utilized to incorporate a secret image and its key map into a processed secret image, and HideNet is adopted to conceal multiple processed secret images within cover image and generate a stego image. From the side of the receiver, according to a transmitted private key, RevealNet can be applied to reveal the corresponding secret image from the stego image. Experimental results show that DEMIHAK outperforms existing method from the perspective of visual quality, security, and secrecy. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Colour Variation Minimization Retinex Decomposition and Enhancement with a Multi-Branch Decomposition Network

引用

Chinese Journal of Electronics 2023年第4期32卷 908-919页

作者： DENG Jiawei YU Zhenming PANG Guangyao Guangxi Key Laboratory of Machine Vision and Intelligent Control Wuzhou University School of Information and Communication Guilin University of Electronic Technology

This paper proposes a colour variation minimization retinex decomposition and enhancement with a multi-branch decomposition network(CvmD-net)to remove single image darkness. The network overcomes the problem that retinex deep learning model relies on matching bright images to process dark images. Specifically, our method takes two stages to light up the darkness in initial images: image decomposition and brightness optimization. We propose an input constant feature prior mechanism(ICFP) based on reflection constant features. The mechanism extracts structure and colour from the input images and constrains the reflected images output from the decomposition model to reduce color distortion and artifacts. The noise amplification during decomposition is addressed by a multi-branch decomposition network. Sub-networks with different structures are employed to focus on different prediction tasks. This paper proposes a reference mechanism for input brightness. This mechanism optimizes the output brightness distribution by calculating the reference brightness of the dark *** results on two benchmark datasets, namely,LOL and ZeroDCE, demonstrate that the proposed method can better balance dense noise interference and colour restoration. For the evaluation on real images, we collect Skynet images at night to verify the performance of the proposed approach. Compared with the state-of-the-art non-reference retinex decomposition-enhancement models,this paper has the best brightness optimization.

关键词： Reflectivity Image color analysis Brightness Interference Feature extraction Minimization Reflection

来源：评论

学校读者我要写书评

暂无评论

Cross-Modal Ship Grounding: Towards Large Model for Enhanced Few-Shot Learning 27th

Cross-Modal Ship Grounding: Towards Large Model for Enhanced...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Hu, Quan Chen, Li Feng, Zhida Chen, Yaojie School of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan University of Science and Technology Wuhan China

ISBN: (纸本)9783031781124

A growing body of research indicates that employing large models for adaptation to downstream tasks often yields remarkable performance. However, in the domain of ship detection, the potential of these large models is frequently underutilized due to domain shift issues. This paper introduces the Cross-Modal Ship Grounding (CSG) model, which leverages an efficient Cross-Modal Adapter (CMA) technology to transfer the general detection capabilities of large models to ship images, addressing domain shift with minimal training costs. To mitigate the challenges posed by complex and variable background interference, the Water-Land Separation (WLS) module is proposed to focus specifically on the water area. This module effectively addresses the issue of background target interference, thereby enhancing the model’s accuracy in complex scenes. Empirical evaluations on both private and public datasets demonstrate that the CSG model surpasses all state-of-the-art models in performance. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Particle Swarm Algorithm Based on Fitness Landscape information 13

An Enhanced Particle Swarm Algorithm Based on Fitness Landsc...

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Diao, Zhenya Yu, Fei Guan, Jian Liu, Meitong School of Physics and Information Engineering Minnan Normal University Key Lab of Intelligent Optimization and Information Processing Zhangzhou36300 China School of Physics and Information Engineering Minnan Normal University Key Laboratory of Light Field Manipulation and System Integration Applications in Fujian Province Key Lab of Intelligent Optimization and Information Processing Zhangzhou36300 China

ISBN: (纸本)9798350308365

In the original Particle Swarm Optimization (PSO), the selection of parameters significantly impacts the search capability of PSO. The paper introduces an innovative algorithm called Fitness Landscape-based PSO (FLPSO) to address the impact of parameter selection on the search capability of PSO. The algorithm focuses on acquiring fitness landscape information and analyzing the population state to intelligently select appropriate parameters in each generation. FLPSO defines four primary states: exploration, exploitation, convergence, and escaping state. In the convergence state, an elite learning strategy is incorporated to help the algorithm escape potential local optima by targeting the global best particle. To validate the efficacy of FLPSO, the paper conducted experiments on 30 different characteristic test functions from CEC2017. FLPSO was compared with six existing algorithms: PSO, PSO-TVAC, APSO, AWPSO, RPSO and ASRPPSO. The experimental results showed significant improvements in FLPSO, providing promising evidence for its effectiveness. © 2024 IEEE.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Gait Characteristics and Adaptation Strategies of Ants with Missing Legs

引用

Journal of Bionic Engineering 2024年第5期21卷 2409-2423页

作者： Ming Zeng Chang Meng Bin Han Yuanhao Li Hanshen Yu Huijia Fu Shutong Zhong The Tianjin Key Laboratory of Intelligent Unmanned Swarm Technology and System School of Electrical and Information EngineeringTianjin UniversityTianjin300072China State Grid Tianjin Electric Power Company Tianjin300000China

This paper systematically studies the movement behavior changes of Camponotus japonicus under one or two leg ***,a linear motion channel matching the size of the ants'legs was designed,and the movements of ants with different leg injuries were captured using high-speed cameras,constructing a comprehensive video dataset of ants'movements with missing ***,stable and reliable motion position information for keypoints on the ants'bodies and legs was obtained by utilizing low-annotation biometric keypoint detection ***,by analyzing the filtered gait data,information about the changes in the step locational points areas,phase differences,and duty factors of the injured ants'remaining legs was *** analysis of the ants'gait characteristics revealed some common adjustment patterns when the ants were in the injured ***,the study found that the loss of a foreleg had a significant impact on the ants'*** two legs were missing,the loss of both legs on the same side had a greater effect on movement,whereas symmetric opposite-side leg loss conditions had a lesser *** research will provide an important reference for the subsequent design of gait adjustment algorithms for biomimetic multi-legged robots under damaged conditions.

关键词： Ant gait characteristics Leg missing Adaptation strategies Biometric keypoint detection Hexapod

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：