检索结果-内蒙古大学图书馆

Proceedings of the 38th International Conference on Neural Information Processing systems

作者： Yu Zeng Yang Zhang Jiachen Liu Linlin Shen Kaijun Deng Weizhao He Jinbao Wang Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University and Shenzhen Institute of Artificial Intelligence and Robotics for Society and National Engineering Laboratory for Big Data System Computing Technology Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University and Guangdong Provincial Key Laboratory of Intelligent Information Processing

ISBN: (纸本)9798331314385

Hair editing is a critical image synthesis task that aims to edit hair color and hairstyle using text descriptions or reference images, while preserving irrelevant attributes (e.g., identity, background, cloth). Many existing methods are based on StyleGAN to address this task. However, due to the limited spatial distribution of StyleGAN, it struggles with multiple hair color editing and facial preservation. Considering the advancements in diffusion models, we utilize Latent Diffusion Models (LDMs) for hairstyle editing. Our approach introduces Multi-stage Hairstyle Blend (MHB), effectively separating control of hair color and hairstyle in diffusion latent space. Additionally, we train a warping module to align the hair color with the target region. To further enhance multi-color hairstyle editing, we fine-tuned a CLIP model using a multi-color hairstyle dataset. Our method not only tackles the complexity of multi-color hairstyles but also addresses the challenge of preserving original colors during diffusion editing. Extensive experiments showcase the superiority of our method in editing multi-color hairstyles while preserving facial attributes given textual descriptions and reference images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generative AI-Enhanced Cooperative MEC of UAVs and Ground Stations for Unmanned Surface Vehicles 59

Generative AI-Enhanced Cooperative MEC of UAVs and Ground St...

引用

59th Annual Conference on Information Sciences and systems, CISS 2025

作者： You, Jiahao Jia, Ziye Dong, Chao Wu, Qihui Han, Zhu Nanjing University of Aeronautics and Astronautics The Key Laboratory of Dynamic Cognitive System of Electromagnetic Spectrum Space Ministry of Industry and Information Technology Nanjing211106 China Southeast University National Mobile Communications Research Laboratory Nanjing211111 China University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States Kyung Hee University Department of Computer Science and Engineering Seoul446-701 Korea Republic of

ISBN: (纸本)9798331513269

The increasing deployment of unmanned surface vehicles (USVs) require computational support and coverage in applications such as maritime search and rescue. Unmanned aerial vehicles (UAVs) can offer low-cost, flexible aerial services, and ground stations (GSs) can provide powerful supports, which can cooperate to help the USVs in complex scenarios. However, the collaboration between UAVs and GSs for USVs faces challenges of task uncertainties, USVs trajectory uncertainties, heterogeneities, and limited computational resources. To address these issues, we propose a cooperative UAV and GS based robust multi-access edge computing framework to assist USVs in completing computational tasks. Specifically, we formulate the optimization problem of joint task offloading and UAV trajectory to minimize the total execution time, which is in the form of mixed integer nonlinear programming and NP-hard to tackle. Therefore, we propose the algorithm of generative artificial intelligence-enhanced heterogeneous agent proximal policy optimization (GAI-HAPPO). The proposed algorithm integrates GAI models to enhance the actor network ability to model complex environments and extract high-level features, thereby allowing the algorithm to predict uncertainties and adapt to dynamic conditions. Additionally, GAI stabilizes the critic network, addressing the instability of multi-agent reinforcement learning approaches. Finally, extensive simulations demonstrate that the proposed algorithm outperforms the existing benchmark methods, thus highlighting the potentials in tackling intricate, cross-domain issues in the considered scenarios. © 2025 IEEE.

关键词： Unmanned surface vehicles

来源：评论

学校读者我要写书评

暂无评论

A sketch recognition method based on bi-modal model using cooperative learning paradigm

引用

Neural Computing and Applications 2024年第23期36卷 14275-14290页

作者： Zhang, Shihui Wang, Lei Cui, Zhiguo Wang, Shi School of Information Science and Engineering Yanshan University Hebei Street West Section Hebei Province Qinhuangdao066000 China Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Yanshan University Hebei Street West Section Hebei Province Qinhuangdao066000 China School of Information Technology Hebei University of Business and Economics Xuefu Road Hebei Province Shijiazhuang050061 China School of Mathematics and Information Science and Technology Hebei Normal University of Science and Technology Hebei Street West Section Hebei Province Qinhuangdao066000 China

Static image is an important form of displaying a sketch, representing the appearance information of the sketch. And a stroke sequence composed of several points can also express the shape and contour information of the sketch. Therefore, it is very reasonable to treat a sketch as point-modal data and image-modal data simultaneously. In this paper, a method based on bi-modal model using cooperative learning paradigm is proposed for the sketch recognition task. Specifically, in the point-modal branch, a structural point convolution block is developed by properly dividing local regions to preserve the structural information. In the image-modal branch, the hierarchical residual structure is used to fully extract image-modal features. To reduce the negative impact of noisy samples on the recognition performance, a cooperative learning paradigm is designed based on different perceptual abilities of two modal branches on noisy samples, that is, when training the two branches, the noisy samples can be filtered out through information exchanges and mutual learning. Extensive experiments on the sketch datasets TU-Berlin and QuickDraw show that the proposed method outperforms most baseline methods and has many advantages such as no dependence on additional data and stroke information. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Optimizations and Deoptimizations for Escape Analysis in Open World

引用

Chinese Journal of Electronics 2023年第2期19卷 211-216页

作者： Xiaohua Shi Gansha Wu Jin Maozhong Guei-Yuan Lueh School of Computer Science Beihang University Beijing China Programming System Laboratory Microprocessor Technology Labs Intel Corporation Beijing China

This paper introduced the optimization and deoptimization technologies for Escape analysis in open world. These technologies are used in a novel Escape analysis framework that has been implemented in Open runtime platform, Intel's open-source Java virtual machine. We introduced the optimization technologies for synchronization removal and object stack allocation, as well as the runtime deoptimization and compensation work. The deoptimization and compensation technologies are crucial for a practical Escape analysis in open world. We evaluated the runtime efficiency of the deoptimization and compensation work on benchmarks like SPECjbb2000 and SPECjvm98.

关键词： Java Runtime Education Medical services Benchmark testing Virtual machining Synchronization

来源：评论

学校读者我要写书评

暂无评论

Initialization Approach for Nonlinear State-Space Identification via the Subspace Encoder Approach

引用

IFAC-PapersOnLine 2023年第2期56卷 5146-5151页

作者： Rishi Ramkannan Gerben I. Beintema Roland Tóth Maarten Schoukens Control System group Eindhoven University of Technology Eindhoven the Netherlands Systems and Control Laboratory Institute for Computer Science and Control Budapest Hungary

The SUBNET neural network architecture has been developed to identify nonlinear state-space models from input-output data. To achieve this, it combines the rolled-out nonlinear state-space equations and a state encoder function, both parameterised as neural networks The encoder function is introduced to reconstruct the current state from past input-output data. Hence, it enables the forward simulation of the rolled-out state-space model. While this approach has shown to provide high-accuracy and consistent model estimation, its convergence can be significantly improved by efficient initialization of the training process. This paper focuses on such an initialisation of the subspace encoder approach using the Best Linear Approximation (BLA). Using the BLA provided state-space matrices and its associated reconstructability map, both the state-transition part of the network and the encoder are initialized. The performance of the improved initialisation scheme is evaluated on a Wiener-Hammerstein simulation example and a benchmark dataset. The results show that for a weakly nonlinear system, the proposed initialisation based on the linear reconstructability map results in a faster convergence and a better model quality.

关键词： Nonlinear system Identification Machine Learning Neural Networks State-Space Best Linear Approximation

来源：评论

学校读者我要写书评

暂无评论

A Simultaneous Wireless Information and Power Transfer-based Multi-hop Clustering Routing Protocol for RF Energy Harvesting-Cognitive Radio Sensor Networks

Journal of Network Intelligence

引用

Journal of Network Intelligence 2023年第3期8卷 991-1007页

作者： Wang, Ji-Hong Su, Xi-Tong Ge, Yi-Yang Chen, Yeh-Cheng Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology Ministry of Education Northeast Electric Power University China School of Electrical Engineering Northeast Electric Power University 169 Changchun Road Jilin132012 China Department of Computer Science University of California DavisCA001313 United States

Radio frequency energy harvesting (RF EH) and clustering are promising solutions to solve the energy constraint problem faced by cognitive radio sensor networks (CRSNs). However, study on clustering routing protocol design for RF EH-CRSNs is still in the initial stage, and there lacks of solutions for inter-cluster routing problem, which restricts the network scalability. In addition, unbalanced harvested energy and energy consumption may result in premature death of nodes in key position, which will significantly reduce the network performance. In this paper, a simultaneous wireless information and power transfer (SWIPT)-based multi-hop clustering routing protocol (SMCRP) is proposed for RF EH-CRSNs to well balance the residual energy distribution among nodes and postpone node death. Apart from the RF energy harvested from dedicated or ambi-ent energy sources, the energy obtained through intra-cluster and inter-cluster SWIPT is also considered to facilitate high-quality cluster heads selection, cluster formation and inter-cluster route establishment. Power splitting ratio is derived based on the residual energy of CRSNs nodes and their energy consumption to enable effective implementation of SWIPT in CRSNs. Simulation results show that SMCRP is effective in balancing the residual energy distribution among nodes and improving node sustainability. To be specific, compared with current clustering protocols, the network lifetime is extended by 64.07% while intra-cluster energy balance degree and network energy balance degree are improved by 15.1% and 7.82%, respectively. © 2023 ISSN 2414-8105 (Online).

关键词： Cognitive radio

来源：评论

学校读者我要写书评

暂无评论

RPViT: Vision Transformer Based on Region Proposal 2022

RPViT: Vision Transformer Based on Region Proposal

引用

5th International Conference on Image and Graphics Processing, ICIGP 2022

作者： Ge, Jing Wang, Qianxiang Tong, Jiahui Gao, Guangyu School of Computer Science and Technology Beijing Institute of Technology China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China Beijing Electro-Mechanical Engineering Institute Beijing China

ISBN: (纸本)9781450395465

Vision Transformers constantly absorb the characteristics of convolutional neural networks to solve its shortcomings in translational invariance and scale invariance. However, dividing the image by a simple grid often destroys the position and scale features in the image at the beginning of the network. In this paper, we propose a vision transformer based on region proposal, which obtains the inductive bias in a simple way. Specifically, RPViT achieves locality and scale-invariance by extracting regions with locality using a traditional region proposal algorithm and deflating objects of different scales to the same scale by a bilinear interpolation algorithm. In addition, to enable the network to fully utilize and encode diverse candidate objects, a multi-class token approach based on orthogonalization is proposed and applied. Experiments on ImageNet demonstrate that RPViT outperforms baseline converters and related work. © 2022 ACM.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

ResPocket: A Multi-Scale Feature Fusion Method for Improving Protein Binding Site Detection

ResPocket: A Multi-Scale Feature Fusion Method for Improving...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Xiaoli Lin Wenli Yang Yaoyu Chen Xiongwei Liao Zimo Wu Xiaolong Zhang Hubei Key Laboratory of Intelligent Information Processing and Real-Time Industrial System School of Computer Science and Technology Wuhan University of Science and Technology China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Accurate detection of protein binding sites is critical for facilitating drug design. Most existing models rely on features at a single scale, leading to the loss of crucial global or local structural information. Therefore, this paper proposes a novel 3D model (ResPocket), to fully capture the multi-scale features of proteins. First, Residual Block (ResB) based on U-Net is used to capture features from different scales, including global and local structural information. Then, an Enhanced Attention Module (EAM) is designed to encode semantic dependencies by effectively capturing global context information. In addition, ResPocket focuses on learning local information about protein pockets with Self-Guided Mask Block (SGMB), to increase the robustness of the overall model and reduce its dependence on external mask guidance. Experimental results show that ResPocket improves by an average of 4.89% on DCA Top-n, by an average of 1.48% and 2.25% on DCC and DVO metrics, respectively.

关键词： Proteins Protein engineering Solid modeling Accuracy Three-dimensional displays Biological system modeling Semantics Feature extraction Robustness Decoding

来源：评论

学校读者我要写书评

暂无评论

FULLY POLARIZED RADAR TARGET DETECTION AND WAVEFORM OPTIMIZATION UNDER RAINY CONDITION

FULLY POLARIZED RADAR TARGET DETECTION AND WAVEFORM OPTIMIZA...

引用

IET International Radar Conference 2023, IRC 2023

作者： Li, Xinda Cheng, Xu Ju, Xinjie Wang, Xuesong Li, Jianbing College of Electronic Science and Technology National University of Defense Technology Hunan Changsha410073 China State Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System Hunan Changsha410073 China School of Computer Science and Engineering Wuhan Institute of Technology Wuhan430205 China Hubei Key Laboratory of Intelligent Robot Wuhan430205 China

ISBN: (纸本)9781839539954

Polarization and waveform optimization can significantly improve the detection ability of fully polarized radar. However, in practical scenarios, atmospheric particles frequently induce depolarization effects on radar waves, thereby influencing precise target detection, a phenomenon predominantly observed with raindrop particles. This paper establishes a target detection model for fully polarized radar in rainy condition. Subsequently, a joint transceiver iterative optimization algorithm is devised, utilizing the maximum output signal-to-interference plus noise ratio (SINR) of the system as the benchmark, and imposing dual constraints of energy and resemblance on the transmitting waveform. Ultimately, the effectiveness of the proposed method under rainy condition is validated through simulation, and recommendations for engineering applications are provided based on the analysis. © The Institution of Engineering & technology 2023.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Quantum Remote State Preparation Based on Quantum Network Coding

引用

computers, Materials & Continua 2022年第10期73卷 119-132页

作者： Zhen-Zhen Li Zi-Chen Li Yi-Ru Sun Haseeb Ahmad Gang Xu Xiu-Bo Chen School of Information Engineering Beijing Institute of Graphic CommunicationBeijing102600China School of Computer Science and Information Engineering Zhejiang Gongshang UniversityHangzhou310018China Information Security Center State key Laboratory of Networking and Switching TechnologyBeijing University of Posts and TelecommunicationsBeijing100876China Department of Computer Science National Textile UniversityFaisalabad37610Pakistan School of Information Science and Technology North China University of TechnologyBeijing100144China Advanced Cryptography and System Security Key Laboratory of Sichuan Province China

As an innovative theory and technology,quantum network coding has become the research hotspot in quantum network *** this paper,a quantum remote state preparation scheme based on quantum network coding is *** with the general quantum remote state preparation schemes,our proposed scheme brings an arbitrary unknown quantum state finally prepared remotely through the quantum network,by designing the appropriate encoding and decoding steps for quantum network *** is worth mentioning,from the network model,this scheme is built on the quantum k-pair network which is the expansion of the typical bottleneck network—butterfly ***,it can be treated as an efficient quantum network preparation scheme due to the characteristics of network coding,and it also makes the proposed scheme more applicable to the large-scale quantum *** addition,the fact of an arbitrary unknown quantum state remotely prepared means that the senders do not need to know the desired quantum ***,the security of the proposed scheme is ***,this scheme can always achieve the success probability of 1 and 1-max flow of value ***,the communication efficiency of the proposed scheme is ***,the proposed scheme turns out to be practicable,secure and efficient,which helps to effectively enrich the theory of quantum remote state preparation.

关键词： Quantum remote state preparation quantum network coding quantum k-pair network

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：