检索结果-内蒙古大学图书馆

RGB-Based Category-Level Object Pose Estimation via Depth Recovery and Adaptive Refinement

IEEE Robotics and Automation Letters 2025年第6期10卷 5377-5384页

作者： Yang, Hui Sun, Wei Liu, Jian Zheng, Jin Zeng, Zhiwen Mian, Ajmal Hunan University National Engineering Research Center for Robot Visual Perception and Control Technology College of Electrical and Information Engineering Changsha410082 China Hunan University State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Changsha410082 China Central South University School of Architecture and Art Changsha410082 China University of Western Australia Department of Computer Science and Software Engineering CrawleyWA6009 Australia

Category-level pose estimation methods have received widespread attention as they can be generalized to intra-class unseen objects. Although RGB-D-based category-level methods have made significant progress, reliance on depth image limits practical application. RGB-based methods offer a more practical and cost-effective solution. However, current RGB-based methods struggle with object geometry perception, leading to inaccurate pose estimation. We propose depth recovery and adaptive refinement for category-level object pose estimation from a single RGB image. We leverage DINOv2 to reconstruct the coarse scene-level depth from the input RGB image and propose an adaptive refinement network based on an encoder-decoder architecture to dynamically improve the predicted coarse depth and reduce its gap from the ground truth. We introduce a 2D–3D consistency loss to ensure correspondence between the point cloud obtained from depth projection and the objects in the 2D image. This consistency supervision enables the model to maintain alignment between the depth image and the point cloud. Finally, we extract features from the refined point cloud and feed them into two confidence-aware rotation regression branches and a translation and size prediction residual branch for end-to-end training. Decoupling the rotation matrix provides a more direct representation, which facilitates parameter optimization and gradient propagation. Extensive experiments on the REAL275 and CAMERA25 datasets demonstrate the superior performance of our method. Real-world estimation and robotic grasping experiments demonstrate our model robustness to occlusion, clutter environments, and low-textured objects. Our code and robotic grasping video are available at DA-Pose. © 2016 IEEE.

关键词： Depth perception

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Power Consumption Model for GPU Data Centers with Time-VAE

A Comprehensive Power Consumption Model for GPU Data Centers...

引用

International Conference of Electrical, Electronic and Networked Energy systems, EENES 2024

作者： Wang, Senyao Wu, Jianhong Zhang, Ruozhu The School of Electrical and Computer Engineering The University of Sydney SydneyNSW2008 Australia The School of Electrical Engineering Shanghai University of Electric Power Shanghai200090 China State Key Laboratory of Alternate Electrical Power System With Renewable Energy Sources North China Electric Power University Beijing102206 China

ISBN: (纸本)9789819618675

In this study, we propose and evaluate a comprehensive power consumption model for GPU-based data centers that integrates the energy consumption of various task types, including language processing, speech recognition, and image generation, along with the power consumption of other components such as the CPU, memory, network, and storage. Using real GPU power consumption data, we measured the server energy consumption. To compensate for the limited experimental data and ensure accurate evaluation of average power consumption per unit time after model convergence, we utilize the TimeVAE model to generate supplementary data. The PCA and t-SNE visualizations validate the effectiveness of the TimeVAE model in preserving data distribution and structure. Our comprehensive model provides valuable insights into the energy consumption patterns in GPU-based data centers and offers practical guidance for optimizing energy usage to improve overall efficiency and sustainability. © Beijing Paike Culture Commu. Co., Ltd. 2025.

关键词： Data centers

来源：评论

学校读者我要写书评

暂无评论

Semantic Gaussian Mixture Variational Autoencoder for Sequential Recommendation

arXiv

引用

arXiv 2025年

作者： Li, Beibei Xiang, Tao Jin, Beihong Zheng, Yiyuan Zhao, Rui College of Computer Science Chongqing University Chongqing China Key Laboratory of System Software Chinese Academy of Sciences State Key Laboratory of Computer Science Institute of Software Chinese Academy of Science Beijing China University of Chinese Academy of Sciences Beijing China

Variational AutoEncoder (VAE) for Sequential Recommendation (SR), which learns a continuous distribution for each user-item interaction sequence rather than a determinate embedding, is robust against data deficiency and achieves significant performance. However, existing VAE-based SR models assume a unimodal Gaussian distribution as the prior distribution of sequence representations, leading to restricted capability to capture complex user interests and limiting recommendation performance when users have more than one interest. Due to that it is common for users to have multiple disparate interests, we argue that it is more reasonable to establish a multimodal prior distribution in SR scenarios instead of a unimodal one. Therefore, in this paper, we propose a novel VAE-based SR model named SIGMA. SIGMA assumes that the prior of sequence representation conforms to a Gaussian mixture distribution, where each component of the distribution semantically corresponds to one of a user’s multiple interests. For multi-interest elicitation, SIGMA includes a probabilistic multi-interest extraction module that learns a unimodal Gaussian distribution for each interest according to implicit item hyper-categories. Additionally, to incorporate the multimodal interests into sequence representation learning, SIGMA constructs a multi-interest-aware ELBO, which is compatible with the Gaussian mixture prior. Extensive experiments on public datasets demonstrate the effectiveness of SIGMA. The code is available at https://***/libeibei95/SIGMA. acceptance. © 2025, CC BY-NC-SA.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

S2KAN-SLAM: Elastic Neural LiDAR SLAM with SDF Submaps and Kolmogorov-Arnold Networks

引用

IEEE Transactions on Circuits and systems for Video Technology 2025年

作者： Wang, Zhong Zhang, Lin Wang, Hesheng Shanghai Jiao Tong University State Key Laboratory of Avionics Integration and Aviation System-of-Systems Synthesis Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Shanghai200240 China Tongji University School of Computer Science and Technology National Pilot Software Engineering School with Chinese Characteristics Shanghai201804 China

Traditional LiDAR SLAM approaches prioritize localization over mapping, yet high-precision dense maps are essential for numerous applications involving intelligent agents. Recent advancements have introduced methods leveraging neural fields to enhance mapping capabilities;however, these approaches still face several limitations. Firstly, concerning scene representation, they typically employ neural fields with high-dimensional features and multi-layer perceptron decoders utilizing non-continuous activation functions. This results in low learning efficiency and challenges in capturing high-frequency signals. Secondly, in terms of scene organization, these methods often treat the entire scene as a singular neural field, leading to inefficiencies, inflexibility, and difficulties in rectifying accumulated errors when mapping large-scale environments over extended periods. To tackle the first issue, we propose a lightweight continuous SDF regression approach by encoding the scene in single-valued embeddings and decoding SDF values from a Kolmogorov-Arnold Network. By minimizing discrepancies in measuring range, sampling distance, and decoded SDF values, we facilitate iterative frame-to-model tracking and bundle adjustment neural mapping. To mitigate the second challenge, we propose structuring the whole scene into multiple neural SDF submaps. By establishing node-node, node-submap, and loop closure constraints into a global pose graph, the system can create dense neural maps with global consistency across large-scale scenes. Experimental evaluations in both real-world and simulated settings indicate that our system achieves superior mapping completeness and accuracy, enhanced learning efficiency, reduced memory consumption, and greater flexibility compared to its counterparts. © 2025 IEEE.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

An active power control of DFIG-based wind turbine generators for frequency regulation with expected dynamic performance

引用

Applied Energy 2025年 391卷

作者： Zhao, Teyang Liu, Hui Wang, Ni Su, Jinshuo Luo, Zhiqiang Ma, Siyu School of Electrical Engineering Guangxi University Nanning530004 China Guangxi Key Laboratory of Power System Optimization and Energy Technology Guangxi University Nanning530004 China The State Key Laboratory of Internet of Things for Smart City and Department of Electrical and Computer Engineering University of Macau 519000 China

The escalating wind power penetration presents a substantial challenge in ensuring the system frequency stability. Although wind turbine generators (WTGs) can offer rapid frequency support by the presetting power trajectory response (PPTR), it will result in a secondary frequency dip (SFD) while facing the demand of restoring rotor speed after frequency regulation. Moreover, the frequency overshoot will occur due to the fixed power increment provided by PPTR under minor disturbances. In this paper, an active power control strategy of DFIG-based WTGs is proposed for eliminating frequency overshoot and mitigating SFD while providing power support for the system frequency. A rotor-speed-based power increment and power attenuation trajectory are designed to enhance the primary frequency nadir while ensuring the operation stability of WTGs. After that, SFD will be mitigated by the proposed parabolic-formed compensation power. Moreover, a power increment control mode is proposed to eliminate the frequency overshoot by a membership-function-based global controller, which can smoothly switch the combined inertial response and the improved PPTR to provide a flexible power increment. Finally, the validity of the proposed strategy in improving frequency nadir, eliminating frequency overshoot, and mitigating SFD are verified by simulations under different wind power penetration levels, disturbances, and wind conditions. © 2025

关键词： Frequency stability

来源：评论

学校读者我要写书评

暂无评论

Resilient Cooperative Control of Multiple DC Microgrids With Interconnection Networks Against Cyber Attacks

IEEE Transactions on Industrial Cyber-Physical Systems

引用

IEEE Transactions on Industrial Cyber-Physical systems 2025年 3卷 116-126页

作者： Xiao, Feng Liu, Shiyu Wei, Bo Fang, Fang Qin, Jiahu North China Electric Power University State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources Beijing102206 China North China Electric Power University School of Control and Computer Engineering Beijing102206 China North China Electric Power University New Energy Generation National Engineering Research Center Beijing102206 China University of Science and Technology of China Department of Automation Hefei230027 China

The two control objectives of voltage regulation and precise current sharing are conflicting in multi-bus DC microgrids. In this paper, a distributed control strategy is proposed, and it can achieve accurate current sharing and regulate the voltage of a critical node to the rated value. However, such a distributed control system is susceptible to potential cyber attacks that could deteriorate microgrids performances by corrupting communication links or actuators. To overcome these difficulties, we design the interconnected communication networks to establish a resilient cooperative system of multiple microgrids against unknown bounded injection attacks. The proposed resilient control strategy can achieve the control objectives of maintaining voltage regulation and current sharing within each microgrids under different operating conditions, and the interconnected system consisting of multiple microgrids cooperates to mitigate the adverse effect of cyber attacks. The dynamics and stability of the overall close-loop system of the DC microgrids are analyzed, in the present or absent of cyber attacks. Simulation results validate the effectiveness of the proposed approach in two 4-bus DC microgrids. © 2023 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Continual Reinforcement Learning for Digital Twin Synchronization Optimization

引用

IEEE Transactions on Mobile Computing 2025年

作者： Tong, Haonan Chen, Mingzhe Zhao, Jun Hu, Ye Yang, Zhaohui Liu, Yuchen Yin, Changchuan Beijing University of Posts and Telecommunications Beijing Key Laboratory of Network System Architecture and Convergence Beijing Advanced Information Network Laboratory Beijing China College of Computing and Data Science Singapore University of Miami Department of Electrical and Computer Engineering Frost Institute for Data Science and Computing Coral Gables33146 United States University of Miami Department of Industrial and Systems Engineering Coral Gables33146 United States Zhejiang University College of Information Science and Electronic Engineering Hangzhou310027 China North Carolina State University Department of Computer Science RaleighNC27695 United States Beijing Key Laboratory of Network System Architecture and Convergence China Beijing University of Posts and Telecommunications Beijing Advanced Information Network Laboratory Beijing100876 China

This article investigates the adaptive resource allocation scheme for digital twin (DT) synchronization optimization over dynamic wireless networks. In our considered model, a base station (BS) continuously collects factory physical object state data from wireless devices to build a real-time virtual DT system for factory event analysis. Due to continuous data transmission, maintaining DT synchronization must use extensive wireless resources. To address this issue, a subset of devices is selected to transmit their sensing data, and resource block (RB) allocation is optimized. This problem is formulated as a constrained Markov process (CMDP) problem that minimizes the long-term mismatch between the physical and virtual systems. To solve this CMDP, we first transform the problem into a dual problem that refines RB constraint impacts on device scheduling strategies. We then propose a continual reinforcement learning (CRL) algorithm to solve the dual problem. The CRL algorithm learns a stable policy across historical experiences for quick adaptation to dynamics in physical states and network capacity. Simulation results show that the CRL can adapt quickly to network capacity changes and reduce normalized root mean square error (NRMSE) between physical and virtual states by up to 55.2%, using the same RB number as traditional methods. © 2025 IEEE. All rights reserved.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Language-Queried Target Sound Extraction Without Parallel Training Data

Language-Queried Target Sound Extraction Without Parallel Tr...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Ma, Hao Peng, Zhiyuan Li, Xu Li, Yukai Shao, Mingjie Kong, Qiuqiang Liu, Ju School of Information Science and Engineering Shandong University Qingdao China Department of Computer Science North Carolina State University NC United States ARC Lab Tencent PCG China Key Laboratory of System and Control AMSS Chinese Academy of Sciences Beijing China The Chinese University of Hong Kong Hong Kong

ISBN: (纸本)9798350368741

Language-queried target sound extraction (TSE) aims to extract specific sounds from mixtures based on language queries. Traditional fully-supervised training schemes require extensively annotated parallel audio-text data, which are labor-intensive. We introduce a parallel-data-free training scheme, requiring only unlabelled audio clips for TSE model training by utilizing the contrastive language-audio pre-trained model (CLAP). In a vanilla parallel-data-free training stage, target audio is encoded using the pre-trained CLAP audio encoder to form a condition embedding, while during testing, user language queries are encoded by CLAP text encoder as the condition embedding. This vanilla approach assumes perfect alignment between text and audio embeddings, which is unrealistic. Two major challenges arise from training-testing mismatch: the persistent modality gap between text and audio and the risk of overfitting due to the exposure of rich acoustic details in target audio embedding during training. To address this, we propose a retrieval-augmented strategy. Specifically, we create an embedding cache using audio captions generated by a large language model (LLM). During training, target audio embeddings retrieve text embeddings from this cache to use as condition embeddings, ensuring consistent modalities between training and testing and eliminating information leakage. Extensive experiment results show that our retrieval-augmented approach achieves consistent and notable performance improvements over existing state-of-the-art with better generalizability. © 2025 IEEE.

关键词： contrastive language-audio pre-training retrieval-augmented strategy target sound extraction uni-modal training for multi-modal tasks

来源：评论

学校读者我要写书评

暂无评论

Achieving partial nitrification and denitrification coupled with simultaneous partial nitrification, anammox, and denitrification (PND-SNAD) by the inhibition of sulfide to accomplish stabilized nitrogen removal

引用

Environmental Research 2025年 278卷

作者： Bian, Yihao Fu, Kunming Xu, Ruotong Guan, Teng Huo, Aotong Zhang, Ruibao Li, Xueqin Qiu, Fuguo Zhang, Yongji State Key Laboratory of Pollution Control and Resource Reuse College of Environmental Science and Engineering Tongji University Shanghai200092 China Shanghai Institute of Pollution Control and Ecological Security Shanghai200092 China Key Laboratory of Urban Storm Water System and Water Environment Ministry of Education Beijing University of Civil Engineering and Architecture Beijing100044 China

The simultaneous partial nitrification, anammox, and denitrification (SNAD) process is widely applied for treating high-ammonia wastewater, but its application to low-ammonia organic wastewater has been scarcely explored. In this study, a partial nitrification and denitrification coupled with simultaneous partial nitrification, anammox, and denitrification (PND-SNAD) system was established to treat organic wastewater with low ammonia concentration. Experimental results revealed that sulfide at 5 mg/L selectively inhibited nitrite-oxidizing bacteria (NOB) but had little effect on ammonium-oxidizing bacteria (AOB). Finally, NOB was suppressed in PND system by intermittently adding sulfide to the PND system. The PND system provided nitrite and activated sludge enriched with AOB to the SNAD system during stable operation. The SNAD system demonstrated chemical oxygen demand (COD) and nitrogen removal efficiencies of 89.86 % and 86.45 %. Candidatus Brocadia and Nitrosomonas were the main ammonium oxidizing bacteria (AnAOB) and AOB. The contribution of AOB and denitrifying bacteria (DNB) to nitrogen transformation was 67.15 % and 25.33 % in the PND system. In the SNAD system, the contributions of AnAOB, AOB, and DNB were 34.40 %, 33.59 %, and 27.56 %, respectively. Overall, this study provided a new sustainable strategy for treating organic wastewater with low ammonia concentration. © 2025 Elsevier Inc.

关键词： Sulfur compounds

来源：评论

学校读者我要写书评

暂无评论

Moving Target Defense Meets Artificial Intelligence-Driven Network: A Comprehensive Survey

引用

IEEE Internet of Things Journal 2025年第10期12卷 13384-13397页

作者： Zhang, Tao Kong, Fanyu Deng, Dongshang Tang, Xiangyun Wu, Xuangou Xu, Changqiao Zhu, Liehuang Liu, Jiqiang Ai, Bo Han, Zhu Deng, Robert H. Beijing Jiaotong University School of Cyberspace Science and Technology Beijing100044 China Anhui Engineering Research Center for Intelligent Applications and Security of Industrial Internet Anhui243002 China Minzu University of China School of Information Engineering Beijing100081 China Chongqing University College of Computer Science Chongqing400044 China Anhui University of Technology School of Computer Science and Technology Anhui Province Key Laboratory of Digital Twin Technology in Metallurgical Industry Anhui243002 China Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology China Beijing Institute of Technology School of Cyberspace Science and Technology Beijing100081 China Beijing Jiaotong University School of Electronic and Information Engineering Frontiers Science Center for Smart High-speed Railway System Beijing100044 China University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States Singapore Management University Department of Information Systems Singapore Singapore

Based on emerging Artificial Intelligence (AI) tasks, cloud-edge-terminal architecture can provide powerful computing, intelligent interconnection, and real-time response, which can also be regarded as AI-driven network. Unfortunately, multiple network layers in the AI-driven network usually face various types of network threats such as malicious network reconnaissance, side-channel attacks, and Distributed Denial of Service (DDoS). Traditional security solutions respond to network threats after the occurrence of attacks. To solve this problem, the concept of Moving Target Defense (MTD) has been proposed as a proactive defense mechanism that aims to defend against cyber attacks before they occur. In this paper, we firstly provide a thorough analysis of the threats in the cloud-edge-terminal network. Then we conduct a comprehensive survey to discuss the concept, design principles, and main classifications of MTD. Next, we further introduce the development potential in terms of AI-powered MTD on each network layer. Meanwhile, we also explore how MTD improves the security of AI algorithms. Lastly, we describe the existing challenges and research directions of MTD. The aim of this paper is to provide an in-depth understanding for the readers on how to realize the integration between MTD and AI-driven network. © 2014 IEEE.

关键词： Cloud security

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：