检索结果-内蒙古大学图书馆

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Tao Wu Yuben Qu Chunsheng Liu Yuqian Jing Feiyu Wu Haipeng Dai Chao Dong Jiannong Cao National University of Defense Technology China Key Laboratory of Dynamic Cognitive System of Electromagnetic Spectrum Space Nanjing University of Aeronautics and Astronautics China State Key Laboratory for Novel Software Technology Nanjing University China Department of Computing The Hong Kong Polytechnic University Hong Kong

Federated learning (FL) has been proposed as a promising distributed learning paradigm to realize edge artificial intelligence (AI) without revealing the raw data. Nevertheless, it would incur inevitable costs in terms of training latency and energy consumption, due to periodical communication between user equipments (UEs) and the geographically remote central parameter server. Thus motivated, we study the joint edge aggregation and association problem to minimize the total cost, where the model aggregation over multiple cells just happens at the network edge. After proving its hardness with complex coupled variables, we transform it into a set function optimization problem and prove the objective function is neither submodular nor supermodular, which further complicates the problem. To tackle this difficulty, we first split it into multiple edge association subproblems, where the optimal solution to the computation resource allocation can be efficiently obtained in the closed form. We then construct a substitute function with the supermodularity and provable upper bound. On this basis, we reformulate an equivalent set function minimization problem under a matroid base constraint. We then propose an approximation algorithm to the original problem based on the two-stage search strategy with theoretical performance guarantee. Both extensive simulations and field experiments are conducted to validate the effectiveness of our proposed solution.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis

arXiv

引用

arXiv 2024年

作者： Deng, Kaijun Zheng, Dezhi Xie, Jindong Wang, Jinbao Xie, Weicheng Shen, Linlin Song, Siyang Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China Department of Computer Science University of Exeter United Kingdom

Accurately synthesizing talking face videos and capturing fine facial features for individuals with long hair presents a significant challenge. To tackle these challenges in existing methods, we propose a decomposed per-embedding Gaussian fields (DEGSTalk), a 3D Gaussian Splatting (3DGS)-based talking face synthesis method for generating realistic talking faces with long hairs. Our DEGSTalk employs Deformable Pre-Embedding Gaussian Fields, which dynamically adjust pre-embedding Gaussian primitives using implicit expression coefficients. This enables precise capture of dynamic facial regions and subtle expressions. Additionally, we propose a Dynamic Hair-Preserving Portrait Rendering technique to enhance the realism of long hair motions in the synthesized videos. Results show that DEGSTalk achieves improved realism and synthesis quality compared to existing approaches, particularly in handling complex facial dynamics and hair preservation. Our code will be publicly available at https://***/CVI-SZU/DEGSTalk. Copyright © 2024, The Authors. All rights reserved.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Contrastive Learning Based Human Activity Recognition Using Body Sensors 9

Contrastive Learning Based Human Activity Recognition Using ...

引用

9th International Conference on Big Data Computing and Communications, BigCom 2023

作者： Xie, Chuanshi Zhou, Yu Yu, Dandan Sun, Shilong Zhang, Xiao Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China The First Affiliated Hospital of Dalian Medical University Information Center Dalian China Harbin Institute of Technology School of Mechanical Engineering and Automation Shenzhen518055 China South-Central Minzu University Department of Computer Science China South-Central Minzu University Key Laboratory of Cyber-Physical Fusion Intelligent Computing State Ethnic Affairs Commission Wuhan430074 China

ISBN: (纸本)9798350331240

Pervasive sensing and wearable sensor techniques have been increasingly employed to monitor and recognize human activities through body sensors in areas of smart healthcare and manufacturing. However, conventional machine learning or deep learning based human activity recognition (HAR) requires a large amount of labeled data, which is cost-expensive in real-world scenarios. To tackle this issue, we propose a contrastive learning framework for HAR (CL-HAR), which utilizes the generated unlabeled data as the input and explores the supervised features of the unlabeled data under the principle of self-supervised learning. A simple yet effective backbone network as a feature extractor for subsequent activity recognition is proposed. By using a small portion of the labeled samples as the training set which is fed into our learned feature extractor, we build a classifier and use the rest of the data to verify the feasibility and effectiveness of our CL method. Extensive experiments on three benchamark datasets and one real-world dataset demonstrate that CL-HAR can achieve better classification accuracy than compared supervised and semi-supervised methods with less labelled samples, which is of practical use. © 2023 IEEE.

关键词： Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

Reply with Sticker: New Dataset and Model for Sticker Retrieval

arXiv

引用

arXiv 2024年

作者： Liang, Bin Wang, Bingbing Bai, Zhixin Lang, Qiwei Sun, Mingwei Hou, Kaiheng Zhou, Lanjun Xu, Ruifeng Wong, Kam-Fai Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong Hong Kong Shenzhen China Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies Shenzhen China School of Computer Science and Technology Harbin Institute of Technology Harbin China School of Computer Science and Artificial Intelligence Foshan University Foshan China

Using stickers in online chatting is very prevalent on social media platforms, where the stickers used in the conversation can express someone’s intention/emotion/attitude in a vivid, tactful, and intuitive way. Existing sticker retrieval research typically retrieves stickers based on context and the current utterance delivered by the user. That is, the stickers serve as a supplement to the current utterance. However, in the real-world scenario, using stickers to express what we want to say rather than as a supplement to our words only is also important. Therefore, in this paper, we create a new dataset for sticker retrieval in conversation, called StickerInt, where stickers are used to reply to previous conversations or supplement our words1. Based on the created dataset, we present a simple yet effective framework for sticker retrieval in conversation based on the learning of intention and the cross-modal relationships between conversation context and stickers, coined as Int-RA. Specifically, we first devise a knowledge-enhanced intention predictor to introduce the intention information into the conversation representations. Subsequently, a relation-aware sticker selector is devised to retrieve the response sticker via cross-modal relationships. Extensive experiments on the created dataset show that the proposed model achieves state-of-the-art performance in sticker retrieval2 © 2024, CC BY-NC-ND.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bctm:A Topic Modeling Method Based on External Information

SSRN

引用

SSRN 2022年

作者： Liu, Gang Wan, TaiYing Gao, JingQi Buntine, Wary College of Computer Science and Technology Harbin Engineering University Harbin150001 China State Key Laboratory for Novel Software Technology Nanjing University Nanjing210000 China Faculty of Information Technology Monash University Melbourne3800 Australia

Topic models are often used as intermediate algorithms for text mining and semantic analysis in natural language processing, and have a wide range of functions. However, most of the existing improvements to the topic model use word embedding to improve the accuracy of text modeling, but ignore the external information in the text. Aiming at the above problems, this paper proposes a topic model BCTM (Bi-Concept Topic Model) using the word feature information and concept information. Based on the BTM topic model, BCTM introduces word feature information through word vector technology and concept information based on ConceptNet to optimize topic modeling. The construction method of Bi-Concept pair is proposed. Based on ConceptNet semantic network, and the content of text is enriched with concept information. A more accurate topic distribution is obtained through the improved topic model, at the same time, due to the rich feature information, the model is also superior to the baseline model in short text modeling. The experiments prove that the bilingual topic model proposed in this paper has a good performance in modeling accuracy. © 2022, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

A New Sequential Image Prediction Method Based on LSTM and DCGAN

引用

computers, Materials & Continua 2020年第7期64卷 217-231页

作者： Wei Fang Feihong Zhang Yewen Ding Jack Sheng School of Computer&Software Jiangsu Engineering Center of Network MonitoringNanjing University of Information Science&TechnologyNanjing210044China State Key Laboratory for Novel Software Technology Nanjing UniversityNanjing210023China Department of Economics FinanceInsurance and Risk Management University of Central ArkansasConway72035USA

Image recognition technology is an important field of artificial *** with the development of machine learning technology in recent years,it has great researches value and commercial *** a matter of fact,a single recognition function can no longer meet people’s needs,and accurate image prediction is the trend that people *** paper is based on Long Short-Term Memory(LSTM)and Deep Convolution Generative Adversarial Networks(DCGAN),studies and implements a prediction model by using radar image *** adopt a stack cascading strategy in designing network connection which can control of parameter convergence *** new method enables effective learning of image features and makes predictive models to have greater generalization *** demonstrate that our network model is more robust and efficient in terms of timing prediction than 3DCNN and traditional *** sequential image prediction model architecture proposed in this paper is theoretically applicable to all sequential images.

关键词： Image prediction LSTM DCGAN

来源：评论

学校读者我要写书评

暂无评论

GeneDroid Fuzz: An Android Intent Fuzzing Method Based on Gene Mutation

GeneDroid Fuzz: An Android Intent Fuzzing Method Based on Ge...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Runfeng Lu Yuzhu Sun Haofeng Sun Xiao Fu Bin Luo Xiaojiang Du Jin Shi Nadjib Aitsaadi Mohsen Guizani State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Department of Electrical and Computer Engineering Stevens Institute of Technology Hoboken NJ USA School of Information Management Nanjing University Nanjing China DAVID UVSQ Université Paris-Saclay France Machine Learning Department Mohamed Bin Zayed University of Artificial Intelligence Abu Dhabi UAE

ISBN: (数字)9798350351255

ISBN: (纸本)9798350351262

With the rapid expansion of mobile internet usage, the prevalence of the Android operating system on smartphones is steadily growing. However, improper utilization of the Intent mechanism within Android applications can result in security vulnerabilities. Presently, the majority of Android security testing methods, which rely heavily on fuzzing, are predominantly focused on UI interactions, lacking sufficient testing capabilities for Intents. The motivation of this paper is to find a more effective testing method to improve the security detection capabilities of Intents. This paper introduces an Intent fuzzing method based on genetic mutation principles. Initially, we establish an Intent seed library using a text classification model, followed by employing Jaccard distance and minimum edit distance to refine high-quality seeds. Subsequently, we augment the seeds through extensive mutation using genetic algorithms, generating numerous test cases that exhibit structural similarity but contain varied content. During testing, we compare the state before and after Intent testing using image similarity to detect anomalies. Experimental results demonstrate that this method effectively enhances test coverage and identifies potential issues in edge cases. This approach offers an efficient means of conducting Intent security testing and enhances Android app robustness and security.

关键词： Operating systems Image edge detection Genetic mutations Text categorization Fuzzing Libraries Robustness Security Smart phones Testing

来源：评论

学校读者我要写书评

暂无评论

Photonic integrated spiking neuron chip based on a self-pulsating DFB laser with a saturable absorber

引用

Photonics Research 2023年第8期11卷 1382-1389页

作者： YUECHUN SHI SHUIYING XIANG XINGXING GUO YAHUI ZHANG HONGJI WANG DIANZHUANG ZHENG YUNA ZHANG YANAN HAN YONG ZHAO XIAOJUN ZHU XIANGFEI CHEN XUN LI YUE HAO Yongjiang Laboratory Ningbo 315202China State Key Laboratory of Integrated Service Networks State Key Discipline Laboratory of Wide Bandgap Semiconductor TechnologyXidian UniversityXi’an 710071China Key Laboratory of Intelligent Optical Sensing and Manipulation Ministry of EducationNational Laboratory of Solid State MicrostructuresCollege of Engineering and Applied SciencesInstitute of Optical Communication EngineeringNanjing UniversityNanjing 210023China School of Science Jiangnan UniversityWuxi 214122China School of Information Science and Technology Nantong UniversityNantong 226019China Department of Electrical and Computer Engineering McMaster UniversityHamiltonOantario L8S 4K1Canada

We proposed and experimentally demonstrated a simple and novel photonic spiking neuron based on a distributed feedback(DFB)laser chip with an intracavity saturable absorber(SA).The DFB laser with an intracavity SA(DFBSA)contains a gain region and an SA *** gain region is designed and fabricated by the asymmetric equivalentπ-phase shift based on the reconstruction-equivalent-chirp *** properly injected current in the gain region and reversely biased voltage in the SA region,periodic self-pulsation was experimentally observed due to the Q-switching *** self-pulsation frequency increases with the increase of the bias current and is within the range of several *** the bias current is below the self-pulsation threshold,neuronlike spiking responses appear when external optical stimulus pulses are *** results show that the spike threshold,temporal integration,and refractory period can all be observed in the fabricated DFB-SA *** numerically verify the experimental findings,a time-dependent coupled-wave equation model was developed,which described the physics processes inside the gain and SA *** numerical results agree well with the experimental *** further experimentally demonstrated that the weighted sum output can readily be encoded into the self-pulsation frequency of the DFB-SA *** also benchmarked the handwritten digit classification task with a simple single-layer fully connected neural *** using the experimentally measured dependence of the self-pulsation frequency on the bias current in the gain region as an activation function,we can achieve a recognition accuracy of 92.2%,which bridges the gap between the continuous valued artificial neural networks and spike-based neuromorphic *** the best of our knowledge,this is the first experimental demonstration of a photonic integrated spiking neuron based on a DFB-SA,which shows great potential to realizing large-scale mult

关键词： technique laser saturable

来源：评论

学校读者我要写书评

暂无评论

Exact Algorithm for Batch Scheduling with Many-to-Many Job-Tool Matching and Job Release Time Constraints

引用

IEEE Transactions on Automation science and Engineering 2025年 22卷 16499-16511页

作者： Li, Shengchao Liu, Shixin Zhao, Ziyan Zhou, Mengchu Northeastern University State Key Laboratory of Synthetical Automation for Process Industries College of Information Science and Engineering Shenyang 110819 China Northeastern University at Qinhuangdao Hebei Key Laboratory of Industrial Software for Advanced Planning and Scheduling of Complex Industrial Processes School of Control Engineering Qinhuangdao 066004 China New Jersey Institute of Technology Department of Electrical and Computer Engineering Newark 07102 NJ United States

Job-dependent tool switching is necessary in many batch processing systems (BPSs). Heterogeneous tool demand and extra time consumption for tool switch bring great challenge for high-performance production scheduling in BPSs. In this study, we present a novel batch scheduling problem derived from a satellite vibration test system. Different from basic scheduling problems in BPSs with tool switching, it has complications caused by many-to-many task-tool matching and job release time constraints. Specifically, each job has predetermined candidate tools. One of them should be selected and equipped to process a given job. Unlike sequence-dependent setup time that is only related to two adjacent jobs, tool switching time is additionally dependent on the tools selected by both jobs from their respective candidate tools. Both job sequence and tool selections need to be determined to minimize makespan. Mixed-integer linear programming (MILP) and constraint programming (CP) models are developed for formulating the problem. We prove that the problem is NP hard. To obtain exact solutions, we propose a novel branch-and-bound algorithm (B&B) based on the analysis and extraction of problem properties. It integrates a domain reduction mechanism, branching strategies, and dominance rules. Among them, the domain reduction mechanism reduces the number of jobs to be scheduled;the branching strategies accelerate solving speed;and the dominance rules save the memory consumption. Ablation studies and key influencing factor experiments are performed. The results show that the proposed B&B can optimally solve much larger instances than state-of-the-art methods (including some heuristics). It can optimally solve industrial-size problems in a short time, implying that it can well satisfy the performance demand of a satellite vibration test system and thus advancing the filed of optimal scheduling for BPSs. © 2004-2012 IEEE.

关键词： Batch scheduling branch-and-bound algorithm heterogenerous tool demand mixed-integer linear programming satellite vibration test system

来源：评论

学校读者我要写书评

暂无评论

UNIFIED POLICY OPTIMIZATION FOR CONTINUOUS-ACTION REINFORCEMENT LEARNING IN NON-STATIONARY TASKS AND GAMES

arXiv

引用

arXiv 2022年

作者： Qin, Rong-Jun Luo, Fan-Ming Qian, Hong Yu, Yang National Key Laboratory for Novel Software Technology Nanjing University China Polixir.ai United States School of Computer Science and Technology East China Normal University China

This paper addresses policy learning in non-stationary environments and games with continuous actions. Rather than the classical reward maximization mechanism, inspired by the ideas of follow-the-regularized-leader (FTRL) and mirror descent (MD) update, we propose a no-regret style reinforcement learning algorithm PORL for continuous action tasks. We prove that PORL has a last-iterate convergence guarantee, which is important for adversarial and cooperative games. Empirical studies show that, in stationary environments such as MuJoCo locomotion controlling tasks, PORL performs equally well as, if not better than, the soft actor-critic (SAC) algorithm;in non-stationary environments including dynamical environments, adversarial training, and competitive games, PORL is superior to SAC in both a better final policy performance and a more stable training process. © 2022, CC BY.

关键词： Reinforcement learning

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：