检索结果-内蒙古大学图书馆

Learning efficient text-to-image synthesis via interstage cross-sample similarity distillation

Science China(Information Sciences) 2021年第2期64卷 19-30页

作者： Fengling MAO Bingpeng MA Hong CHANG Shiguang SHAN Xilin CHEN School of Information Science and Technology ShanghaiTech University Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing TechnologyChinese Academy of Sciences University of Chinese Academy of Sciences CAS Center for Excellence in Brain Science and Intelligence Technology

For a given text, previous text-to-image synthesis methods commonly utilize a multistage generation model to produce images with high resolution in a coarse-to-fine manner. However, these methods ignore the interaction among stages, and they do not constrain the consistent cross-sample relations of images generated in different stages. These deficiencies result in inefficient generation and discrimination. In this study, we propose an interstage cross-sample similarity distillation model based on a generative adversarial network(GAN) for learning efficient text-to-image synthesis. To strengthen the interaction among stages,we achieve interstage knowledge distillation from the refined stage to the coarse stages with novel interstage cross-sample similarity distillation blocks. To enhance the constraint on the cross-sample relations of the images generated at different stages, we conduct cross-sample similarity distillation among the stages. Extensive experiments on the Oxford-102 and Caltech-UCSD Birds-200-2011(CUB) datasets show that our model generates visually pleasing images and achieves quantitatively comparable performance with state-of-the-art methods.

关键词： generative adversarialnetwork (GAN) text-to-image synthesis knowledge distillation

来源：评论

学校读者我要写书评

暂无评论

QoS Prediction based on the Low-rank Autoregressive Tensor Completion

QoS Prediction based on the Low-rank Autoregressive Tensor C...

引用

2022 International Conference on Networking and Network Applications, NaNA 2022

作者： Xia, Hong Dong, Qingyi Chen, Yanping Zheng, Jiahao Gao, Cong Wang, ZhongMin School of Computer Science and Technology Xi’an University of Posts and Telecommunications Shaanxi Xi’an710121 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Shaanxi Xi’an710121 China Xi'an Key Laboratory of Big Data and Intelligent Computing Shaanxi Xi’an710121 China

ISBN: (数字)9781665461313

ISBN: (纸本)9781665461313

With the rapid development of network services and edge computing, Quality of Service (QoS) has become an important indicator to validate performances of a network. Recommend high-quality services to users based on QoS values. However, the high sparsity of QoS data is because users usually call certain services only at a given time. Missing QoS data is very common in various service recommendation systems. Therefore, it is essential to predict QoS data to accurately recommend high-quality services to users. For the QoS data prediction problem, we build a third-order data tensor 'User-Service-Time' for the time series characteristics of QoS data. And introduce time-series variation as a regularization term into third-order tensor Data prediction. We propose a QoS prediction framework using Low-Rank Autoregressive Tensor Completion (LATC). In particular, constructing a third-order tensor data model can better capture the global consistency of the data structure. Time regularization is introduced to take into account the local correlation of the data. Finally, in order to solve the constrained optimization problem, we use the general Alternating Direction Method of Multipliers (ADMM) to minimize the iterative optimization of variables and autoregressive parameters to obtain the final prediction result. Meanwhile, we conduct extensive research experiments on the real dataset WS-Dream. Experiments show that the QoS data prediction accuracy of our proposed QoS prediction method is higher than that of existing prediction methods under different degrees of data density. © 2022 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Disturbance Estimation of Legged Robots: Predefined Convergence via Dynamic Gains

arXiv

引用

arXiv 2025年

作者： Li, Bolin Cai, Peiyuan Zuo, Gewei Zhu, Lijun Ding, Han School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430072 China Key Laboratory of Imaging Processing and Intelligence Control China State Key Laboratory of Intelligent Manufacturing Equipment and Technology Huazhong University of Science and Technology China

In this study, we address the challenge of disturbance estimation in legged robots by introducing a novel continuous-time online feedback-based disturbance observer that leverages measurable variables. The distinct feature of our observer is the integration of dynamic gains and comparison functions, which guarantees predefined convergence of the disturbance estimation error, including ultimately uniformly bounded, asymptotic, and exponential convergence, among various types. The properties of dynamic gains and the sufficient conditions for comparison functions are detailed to guide engineers in designing desired convergence behaviors. Notably, the observer functions effectively without the need for upper bound information of the disturbance or its derivative, enhancing its engineering applicability. An experimental example corroborates the theoretical advancements achieved. Copyright © 2025, The Authors. All rights reserved.

关键词： Continuous time systems

来源：评论

学校读者我要写书评

暂无评论

Out-of-Distribution Fault Diagnosis of Industrial Cyber-Physical Systems Based on Orthogonal Anchor Clustering With Adaptive Balance

IEEE Transactions on Industrial Cyber-Physical Systems

引用

IEEE Transactions on Industrial Cyber-Physical Systems 2025年 3卷 48-60页

作者： Liu, Ruonan Hu, Puyuan Zhao, Siheng Sun, Zhijian Han, Te Pang, Zhibo Zhang, Weidong Shanghai Jiao Tong University Department of Automation Shanghai200240 China National Key Laboratory of Marine Engine Science and Technology Shanghai201108 China Crossocean of Suzhou Technology Suzhou215121 China Beijing Institute of Technology Center for Energy and Environmental Policy Research School of Management Beijing100081 China ABB Corporate Research Sweden Department of Automation Technology Vasteras722 26 Sweden KTH Royal Institute of Technology Department of Intelligent Systems Stockholm114 28 Sweden Henan University Henan Key Laboratory of Big Data Analysis and Processing School of Computer and Information Engineering Kaifeng475001 China Shanghai Jiaotong University Department of Automation Shanghai200240 China

Given the critical role of rotating machinery in industrial cyber-physical systems (ICPS), ensuring their reliable operation is essential for the stability and safety of ICPS. Deep neural networks have demonstrated competitive results for intelligent fault diagnosis, which are usually trained via the historical data of all fault modes. However, in real engineering, it is usually difficult to collect samples and exhaust all failures during the training stage. As a result, out-of-distribution fault diagnosis (OOD-FD) becomes a more realistic problem that requires the methods to not only accurately diagnose the known faults, but also effectively recognize unknown ones. Therefore, a novel orthogonal anchor clustering with focal attention (FA-OAC) is proposed in this paper for OOD-FD. Firstly, an orthogonal anchor clustering (OAC) algorithm is proposed to fix the class center of each fault mode orthogonally and distinguish the known and unknown faults at the class level. Then, because the identifiability of different fault modes changes a lot in OOD-FD, the focal attention mechanism is applied to dynamically adjust the attention to different fault modes according to the distance loss of OAC, thus addressing the identifiability imbalance problem. To verify the effectiveness of the proposed method, different OOD-FD tasks are designed based on two rotating machinery datasets. The experimental results and comparison with state-of-the-art fault diagnosis methods have demonstrated that the proposed method has improved the OOD-FD performance greatly and therefore provides an effective tool in real engineering. © 2023 IEEE.

关键词： Rotating machinery

来源：评论

学校读者我要写书评

暂无评论

Entity disambiguation method based on Graph Attention Networks 14

Entity disambiguation method based on Graph Attention Networ...

引用

14th International Conference on Measuring technology and Mechatronics Automation, ICMTMA 2022

作者： Qiang, Chengyu Li, Xiaogo Ma, Xianyan Han, Wei Yao, Yi School of Computer Science and Technology Xi'an University of Posts and Telecommunications Shaanxi Xi'an71012 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Shaanxi Xi'an710121 China Xi 'an Key Laboratory of Big Data and Intelligent Computing Shaanxi Xi'an710121 China

ISBN: (纸本)9781665499781

Entity disambiguation based on entity-link is a technique which constructs the mappings between entity reference items appearing in the short text and target entity in knowledge base respectively. In this paper we propose an entity disambiguation method based on Graph Attention Networks for semi-structured knowledge base data. First, a global Knowledge Graph is constructed from the semi-structured knowledge base, and the entity reference items are embedded by Bert pre-trained model meanwhile. Next, Graph Attention Networks which leverages masked self-attention layers is applyed on candidate entity nodes of global Knowledge Graph to fetch a vector of node level. Furtherly, we compute similarity scores rank between the entity reference items and the candidate entity to complete the task of entity disambiguation. The experimental results on CCKS2019 dataset achieve state-of-the-art. © 2022 IEEE

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Data-driven risk assessment and early warning of learning situations 4

Data-driven risk assessment and early warning of learning si...

引用

4th International Conference on Computer Science and Educational Informatization, CSEI 2022

作者： Mi, Chunqiao Deng, Qingyou Zhao, Changhua Huaihua University Hunan Huaihua China Key Laboratory of Intelligent Control Technology for Wuling-Mountain Ecological Agriculture in Hunan Province Hunan Huaihua China Key Laboratory of Wuling-Mountain Health Big Data Intelligent Processing and Application in Hunan Province Universities Hunan Huaihua China

ISBN: (数字)9781839537882

ISBN: (纸本)9781839537882

At present, quality governance has become the internal demand of education reform and high-quality education system construction. First, this study analyzed the current research status and existing problems of early warning education in universities and colleges from the aspects of basic data, evaluation index, assessment method, and tool system application. Second, driven by learning situation big data analysis, this study puts forward a complete method system of risk assessment and early warning of learning situations, which consists of basic data collection and processing, index system construction and quantification, model construction and calculation, result expression and visualization, and a prototype information system was also realized by using modern software engineering and visualization technology. Finally, a specific course was taken as an example, and the application practice of learning situation risk assessment and early warning was carried out. The obtained results are very helpful to solve the problems of lagging early warning time, single evaluation factor, outdated technology and so on in traditional early warning education. It has reference significance for improving students' learning quality, teachers' teaching effect and early warning education management efficiency. © 2022 IET Conference Proceedings. All rights reserved.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning-Based URLLC-Aware Task Offloading in Collaborative Vehicular Networks

引用

China Communications 2021年第7期18卷 134-146页

作者： Chao Pan Zhao Wang Zhenyu Zhou Xincheng Ren Hebei Key Laboratory of Power Internet of Things Technology North China Electric Power UniversityBeijing102206Baoding071003HebeiChina Shaanxi Key Laboratory of Intelligent Processing for Big Energy Data Yanan UniversityYanan 716000China

Collaborative vehicular networks is a key enabler to meet the stringent ultra-reliable and lowlatency communications(URLLC)requirements.A user vehicle(UV)dynamically optimizes task offloading by exploiting its collaborations with edge servers and vehicular fog servers(VFSs).However,the optimization of task offloading in highly dynamic collaborative vehicular networks faces several challenges such as URLLC guaranteeing,incomplete information,and dimensionality *** this paper,we first characterize URLLC in terms of queuing delay bound violation and high-order statistics of excess ***,a Deep Reinforcement lEarning-based URLLCAware task offloading algorithM named DREAM is proposed to maximize the throughput of the UVs while satisfying the URLLC constraints in a besteffort *** with existing task offloading algorithms,DREAM achieves superior performance in throughput,queuing delay,and URLLC.

关键词： collaborative vehicular networks task of-floading URLLC awareness deep Q-learning

来源：评论

学校读者我要写书评

暂无评论

In situ converting the native passivation layer into a fast ion transport interphase to boost the stability of zinc anodes

引用

Green Energy and Environment 2025年

作者： Xie, Zi-Long Zhu, Yunhai Du, Jia-Yi Yang, Dong-Yue Chen, Hao Wang, Zhi Huang, Gang Zhang, Xin-Bo State Key Laboratory of Rare Earth Resource Utilization Changchun Institute of Applied Chemistry Chinese Academy of Sciences Changchun130022 China School of Applied Chemistry and Engineering University of Science and Technology of China Hefei230026 China State Key Laboratory of New Textile Materials and Advanced Processing Technologies Wuhan Textile University Wuhan430200 China

Aqueous zinc batteries offer significant potential for large-scale energy storage, wearable devices, and medium-to low-speed transportation due to their safety, affordability, and environmental friendliness. However, the uneven zinc deposition at the anode side caused by localized reaction activity from the passivation layer presents challenges that significantly impact the battery's stability and lifespan. In this study, we have proposed an expandable and maneuverable gel sustained-release (GSR) treatment to polish the Zn metal, which in situ converts its native passivation layer into a composite interphase layer with nanocrystal zinc phosphate and flexible polyvinyl alcohol. Such a thin and uniform interface contributes to fast and homogeneous Zn ion transport and improved anti-corrosion ability, enabling uniform zinc deposition without dendrite growth and thereby improving the battery performance with high-rate ability and long cycle life. This GSR treatment method, characterized by its simplicity, low cost, and universality, facilitates the widespread application of aqueous zinc batteries. © 2025 Institute of Process Engineering, Chinese Academy of Sciences

关键词： Passivation

来源：评论

学校读者我要写书评

暂无评论

Hot-Start Transfer Learning Combined with Approximate Distillation for Mongolian-Chinese Neural Machine Translation 1

引用

18th China Conference on Machine Translation, CCMT 2022

作者： Wang, Pengcong Hou, Hongxu Sun, Shuo Wu, Nier Jian, Weichen Yang, Zongheng Wang, Yisong College of Computer Science Inner Mongolia University Hohhot China National and Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Hohhot China Inner Mongolia Key Laboratory of Mongolian Information Processing Technology Hohhot China

ISBN: (数字)9789811979606

ISBN: (纸本)9789811979590

When parallel training data is scarce, it will affect neural machine translation. For low-resource neural machine translation (NMT), transfer learning is very important, and the use of pre-training model can also alleviate the shortage of data. However, the good performance of common cold-start transfer learning methods is limited to the cognate language realized by sharing its vocabulary. Moreover, when using the pre-training model, the combination of general fine tuning methods and NMT will lead to a serious problem of knowledge forgetting. Both methods have some defects, so this paper optimizes the above two problems, and applies a new training framework suitable for low correlation language to Mongolian-Chinese neural machine translation. Our framework includes two technologies: a) word alignment method under hot-start, which alleviates the problem of word mismatch between the transferred subject and object in transfer learning. b) approximate distillation,not only retains the pre-trained knowledge, but also solves the forgetting problem, so that the encoder of NMT has stronger language representation ability. The results show that BLEU is increased by 3.2, which is better than ordinary transfer learning and multilingual translation system. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Body-Comfort Cellulose Acetate-Based textiles-Triboelectric Nanogenerators with Radiation Cooling and Moisture Permeability

SSRN

引用

SSRN 2024年

作者： Xu, Mei Chen, Zhicheng Hu, Ziyao Zhou, Cheng Fu, Xinming Song, Yiheng Wen, Xianjie Wang, Jinfeng Yin, Xianze College of Materials Science and Engineering National Local Joint Laboratory for Advanced Textile Processing and Clean Production Wuhan Textile University Wuhan430200 China Department of Anesthesiology The Second People’s Hospital of Foshan City Guangdong Province Foshan528000 China State Key Laboratory of New Textile Materials & Advanced Processing Technology Wuhan Textile University 430200 China

Wearable textile-triboelectric nanogenerators (t-TENGs) faced impediments in terms of the inadequate heat dissipation and moisture permeability performance. Specifically, actively heat-dissipating TENG devices exhibited intricacies, while passively heat-dissipating t-TENGs were considered unsatisfactory in sustaining optimal body temperature ranges for comfort. Herein, solvent-free titanium dioxide nanofluids (TiO2 nfs) were prepared to in-situ enhance the radiation cooling performance of electrospun TiO2 nfs@cellulose acetate (TiO2 nfs@CA) t-TENGs by grafting flexible chains on the TiO2 surface. TiO2 in the core layer of TiO2 nfs enhanced the infrared emission, hydrophilicity, and dielectric properties of TiO2 nfs@CA t-TENGs. Moreover, TiO2 nfs demonstrated a phase transition by absorbing energy within the physiological temperature ranges of the human body. TiO2 nfs enhanced the infrared emission, hydrophilicity, and dielectric properties of TiO2 nfs@CA t-TENGs by grafting flexible long chains ion on the TiO2 surface. The large-scale fabricated TiO2 nfs@CA membranes showcased remarkable radiation cooling performance (dropped 4 °C ~ 8 °C under 45 °C environments) in authentic and humid environments (like indoors, house and car). And TiO2 nfs@CA endowed a substantial enthalpy change within body temperature ranges, manifesting an exceptionally comfortable skin temperature (34 °C ~ 38 °C) even under scorching sunlight. Besides, TiO2 nfs@CA t-TENGs accurately monitored and pridicted foot movements in humid and enclosed environments by support vector machine (SVM). This made it promising as self-powered wearable devices. TiO2 nfs@CA t-TENGs provided a novel strategy for large scale fabricating of t-TENGs with comfort. © 2024, The Authors. All rights reserved.

关键词： textiles

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：