检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Yuan, Zhenlong Yang, Zhidong Cai, Yujun Wu, Kuangxin Liu, Mufan Zhang, Dapeng Jiang, Hao Li, Zhaoxin Wang, Zhaoqi The Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Australia The Information Technology Department Hunan Police Academy Changsha410100 China Cooperative MediaNet Innovation Center Shanghai Jiao Tong University Shanghai200240 China DSLAB School of Information Science & Engineering Lanzhou University 730000 China Agricultural Information Institute Chinese Academy of Agricultural Sciences Key Laboratory of Agricultural Big Data Ministry of Agriculture and Rural Affairs 100081 China

Recently, patch-deformation methods have exhibited significant effectiveness in multi-view stereo owing to the deformable and expandable patches in reconstructing textureless areas. However, such methods primarily emphasize broadening the receptive field in textureless areas, while neglecting deformation instability caused by easily overlooked edge-skipping, potentially leading to matching distortions. To address this, we propose SED-MVS, which adopts panoptic segmentation and multi-trajectory diffusion strategy for segmentation-driven and edge-aligned patch deformation. Specifically, to prevent unanticipated edge-skipping, we first employ SAM2 for panoptic segmentation as depth-edge guidance to guide patch deformation, followed by multi-trajectory diffusion strategy to ensure patches are comprehensively aligned with depth edges. Moreover, to avoid potential inaccuracy of random initialization, we combine both sparse points from LoFTR and monocular depth map from DepthAnything V2 to restore reliable and realistic depth map for initialization and supervised guidance. Finally, we integrate segmentation image with monocular depth map to exploit inter-instance occlusion relationship, then further regard them as occlusion map to implement two distinct edge constraint, thereby facilitating occlusion-aware patch deformation. Extensive results on ETH3D, Tanks & Temples, BlendedMVS and Strecha datasets validate the state-of-the-art performance and robust generalization capability of our proposed method. Copyright © 2025, The Authors. All rights reserved.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

Federated Graph Learning via Constructing and Sharing Feature Spaces for Cross-Domain IoT

引用

IEEE Internet of Things Journal 2025年

作者： Chen, Jiale Zhuo, Shengda He, Jinchun Qiu, Wangjie Zhang, Qinnan Xiong, Zehui Zheng, Zhiming Tang, Yin Chen, Min Wang, Changdong Huang, Shuqiang Jinan University College of Cyber Security Guangzhou China Beihang University Institute of Artificial Intelligence Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing Beijing100191 China Zhongguancun Laboratory Beijing China Singapore University of Technology and Design Information Systems Technology and Design 487372 Singapore Jinan University School of Management Guangzhou China South China University of Technology School of Computer Science and Engineering Guangzhou China Sun Yat-sen University School of Computer Guangzhou China Jinan University College of Cyber Security of Jinan University China Guangdong Key Laboratory of Data Security and Privacy Preserving Guangzhou China

The Internet of Things (IoT) collects large volumes of diverse data, with graph data as a critical component, and extensively utilizes Federated Graph Learning (FGL) to process this data while preserving data security. However, the graph data collected by different IoT institutions are relatively independent due to various factors (e.g., data collection methods, geographical locations), and data access is restricted to local environments due to privacy constraints, IoT institutions typically possess heterogeneous feature spaces. Aggregating under these conditions could potentially contaminate local graph representations. Unfortunately, most existing FGL methods tend to overlook this issue. To address this challenge, we propose Federated Graph Learning via Constructing and Sharing Features (FedCSF), a novel FGL framework designed to build a globally consistent feature space and share it among IoT institutions. To construct and extract the feature space, we employ an uniform feature initialization across IoT institutions and design an encoder to extract both global and local feature relationships, thereby facilitating effective collaboration across data from different IoT institutions. Furthermore, we introduce an independent adaptive aggregation strategy to eliminate the integration of harmful knowledge, ensuring that the contributions from each IoT institution are effectively integrated into the global model. We theoretically analyze the convergence of FedCSF. To validate the effectiveness of FedCSF, we conducted extensive experiments under various settings (i.e., cross-datasets, and cross-domains), demonstrating its significant advantages of FedCSF in terms of performance, convergence speed, and practical adaptability © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Facial expression recognition via weighted group sparsity

引用

Frontiers of Computer Science 2017年第2期11卷 266-275页

作者： Hao ZHENG Xin GENG Key Laboratory of Trusted Cloud Computing and Big Data Analysis School of Information Engineering Nanjing Xiaozhuang University Nanjing 211171 China School of Computer Science and Engineering Southeast University Nanjing 211189 China

Considering the distinctiveness of different group features in the sparse representation, a novel joint multi- task and weighted group sparsity （JMT-WGS） method is pro- posed. By weighting popular group sparsity, not only the rep- resentation coefficients from the same class over their asso- ciate dictionaries may share some similarity, but also the rep- resentation coefficients from different classes have enough di- versity. The proposed method is cast into a multi-task frame- work with two-stage iteration. In the first stage, representa- tion coefficient can be optimized by accelerated proximal gra- dient method when the weights are fixed. In the second stage, the weights are computed via the prior information about their entropy. The experimental results on three facial expres- sion databases show that the proposed algorithm outperforms other state-of-the-art algorithms and demonstrate the promis- ing performance of the proposed algorithm.

关键词： facial expression recognition multi-task learning group sparsity

来源：评论

学校读者我要写书评

暂无评论

Linearized Proximal Alternating Direction Method of Multipliers for Parallel Magnetic Resonance Imaging

引用

IEEE/CAA Journal of Automatica Sinica 2017年第4期4卷 763-769页

作者： Benxin Zhang Zhibin Zhu School of Electronic Engineering and Automation and Guangxi Key Laboratory of Automatic Detecting Technology and Instruments Guilin University of Electronic Technology School of Mathematics and Computing Science and Guangxi Colleges and Universities Key Laboratory of Data Analysis and Computation Guilin University of Electronic Technology

In this study, we propose a linearized proximal alternating direction method with variable stepsize for solving total variation image reconstruction problems. Our method uses a linearized technique and the proximal function such that the closed form solutions of the subproblem can be easily *** the subproblem, we apply a variable stepsize, that is like Barzilai-Borwein stepsize, to accelerate the algorithm. Numerical results with parallel magnetic resonance imaging demonstrate the efficiency of the proposed algorithm.

关键词： Alternating direction method Barzilai-Borwein stepsize parallel magnetic resonance imaging total variation image reconstruction

来源：评论

学校读者我要写书评

暂无评论

PreZ-DGGAN: A Drug Graph GAN Based on Pre-Learning of Implicit Variables 2nd

PreZ-DGGAN: A Drug Graph GAN Based on Pre-Learning of Implic...

引用

2nd International Conference on Applied Intelligence, ICAI 2024

作者： Liu, Yixin Fan, Yueqin Li, Zhipeng Zhang, Qinhu Big Data and Intelligent Computing Research Center Guangxi Academy of Science Nanning530007 China School of Mechanical Engineering Guangxi University Nanning530004 China Ningbo Institute of Digital Twin Eastern Institute of Technology Ningbo315201 China Institute for Regenerative Medicine Medical Innovation Center and State Key Laboratory of Cardiology School of Medicine Shanghai East Hospital Tongji University Shanghai200123 China College of Advanced Agricultural Sciences Zhejiang Agriculture and Forestry University Hangzhou311300 China

ISBN: (纸本)9789819619061

In the field of drug discovery and development, deep learning techniques have become a powerful tool to accelerate the discovery and development of new drugs. In the design and optimization of lead molecules, generative adversarial network and graph neural network are one of the prime techniques for accelerating research and development, because the former is based on the idea of two-player game to learn drug features to generate effective molecules, while the unstructured inputs of the latter are well-suited for the analysis of molecular data. Therefore, this study develops a new graph generative adversarial model, called PreZ-DGGAN, by inserting the graph neural network layer into the generative adversarial network. Within PreZ-DGGAN, the latent variable input of the generator is pre-learned by an improved graph variational autoencoder, which effectively avoids the mode collapse of the generative adversarial network, whereas the hidden layer of the discriminator is graph neural network layer, which is able to better learn the real molecules and judge the generated molecules as true or false. Experiments on two molecule datasets show that the molecules generated by PreZ-DGGAN have higher validity (100% on average) and uniqueness (91.5% on average), and the generated molecules are more diverse in structure. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Product-oriented review summarization and scoring

引用

Frontiers of Computer Science 2015年第2期9卷 210-223页

作者： Rong ZHANG Wenzhe YU Chaofeng SHA Xiaofeng HE Aoying ZHOU Institute of Data Science and Engineering Shanghai Key Laboratory of Trustworthy Computing East China Normal University Shanghai 200062 China School of Computer Science Fudan University Shanghai 200433 China

Currently, mere are many onune review weo sites where consumers can freely write comments about different kinds of products and services. These comments are quite useful for other potential consumers. However, the number of online comments is often large and the number continues to grow as more and more consumers contribute. In addition, one comment may mention more than one product and con- tain opinions about different products, mentioning something good and something bad. However, they share only a single overall score, Therefore, it is not easy to know the quality of an individual product from these comments. This paper presents a novel approach to generate review summaries including scores and description snippets with re- spect to each individual product. From the large number of comments, we first extract the context （snippet） that includes a description of the products and choose those snippets that express consumer opinions on them. We then propose several methods to predict the rating （from 1 to 5 stars） of the snip- pets. Finally, we derive a generic framework for generating summaries from the snippets. We design a new snippet selec- tion algorithm to ensure that the returned results preserve the opinion-aspect statistical properties and attribute-aspect cov- erage based on a standard seat allocation algorithm. Through experiments we demonstrate empirically that our methods are effective. We also quantitatively evaluate each step of our ap- proach.

关键词： online transaction diversification review sum-marization review scoring

来源：评论

学校读者我要写书评

暂无评论

Spiking Neural Networks for Temporal Processing: Status Quo and Future Prospects

arXiv

引用

arXiv 2025年

作者： Ma, Chenxiang Chen, Xinyi Li, Yanchen Yang, Qu Wu, Yujie Li, Guoqi Pan, Gang Tang, Huajin Tan, Kay Chen Wu, Jibin Department of Data Science and Artificial Intelligence The Hong Kong Polytechnic University Hong Kong Department of Computing The Hong Kong Polytechnic University Hong Kong Department of Electrical and Computer Engineering National University of Singapore 119077 Singapore Institute of Automation Chinese Academy of Sciences Beijing100045 China State Key Laboratory of Brain-Machine Intelligence College of Computer Science and Technology MOE Frontier Science Center for Brain Science and Brain-Machine Integration Zhejiang University Hangzhou310027 China

Temporal processing is fundamental for both biological and artificial intelligence systems, as it enables the comprehension of dynamic environments and facilitates timely responses. Spiking Neural Networks (SNNs) excel in handling such data with high efficiency, owing to their rich neuronal dynamics and sparse activity patterns. Given the recent surge in the development of SNNs, there is an urgent need for a comprehensive evaluation of their temporal processing capabilities. In this paper, we first conduct an in-depth assessment of commonly used neuromorphic benchmarks, revealing critical limitations in their ability to evaluate the temporal processing capabilities of SNNs. To bridge this gap, we further introduce a benchmark suite consisting of three temporal processing tasks characterized by rich temporal dynamics across multiple timescales. Utilizing this benchmark suite, we perform a thorough evaluation of recently introduced SNN approaches to elucidate the current status of SNNs in temporal processing. Our findings indicate significant advancements in recently developed spiking neuron models and neural architectures regarding their temporal processing capabilities, while also highlighting a performance gap in handling long-range dependencies when compared to state-of-the-art non-spiking models. Finally, we discuss the key challenges and outline potential avenues for future research. Copyright © 2025, The Authors. All rights reserved.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Modeling the Correlations of Relations for Knowledge Graph Embedding

引用

Journal of Computer Science & Technology 2018年第2期33卷 323-334页

作者： Ji-Zhao Zhu Yan-Tao Jia Jun Xu Jian-Zhong Qiao Xue-Qi Cheng College of Computer Science and Engineering Northeastern University Shenyang 110169 China Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing 110190 China

Knowledge graph embedding, which maps the entities and relations into low-dimensional vector spaces, has demonstrated its effectiveness in many tasks such as link prediction and relation extraction. Typical methods include TransE, TransH, and TransR. All these methods map different relations into the vector space separately and the intrinsic correlations of these relations are ignored. It is obvious that there exist some correlations among relations because different relations may connect to a common entity. For example, the triples （Steve Jobs, PlaceOfBrith, California） and （Apple Inc., Location, California） share the same entity California as their tail entity. We analyze the embedded relation matrices learned by TransE/TransH/TransR, and find that the correlations of relations do exist and they are showed as low-rank structure over the embedded relation matrix. It is natural to ask whether we can leverage these correlations to learn better embeddings for the entities and relations in a knowledge graph. In this paper, we propose to learn the embedded relation matrix by decomposing it as a product of two low-dimensional matrices, for characterizing the low-rank structure. The proposed method, called TransCoRe （Translation-Based Method via Modeling the Correlations of Relations）, learns the embeddings of entities and relations with translation-based framework. Experimental results based on the benchmark datasets of WordNet and Freebase demonstrate that our method outperforms the typical baselines on link prediction and triple classification tasks.

关键词： knowledge graph embedding low-rank matrix decomposition

来源：评论

学校读者我要写书评

暂无评论

DRLO: Optimizing edge server placement in dynamic MEC scenarios using deep reinforcement learning

引用

Computer Networks 2025年 268卷

作者： Yingya Guo Cen Chen College of Computer and Data Science Fuzhou University PR China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University PR China Engineering Research Center of Big Data Intelligence Ministry of Education Fujian PR China

As an emerging computing paradigm, Mobile Edge computing (MEC) significantly enhances user experience and alleviates network congestion by strategically deploying edge servers in close proximity to mobile users. However, the effectiveness of MEC hinges on the precise placement of these edge servers, a critical factor in determining the Quality of Experience (QoE) for mobile users. While existing studies predominantly focus on optimizing edge server placement in static scenarios, they often fall short when faced with user mobility, resulting in a degradation of QoE. To address this challenge, we propose an adaptive edge server placement approach that leverages Deep Reinforcement Learning (DRL) to select the base stations for placing edge servers in a dynamic MEC environment. Our objective is to minimize access delay by optimizing edge server placement for adapting to dynamic environment. To tackle the vast action space associated with edge server placement, we introduce a novel activation function in the actor neural network for efficient exploration. Furthermore, to enhance the adaptability of the derived edge server placement strategy, we meticulously design a new reward function, which takes into account the minimization of total access delay within dynamic MEC scenarios. Finally, to validate the effectiveness of our proposed method, extensive experiments were conducted using the Shanghai Telecom dataset. The results demonstrate that our approach outperforms baseline methods in minimizing access delay for users in dynamic MEC scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep LSTM Transfer Learning for Personalized ECG Anomaly Detection on Wearable Devices 5th

Deep LSTM Transfer Learning for Personalized ECG Anomaly Det...

引用

5th International Conference on Cognitive Systems and Signal Processing, ICCSIP 2020

作者： Deng, Xin Zhou, Jianqiao Xiao, Bin Xiang, Xiaohong Yuan, Yi Key Laboratory of Data Engineering and Visual Computing Chongqing University of Posts and Telecommunication Chongqing400065 China Chongqing Key Laboratory of Image Recognition Chongqing University of Posts and Telecommunication Chongqing400065 China

ISBN: (纸本)9789811623356

Cardiovascular diseases are the main cause of global non-communicable deaths, accounting for about one-third of the total deaths in the world. Wearable devices are used for early monitoring and early prevention of cardiovascular diseases. Aimed at the low configuration, low power consumption and personalized characteristics of the wearable ECG equipment, a transfer learned with deep LSTM model is proposed in this work. The model is computational efficient and serves as the patient-specific ECG anomaly detector that can be used on the wearable devices. Based on the MIT-BIH open dataset, the experiment results show that the transfer learning model produces superior weighted F2 scores compared to the general model and the naive model for detecting ECG anomalies, such as the premature ventricular contractions and atrial premature beats. The transfer learning model proposed here provides a sensitive, personalized ECG anomaly detection mechanism that has the added benefit of light, quick and robust learning process to be used on wearable devices, which can meet the requirement of ECG monitoring for patients by wearable devices. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Electrocardiograms

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：