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： Boyu Han Qianqian Xu Zhiyong Yang Shilong Bao Peisong Wen Yangbangyan Jiang Qingming Huang Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and School of Computer Science and Tech. University of Chinese Academy of Sciences Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and Peng Cheng Laboratory School of Computer Science and Tech. University of Chinese Academy of Sciences School of Computer Science and Tech. University of Chinese Academy of Sciences and Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and Key Laboratory of Big Data Mining and Knowledge Management CAS

ISBN: (纸本)9798331314385

The Area Under the ROC Curve (AUC) is a well-known metric for evaluating instance-level long-tail learning problems. In the past two decades, many AUC optimization methods have been proposed to improve model performance under long-tail distributions. In this paper, we explore AUC optimization methods in the context of pixel-level long-tail semantic segmentation, a much more complicated scenario. This task introduces two major challenges for AUC optimization techniques. On one hand, AUC optimization in a pixel-level task involves complex coupling across loss terms, with structured inner-image and pairwise inter-image dependencies, complicating theoretical analysis. On the other hand, we find that mini-batch estimation of AUC loss in this case requires a larger batch size, resulting in an unaffordable space complexity. To address these issues, we develop a pixel-level AUC loss function and conduct a dependency-graph-based theoretical analysis of the algorithm's generalization ability. Additionally, we design a Tail-Classes Memory Bank (T-Memory Bank) to manage the significant memory demand. Finally, comprehensive experiments across various benchmarks confirm the effectiveness of our proposed AUCSeg method. The code is available at https://***/boyuh/AUCSeg.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Automatic Text Summarization Model for Judgment Documents 8th

A Hybrid Automatic Text Summarization Model for Judgment Doc...

引用

8th International Conference on Artificial Intelligence and Security , ICAIS 2022

作者： Ouyang, Jianquan Huang, Wenpeng Liu, Tianming Key Laboratory of Intelligent Computing Information Processing Ministry of Education School of Computer Science and School of Cyberspace Science Xiangtan University Xiangtan China Department of Computer Science The University of Georgia AthensGA United States

ISBN: (纸本)9783031067662

Judgment documents are the final carrier of judicial trial activities, and they are an indispensable component for assisting sentencing decision-making and standardizing the scale of judgment. At present, the number of public judgment documents in China has reached 120 million, and it does not stop there, which brings a significant challenge for users to obtain useful information. To solve this problem, this paper proposes a hybrid automatic text summarization model for judgment documents. The method is divided into two stages. The first stage is, through extracting abstract technology, to extract key sentences from the original text to form a set of them. In the second stage, the set of key sentences extracted in the previous stage will be copied or rewritten to generate the final summary using the sequence generation model. The ROUGE indexes of this method in the automatic summarization experiment of judgment documents are 59.79, 37.71, and 52.67, which are 5.26, 7.25, and 10.41 higher than the benchmark model UniLM, respectively. The method proposed in this paper can effectively be applied in the automatic summarization service of judgment documents and solve the problem of information overload thereof and, finally, provide a new way for users to gain smooth access to judgment documents and information. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Downstream Task-agnostic Transferable Attacks on Language-Image Pre-training Models

Downstream Task-agnostic Transferable Attacks on Language-Im...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yiqiang Lv Jingjing Chen Zhipeng Wei Kai Chen Zuxuan Wu Yu-Gang Jiang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai Collaborative Innovation Center of Intelligent Visual Computing

Vision-language pre-trained models (e.g., CLIP) trained on large-scale datasets via self-supervised learning, are drawing increasing research attention since they can achieve superior performances on multi-modal downstream tasks. Nevertheless, we find that the adversarial perturbations crafted on vision-language pre-trained models can be used to attack different corresponding downstream task models. Specifically, to investigate such adversarial transferability, we introduce a task-agnostic method named Global and Local Augmentation (GLA) attack to generate highly transferable adversarial examples on CLIP, to attack black-box downstream task models. GLA adopts random crop and resize at both global and local patch levels, to create more diversity and make adversarial noises robust. Then GLA generates the adversarial perturbations by minimizing the cosine similarity between intermediate features from augmented adversarial and benign examples. Extensive experiments on three CLIP image encoders with different backbones and three different downstream tasks demonstrate the superiority of our method compared with other strong baselines. The code is available at https://***/yqlvcoding/GLAattack.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Globally Consistent Vertical Federated Graph Autoencoder for Privacy-Preserving Community Detection 17th

Globally Consistent Vertical Federated Graph Autoencoder for...

引用

17th CCF Conference on Computer Supported Cooperative Work and Social computing, ChineseCSCW 2022

作者： Fang, Yutong Huang, Qingqing Ye, Enjie Guo, Wenzhong Guo, Kun Chen, Xiaoqi Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350108 China College of Computer and Data Science/College of Software Fuzhou University Fuzhou350108 China Key Laboratory of Spatial Data Mining and Information Sharing Ministry of Education Fuzhou350108 China

ISBN: (纸本)9789819923557

Community detection is a trendy area in research on complex network analysis and has a wide range of real-world applications, like advertising. As people become increasingly concerned about privacy, protecting participants’ privacy in distributed community detection has become a new challenge. When applied to not identically and independently distributed (Non-IID) data, most federated graph algorithms suffer from the weight divergence problem caused by diversified training of local and global models, resulting in accuracy degradation. Furthermore, the privacy protection approaches based on anonymization, such as differential privacy (DP), and cryptography, such as homomorphic encryption (HE), incur accuracy loss and high time consumption, respectively. In this paper, we propose a globally consistent vertical federated graph autoencoder (GCVFGAE) algorithm, which builds a globally consistent model among the coordinator and all participants to solve the Non-IID graph data problem. As well, an attribute blinding strategy based on security aggregation is developed to protect the network privacy of each participant without losing accuracy. Both real-world and artificial networks’ experiments show that our algorithm reaches higher accuracy than the existing vertical federated graph neural networks (GNNs) and the simple distributed graph autoencoder without federated learning and detects communities identical to those found by the standard graph autoencoder (GAE). © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Population dynamics

来源：评论

学校读者我要写书评

暂无评论

Horizontal Federated Traffic Speed Prediction Base on Secure Node Attribute Aggregation 17th

Horizontal Federated Traffic Speed Prediction Base on Secur...

引用

17th CCF Conference on Computer Supported Cooperative Work and Social computing, ChineseCSCW 2022

作者： Ye, Enjie Guo, Kun Guo, Wenzhong Chen, Dangrun Zhang, Zihan Li, Fuan Zheng, JiaChen Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350108 China College of Computer and Data Science/College of Software Fuzhou University Fuzhou350108 China Key Laboratory of Spatial Data Mining and Information Sharing Ministry of Education Fuzhou350108 China

ISBN: (纸本)9789819923847

Federated graph learning has been widely used in distributed graph machine learning tasks. The data distribution of existing graph-based federated Spatio-temporal prediction methods is mainly segmented by graph topology. However, in the real-world Spatio-temporal traffic speed prediction task, a location will have data from different devices belonging to different companies. A node may have multi-party information in the real-world distributed traffic speed prediction scenario. The difference in multi-party information leads to the information not being fully utilized. Moreover, the direct transmission of node embedding in the federated learning process may also risk privacy leaks. Using homomorphic encryption and other encryption methods will bring a high computational overhead. Therefore we propose a new distributed privacy-preserving traffic speed prediction algorithm, which uses secure node attribute aggregation strategy(SNAAS) to apply to the multi-party collaborative traffic speed prediction scenario when the graph topology structure is public. At the same time, secret sharing technology is used in SNAAS to protect the attribute matrix and reduce the overhead of secret computing. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Text Guided Road Marking Point Cloud Completion

Text Guided Road Marking Point Cloud Completion

引用

Next Generation Data-driven Networks (NGDN), International Conference on

作者： Xu He Qihong Xu Huan Luo College of Computer and Data Science Fuzhou University Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou China

ISBN: (数字)9798350388374

ISBN: (纸本)9798350388381

With the continuous development of intelligent transportation technologies such as autonomous driving and navigation, accurate perception of road markings becomes crucial. However, due to limitations in sensor perspectives and obstacles blocking the view, the scanned point cloud of road markings is often incomplete, potentially leading to erroneous decisions in intelligent transportation systems. Therefore, it becomes imperative to recover complete road markings from these incomplete point clouds. This paper proposes a text-guided road marking completion method, which integrates text information with point cloud data using attention mechanisms. By leveraging text information to guide the network in completing road marking point clouds, the proposed method aims to enhance the perception accuracy and completeness of road markings. Experimental validation on road marking datasets demonstrates the effectiveness and feasibility of the proposed approach.

关键词： Point cloud compression Accuracy Attention mechanisms Navigation Fuses Roads Transportation Diffusion models Robustness Next generation networking

来源：评论

学校读者我要写书评

暂无评论

Identification of differential brain regions in MCI progression via clustering-evolutionary weighted SVM ensemble algorithm

引用

Frontiers of Computer science 2021年第6期15卷 165-173页

作者： Xia-an BI Yiming XIE Hao WU Luyun XU Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal UniversityChangsha 410081China College of Information Science and Engineering Hunan Normal UniversityChangsha 410081China Business School of Hunan Normal University Changsha 410081China

Mild cognitive impairment(MCI)as the potential sign of serious cognitive decline could be divided into two stages,i.e.,late MCI(LMCI)and early MCI(EMCI).Although the different cognitive states in the MCI progression have been clinically defined,effective and accurate identification of differences in neuroimaging data between these stages still needs to be further *** this paper,a new method of clustering-evolutionary weighted support vector machine ensemble(CEWSVME)is presented to investigate the alterations from cognitively normal(CN)to EMCI to *** CEWSVME mainly includes two *** first step is to build multiple SVM classifiers by randomly selecting samples and *** second step is to introduce the idea of clustering evolution to eliminate inefficient and highly similar SVMs,thereby improving the final classification ***,we extracted the optimal features to detect the differential brain regions in MCI progression,and confirmed that these differential brain regions changed dynamically with the development of *** exactly,this study found that some brain regions only have durative effects on MCI progression,such as parahippocampal gyrus,posterior cingulate gyrus and amygdala,while the superior temporal gyrus and the middle temporal gyrus have periodic effects on the *** work contributes to understanding the pathogenesis of MCI and provide the guidance for its timely diagnosis.

关键词： machine learning MCI progression optimal feature extraction differential brain regions functional magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Edge-Preserving Multi-Exposure Fusion with Guided Filtering for Structural Patch Decomposition 6

Edge-Preserving Multi-Exposure Fusion with Guided Filtering ...

引用

6th IEEE International Conference on Electronic information and Communication Technology, ICEICT 2023

作者： Zhen, Yang Qi, Junwei Li, Yingsong College of Information and Communication Engineering Harbin Engineering University Harbin150001 China Ministry of Education Anhui University Key Laboratory of Intelligent Computing and Signal Processing Hefei China College of Computer Science and Technology Harbin Engineering University Harbin150001 China

ISBN: (纸本)9798350399059

Multi-exposure image fusion (MEF) is one of the effective ways to obtain high dynamic range (HDR) images. Multi-scale structural patch decomposition based MEF(MSPD) and edge-preserving structural patch decomposition (MESPD) have achieved state-of-the-art fusion quality. MESPD incorporates edge-preserving factors into MSPD to preserve details in a single-scale setting. However, we find that the edge-preserving factors put too much emphasis on the edge, resulting in artifacts on some edges and loss of details. To tackle this issue, guided filter is introduced into MSPD, which is directly used as an edge-preserving filter instead of mean filter to implicitly decompose images. In addition, we have designed a flexible adaptive weight, which can further maintain details of the light and dark areas. Likewise, we inherit MESPD and MSPD to extend our method to multi-scale framework. Extensive experimental results demonstrate our method can produce satisfactory results in both static and dynamic scenes with fewer artifacts and low computational cost. © 2023 IEEE.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

An SDN Traffic Engineering Approach Based on Traffic Unsupervised Contrastive Representation and Reinforcement Learning

An SDN Traffic Engineering Approach Based on Traffic Unsuper...

引用

Next Generation Data-driven Networks (NGDN), International Conference on

作者： Ruiyu Yang Qi Tang Yingya Guo College of Computer and Data Science Fuzhou University Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou China

ISBN: (数字)9798350388374

ISBN: (纸本)9798350388381

With the rapid development of Internet technology and the continuous explosive growth of network traffic, Traffic Engineering (TE), as a viable method for optimizing network traffic distribution and improving network performance, attracts widespread attention from both industry and academia. Software Defined Networks (SDN), which decouples the data plane and the control plane, realizes a flexible routing and improves the TE performance. Existing TE approaches in SDN mainly utilize Reinforcement Learning (RL) methods to learn the mapping relationship between network traffic and routing policies. However, due to the continuous expansion of network size and dynamic changes in traffic, the enlargement of traffic state space hinders RL from converging to the optimal routing policy, leading to a decline in network performance. To address these issues, this paper presents a TE method based on unsupervised contrastive representation and RL. This method first shrinks the original traffic state space by efficiently extracting traffic features through Contrastive Learning (CL), aiding quick convergence of RL. It then uses RL to directly learn the mapping from traffic features to traffic splitting policies. Finally, through numerous experiments on real network traffic and topology, it demonstrates that the proposed TE method can effectively achieve load balancing of network traffic under complex and volatile dynamic traffic demands, thereby enhancing network performance.

关键词： Training Network topology Telecommunication traffic Reinforcement learning Feature extraction Routing Load management Topology Software defined networking Next generation networking

来源：评论

学校读者我要写书评

暂无评论

Research on patent recommendation method based on graph neural network 26

Research on patent recommendation method based on graph neur...

引用

26th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2023

作者： Zhang, Enchao Liu, Weidong Liu, Shi Cao, Yan Institute of Scientific and Technical Information of China China College of Computer Science Inner Mongolia University China Natl. Loc. Jt. Eng. Research Center of Intelligent Information Processing Technology for Mongolian China Inner Mongolia Key Laboratory of Social Computing and Data Processing China Inner Mongolia Engineering Laboratory for Big Data Analysis Technology China

ISBN: (纸本)9798350331684

Intellectual property transactions have shown a strong growth momentum in recent years, but the patent transaction market has been plagued by the matching degree of consumers and sellers, resulting in frequent problems such as low patent transformation efficiency and poor transaction quality. This paper proposes a method of recommending patents to consumers by experts to improve the environment of patent transactions. Through the analysis of the past transaction information of the patent, the effective path information of the target is extracted. The graph neural network is used to describe the characteristics and semantics among experts, patents and consumers, and then capture the potential weight among them through the common attention mechanism, and then dynamically integrate them to predict the occurrence of recommendation behavior. The paper makes reasonable use of social information and expert information in the transaction, which significantly improves the rationality and accuracy of expert recommendation. © 2023 IEEE.

关键词： Patents and inventions

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：