检索结果-内蒙古大学图书馆

17th Asian Conference on Computer Vision, ACCV 2024

作者： Ye, Weining Li, Zhixuan Jiang, Tingting School of Computer Science Peking University Beijing100871 China College of Computing and Data Science Nanyang Technological University Singapore Singapore National Engineering Research Center of Visual Technology National Key Laboratory for Multimedia Information Processing School of Computer Science National Biomedical Imaging Center Peking University Beijing100871 China

ISBN: (纸本)9789819609680

While the multi-view 3D reconstruction task has made significant progress, existing methods simply fuse multi-view image features without effectively leveraging available auxiliary information, especially the viewpoint information for guiding and associating features of different views. To this end, we propose to enhance multi-view 3D reconstruction with the power of viewpoint information. Specifically, a simple-yet-effective viewpoint estimator is designed to learn and provide comprehensive viewpoint knowledge for locating and associating learned features from different views. Moreover, to improve the 3D reconstruction quality when 2D images of only very few viewpoints are available, we propose to learn the shape prior knowledge to provide sufficient shape information for compensating the limited 2D observations. Overall, we present VIPNet, benefiting from Viewpoint Information and Shape Prior learning for high-quality multi-view 3D reconstruction. Extensive experiments validate the effectiveness of the proposed VIPNet, which achieves state-of-the-art performance on challenging datasets and shows well generalization ability in real-world scenarios. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Information Quantity Measurement and Feature Selection by Macrogranular Entropy

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年

作者： Zhu, Zhilin Zhang, Chucai Dai, Jianhua Hunan Normal University Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing College of Information Science and Engineering Changsha410081 China

Feature selection is an important data preprocessing process in artificial intelligence, which aims to eliminate redundant features while retaining essential features. Measuring feature significance and relevance between features is a significant challenge. Fuzzy information entropy is an extension of Shannon entropy. It is widely used for quantifying the information of fuzzy divisions. However, it has significant limitations, notably the lack of monotonicity in fuzzy conditional entropy measure of decision uncertainty in the feature selection process. We introduce a novel measurement Macrogranular Entropy (ME) and construct some generalized forms, such as conditional macrogranular entropy, mutual macrogranular information, and joint macrogranular entropy. The conditional macrogranular entropy exhibits monotonicity when measuring decision uncertainty. Additionally, we propose two feature selection algorithms: one based on Monotonic Conditional Macrogranular Entropy (MCME), and the other based on the Degree of Symmetric Association (ADSA). The ADSA algorithm and the MCME algorithm are compared against eight other feature selection algorithms through a series of experiments. The comparison was conducted based on classification performance using SVM and NB classifiers, as well as evaluation metrics including F1-score and Recall. In terms of all four evaluation metrics, ADSA and MCME achieved the top two rankings, respectively. Specifically, on the NB and SVM classifiers, the ADSA algorithm improves the average accuracy by 12.22% and 2.88% compared to the original feature set, while MCME improves the accuracy by 10.07% and 1.01%, respectively. Experimental comparisons demonstrate that ADSA algorithm effectively removes redundant information from the dataset during feature selection. © 2025 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Knowledge circuits in pretrained transformers 24

Knowledge circuits in pretrained transformers

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Yunzhi Yao Ningyu Zhang Zekun Xi Mengru Wang Ziwen Xu Shumin Deng Huajun Chen Zhejiang University National University of Singapore NUS-NCS Joint Lab Singapore Zhejiang University and Zhejiang Key Laboratory of Big Data Intelligent Computing

ISBN: (纸本)9798331314385

The remarkable capabilities of modern large language models are rooted in their vast repositories of knowledge encoded within their parameters, enabling them to perceive the world and engage in reasoning. The inner workings of how these models store knowledge have long been a subject of intense interest and investigation among researchers. To date, most studies have concentrated on isolated components within these models, such as the Multilayer Perceptrons and attention head. In this paper, we delve into the computation graph of the language model to uncover the knowledge circuits that are instrumental in articulating specific knowledge. The experiments, conducted with GPT2 and TinyLLAMA, have allowed us to observe how certain information heads, relation heads, and Multilayer Perceptrons collaboratively encode knowledge within the model. Moreover, we evaluate the impact of current knowledge editing techniques on these knowledge circuits, providing deeper insights into the functioning and constraints of these editing methodologies. Finally, we utilize knowledge circuits to analyze and interpret language model behaviors such as hallucinations and in-context learning. We believe the knowledge circuits hold potential for advancing our understanding of Transformers and guiding the improved design of knowledge editing. Code and data are available in https://***/zjunlp/KnowledgeCircuits.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning with Open-world Noisy data via Class-independent Margin in Dual Representation Space 39

Learning with Open-world Noisy Data via Class-independent Ma...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Pan, Linchao Gao, Can Zhou, Jie Wang, Jinbao College of Computer Science and Software Engineering Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China

ISBN: (纸本)157735897X

Learning with Noisy Labels (LNL) aims to improve the model generalization when facing data with noisy labels, and existing methods generally assume that noisy labels come from known classes, called closed-set noise. However, in real-world scenarios, noisy labels from similar unknown classes, i.e., open-set noise, may occur during the training and inference stage. Such open-world noisy labels may significantly impact the performance of LNL methods. In this study, we propose a novel dual-space joint learning method to robustly handle the open-world noise. To mitigate model overfitting on closed-set and open-set noises, a dual representation space is constructed by two networks. One is a projection network that learns shared representations in the prototype space, while the other is a One-Vs-All (OVA) network that makes predictions using unique semantic representations in the class-independent space. Then, bi-level contrastive learning and consistency regularization are introduced in two spaces to enhance the detection capability for data with unknown classes. To benefit from the memorization effects across different types of samples, class-independent margin criteria are designed for sample identification, which selects clean samples, weights closed-set noise, and filters open-set noise effectively. Extensive experiments demonstrate that our method outperforms the state-of-the-art methods and achieves an average accuracy improvement of 4.55% and an AUROC improvement of 6.17% on CIFAR80N. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

ConvTrans-TPS: A Convolutional Transformer Model for Disk Failure Prediction in Large-Scale Network Storage Systems 26

ConvTrans-TPS: A Convolutional Transformer Model for Disk Fa...

引用

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

作者： Xu, Shicheng Xu, Xiaolong Nanjing University of Posts and Telecommunications Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing210023 China Nanjing University of Posts and Telecommunications School of Computer Science Nanjing210023 China

ISBN: (纸本)9798350331684

Disk failure is one of the most important reliability problems in large-scale network storage systems. Disk failure may lead to serious data loss and even disastrous consequences if the missing data cannot be recovered. Therefore, predicting disk failures is an important means of ensuring storage security in network storage systems. However, since the fault data in the fast degradation stage is smaller than the healthy data in the normal state, the mixture of healthy data and faulty data leads to extremely unbalanced data, which brings great challenges to finding hidden fault information, thus making fault prediction more accurate. Aiming at the above problems, a convolutional transformer model ConvTrans-TPS model for disk failure prediction in large-scale network storage systems is proposed. The ConvTrans-TPS model acquires dependencies between long-term sequence data through transformers and uses convolutional projections for attention computation to enhance attention to local contextual information. data augmentation to predict failures in the next 7 days. Validated by the analysis on the Backblaze dataset, the F1 is 0.96 and the Matthews correlation coefficient (MCC) is 0.92. Compared with the popular CNN-LSTM model in recent years, our proposed method improves F1 and MCC by 4% and 5%, respectively, improving the prediction accuracy. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Cross Deployment of Active and Passive Reconfigurable intelligent Surfaces (RISs) for Next-Generation Communications 5

Cross Deployment of Active and Passive Reconfigurable Intell...

引用

5th IEEE International Conference on Electronic Information and Communication Technology, ICEICT 2022

作者： Chen, Luqi Chung, Kwok L. Lai, Guoming Yao, Junhao Zou, Xiaopeng Cheng, Xin Zheng, Kangtai Li, Yingsong School of Computer Science and Engineering Huizhou University China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education China

ISBN: (数字)9781665472111

ISBN: (纸本)9781665472111

In recent years, reconfigurable intelligent surface (RIS) technologies have been proposed due to its ability in shaping propagation environment for future 6G network development. Existing RIS technologies mainly include the active reconfigurable intelligent surface (ARIS) and the passive reconfigurable intelligent surface (PRIS). In this paper, according to the characteristics of RIS and demands of lower costs, we present a new strategy on the cross-deployment of ARIS and PRIS that meets the beneficial maximization in both capital cost and running cost. © 2022 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Temporal Knowledge Graph Question Answering: A Survey

arXiv

引用

arXiv 2024年

作者： Su, Miao Li, Zixuan Chen, Zhuo Bai, Long Jin, Xiaolong Guo, Jiafeng CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China

Knowledge Base Question Answering (KBQA) has been a long-standing field to answer questions based on knowledge bases. Recently, the evolving dynamics of knowledge have attracted a growing interest in Temporal Knowledge Graph Question Answering (TKGQA), an emerging task to answer temporal questions. However, this field grapples with ambiguities in defining temporal questions and lacks a systematic categorization of existing methods for TKGQA. In response, this paper provides a thorough survey from two perspectives: the taxonomy of temporal questions and the methodological categorization for TKGQA. Specifically, we first establish a detailed taxonomy of temporal questions engaged in prior studies. Subsequently, we provide a comprehensive review of TKGQA techniques of two categories: semantic parsing-based and TKG embedding-based. Building on this review, the paper outlines potential research directions aimed at advancing the field of TKGQA. This work aims to serve as a comprehensive reference for TKGQA and to stimulate further research. © 2024, CC BY.

关键词： Surveying

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Network Based Detection of Seasonal Features in Time Series data 11

Convolutional Neural Network Based Detection of Seasonal Fea...

引用

11th IEEE Global Conference on Consumer Electronics, GCCE 2022

作者： Hu, Kuang Yue, Kun School of Information Science and Engineering Yunnan University Kunming China Yunnan Key Laboratory of Intelligent Systems and Computing Yunnan University Kunming China

ISBN: (纸本)9781665492324

Seasonal features of various kinds of time-varying nodes in large-scale complex networks could facilitate the effective network optimization. It is necessary to find the nodes with seasonal features from the limited labeled training set. In this paper, we proposed a sequence convolutional neural network model to detect the seasonal features in time series data, as well as the method of time series upscaling and subsequence embedding as data preprocessing. Experimental results show the effectiveness of our proposed model. © 2022 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

A Multi-Objective Artificial Physics Optimization Algorithm Based on Two-Phase Search

A Multi-Objective Artificial Physics Optimization Algorithm ...

引用

International Symposium on Computer science and intelligent Controls (ISCSIC)

作者： Huihua Zhang Liping Xie Shanxi Key Laboratory of Big Data Analysis and Parallel Computing Taiyuan University of Science and Technology Taiyuan China

ISBN: (数字)9798350380286

ISBN: (纸本)9798350380293

Aiming at the problems of insufficient utilization of information about elite particles in archive and instability of particle motion in the population in the multi-objective artificial physics optimization algorithm (MOAPO) in solving multiobjective optimization problems, A multi-objective artificial physics optimization algorithm based on two-phase search (TPMOAPO) is proposed. To begin with, the algorithm improves the calculation of the mass of particles, so that the strength and weakness of the particles can be accurately transformed into the corresponding masses while improving the efficiency of particle mass calculation. Next, a two-phase search strategy is proposed, which makes the algorithm have strong exploration ability in the first phase, and the second phase gradually enhances the exploitation capability with iterations, which solves the problem of instability motion of particles in the search process. Finally, the simulated binary crossover (SBX) and polynomial-based mutation (PM) operators are adopted in the archive to further enhance the search capability of the algorithm. For verifying the performance of TP-MOAPO, 21 benchmark functions were selected to compare with the classical multi-objective particle swarm optimization algorithms: MOPSO, dMOPSO, SMPSO, MMOPSO, and NMPSO, and the experimental results show the superiority of TP-MOAPO in these functions.

关键词： Measurement Computer science Benchmark testing Search problems Particle swarm optimization Optimization Physics intelligent control Convergence

来源：评论

学校读者我要写书评

暂无评论

Drug-Protein Interaction Prediction by Fusion of Attention and Graph Neural Network

Drug-Protein Interaction Prediction by Fusion of Attention a...

引用

Chinese Control Conference (CCC)

作者： Tianrui Chen Shouheng Tuo Zengyu Feng School of Computer Science and Technology Xi'an University of Posts and Telecommunications Xi'an Shaanxi China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an Shaanxi China Xi'an Key Laboratory of Big Data and Intelligent Computing Xi'an Shaanxi China

The identification of drug-protein interactions (DTIs) is a critical step in drug development and repositioning. However, detecting these interactions using scientific methods presents a formidable challenge. Existing models often struggle to extract relevant information from drug-protein sequences, and they fail to consider pre-existing interactions between pairs. Here, we introduce a deep learning model, DPAG, based on attention mechanisms and graph neural networks, which overcomes these limitations. DPAG leverages information from both the drug and protein sequences, as well as the association between drug-protein pairs, to predict DTIs. We conducted multiple experiments to evaluate the performance of the model in benchmark datasets, and the results showed that DPAG achieved excellent performance in terms of AUC, AUPR, precision, and recall. Our findings suggest that DPAG holds significant potential as a promising tool for predicting DTIs in drug development and repositioning. Code is available at https://***/veresse/DPAG.

关键词：

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：