检索结果-内蒙古大学图书馆

2021 3rd International Conference on Artificial Intelligence and Computer Science, AICS 2021

作者： Yang, Wen Wang, Lei Liu, Chao Zhong, Qiangqiang School of Information Engineering Nanchang Institute of Technology Nanchang330099 China Jiangxi Provincial Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing Nanchang Institute of Technology Nanchang330099 China

The classical attribute reduction algorithm is not suitable for the neighborhood decision information system of numerical attribute. Since any feature subset in real feature space can be approximated by neighborhood information particles, the concept of knowledge granularity is extended to neighborhood rough set from the perspective of the granularity computation. In this paper, knowledge granularity, attribute importance and heuristic algorithm based on the granularity of knowledge in neighborhood rough set are studied from the point of view of neighborhood relation matrix. The feasibility of heuristic algorithm is analyzed on UCI data sets. Experiments achieve better classification accuracy and lower attribute reduction results than the existing algorithms. © Journal of Physics: Conference Series 2021.

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Exploiting Robust Model Watermarking Against the Model Fine-Tuning Attack via Flat Minima Aware Optimizers

Exploiting Robust Model Watermarking Against the Model Fine-...

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Dongdong Lin Yue Li Bin Li Jiwu Huang Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China Shenzhen Key Laboratory of Media Security Shenzhen University Shenzhen China SZU-AFS Joint Innovation Center for AI Technology Shenzhen University Shenzhen China Xiamen Key Laboratory of Data Security and Blockchain Technology Huaqiao University Xiamen China Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University Shenzhen China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

With the rapid advancement of deep neural networks (DNNs), model watermarking has emerged as a widely adopted technique for safeguarding model copyrights. A prevalent method involves utilizing a watermark decoder to retrieve watermark bits from generated outputs, but such methods are often vulnerable to model fine-tuning attacks. Traditionally, this challenge is mitigated through adversarial training or data augmentation, both of which significantly increase the computational burden. In this paper, we present a solution employing Flat Minima Aware (FMA) optimizers to bolster the robustness of model watermarking without requiring additional training data. By optimizing the watermark loss with flat minima awareness, our approaches significantly enhance the robustness of watermarks against the model fine-tuning attack. Comprehensive experiments have demonstrated our method’s superior ability to preserve watermark integrity. These findings suggest that this innovative optimization strategy offers a robust and efficient pathway for protecting models, thereby contributing to more secure and reliable model copyright protection mechanisms.

关键词： Training Resistance Computational modeling Training data Watermarking Signal processing Diffusion models Robustness Speech processing Optimization

来源：评论

学校读者我要写书评

暂无评论

Modeling the Relative Visual Tempo for Self-supervised Skeleton-based Action Recognition

Modeling the Relative Visual Tempo for Self-supervised Skele...

引用

International Conference on Computer Vision (ICCV)

作者： Yisheng Zhu Hu Han Zhengtao Yu Guangcan Liu Nanjing University of Posts and Telecommunications Key Laboratory of Intelligent Information Processing Institute of Computing Technology (ICT) Chinese Academy of Sciences (CAS) University of the Chinese Academy of Sciences Faculty of Information Engineering and Automation Kunming University of Science and Technology School of Automation Southeast University

Visual tempo characterizes the dynamics and the temporal evolution, which helps describe actions. Recent approaches directly perform visual tempo prediction on skeleton sequences, which may suffer from insufficient feature representation issue. In this paper, we observe that relative visual tempo is more in line with human intuition, and thus providing more effective supervision signals. Based on this, we propose a novel Relative Visual Tempo Contrastive Learning framework for skeleton action Representation (RVTCLR). Specifically, we design a Relative Visual Tempo Learning (RVTL) task to explore the motion information in intra-video clips, and an Appearance-Consistency (AC) task to learn appearance information simultaneously, resulting in more representative spatiotemporal features. Furthermore, skeleton sequence data is much sparser than RGB data, making the network learn shortcuts, and overfit to low-level information such as skeleton scales. To learn high-order semantics, we further design a new Distribution-Consistency (DC) branch, containing three components: Skeleton-specific Data Augmentation (S-DA), Fine-grained Skeleton Encoding Module (FSEM), and Distribution-aware Diversity (DD) Loss. We term our entire method (RVTCLR with DC) as RVTCLR+. Extensive experiments on NTU RGB+D 60 and NTU RGB+D 120 datasets demonstrate that our RVTCLR+ can achieve competitive results over the state-of-the-art methods. Code is available at https://***/Zhuysheng/RVTCLR.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CA-Edit: Causality-Aware Condition Adapter for High-Fidelity Local Facial Attribute Editing 39

CA-Edit: Causality-Aware Condition Adapter for High-Fidelity...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Xian, Xiaole He, Xilin Niu, Zenghao Zhang, Junliang Xie, Weicheng Song, Siyang Yu, Zitong Shen, Linlin Computer Vision Institute School of Computer Science & 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 University of Exeter United Kingdom Great Bay University China

ISBN: (纸本)157735897X

For efficient and high-fidelity local facial attribute editing, most existing editing methods either require additional finetuning for different editing effects or tend to affect beyond the editing regions. Alternatively, inpainting methods can edit the target image region while preserving external areas. However, current inpainting methods still suffer from the generation misalignment with facial attributes description and the loss of facial skin details. To address these challenges, (i) a novel data utilization strategy is introduced to construct datasets consisting of attribute-text-image triples from a data-driven perspective, (ii) a Causality-Aware Condition Adapter is proposed to enhance the contextual causality modeling of specific details, which encodes the skin details from the original image while preventing conflicts between these cues and textual conditions. In addition, a Skin Transition Frequency Guidance technique is introduced for the local modeling of contextual causality via sampling guidance driven by low-frequency alignment. Extensive quantitative and qualitative experiments demonstrate the effectiveness of our method in boosting both fidelity and editability for localized attribute editing. Our codes will be made publicly available. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Logical Relation Modeling and Mining in Hyperbolic Space for Recommendation 40

Logical Relation Modeling and Mining in Hyperbolic Space for...

引用

40th IEEE International Conference on Data Engineering, ICDE 2024

作者： Tan, Yanchao Lv, Hang Zhou, Zihao Guo, Wenzhong Xiong, Bo Liu, Weiming Chen, Chaochao Wang, Shiping Yang, Carl College of Computer and Data Science Fuzhou University Fuzhou China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou China Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou China Institute for Artificial Intelligence University of Stuttgart Stuttgart Germany College of Computer Science Zhejiang University Hangzhou China Emory University Department of Computer Science Atlanta United States

ISBN: (纸本)9798350317152

The sparse interactions between users and items have aggravated the difficulty of their representations in recommender systems. Existing methods leverage tags to alleviate the sparsity problem but ignore prevalent logical relations among items and tags (e.g., membership, hierarchy, and exclusion), which can be leveraged to enhance the accuracy of modeling user preferences and conducting recommendations. To this end, we propose to extract logical relations among item tags from existing tag taxonomies and exploit the individual strengths of the Poincaré and the Lorentz models in hyperbolic space for logical relation modeling towards enhanced recommendations. Moreover, we find that the logical relations directly extracted from existing tag taxonomies can be inaccurate and coarse. Therefore, we further devise innovative consistency-based and granularity-based weighting mechanisms based on user behavior patterns for data-driven logical relation mining that can be jointly optimized along with recommendations in an end-to-end fashion. Extensive experiments on four real-world benchmark datasets show drastic performance gains brought by our proposed framework, which constantly achieves an average of 8.25% improvement over state-of-the-art competitors regarding both Recall and NDCG metrics. Insightful case studies further demonstrate that our automatically refined logical relations are highly accurate and interpretable. © 2024 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Large Model-Based Data Augmentation for Imbalanced Text Classification

Large Model-Based Data Augmentation for Imbalanced Text Clas...

引用

Artificial Intelligence, Networking and information technology (AINIT), International Seminar on

作者： Dawei Zhang Rongxin Mi Peiyao Zhou Dawei Jin Manman Zhang Tianhang Song School of Computer Science Jiangsu University of Science and Technology Zhenjiang Jiangsu China National Computer Network Emergency Response Technical Team/Coordination Center of China Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences (CAS) Beijing China

ISBN: (数字)9798350385557

ISBN: (纸本)9798350385564

This study focuses on the application of large models to deal with imbalanced data problems in text classification. In view of the central position of text in web data and the negative impact of class imbalance on classifier performance, researchers have explored the method of using large models to generate high-quality minority class samples to enhance model performance. This paper reviews the technical progress of machine learning, deep learning, and large language models and their applications in text classification tasks. Although large models perform well in complex tasks due to their excellent language understanding ability, traditional machine learning and deep learning methods are popular in text classification scenarios that require fast response due to their simple structure and higher computational efficiency. This study proposes a data augmentation technique inspired by SMOTE, which uses a large language model combined with a simple prompt engineering strategy to generate high-quality minority samples. The experimental results show that the proposed method significantly improves the macro average precision, recall and F1 score on multiple text classification models, and effectively alleviates the challenge of class imbalance.

关键词： Deep learning Seminars Computational modeling Large language models Text categorization Data augmentation Data models

来源：评论

学校读者我要写书评

暂无评论

DOA estimation for beam scanning radar based on sparse signal reconstruction with incomplete pulse

DOA estimation for beam scanning radar based on sparse signa...

引用

2022 IEEE International Conference on Signal processing, Communications and computing, ICSPCC 2022

作者： Wu, Ran Zhang, Yan Ni, Lihua Zhang, Kehao Liu, Ning Wan, Qun University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu611731 China Northern Institute of Electronic Equipment Beijing100191 China Agile and Intelligent Computing Key Laboratory of Sichuan Province Chengdu611731 China

ISBN: (数字)9781665469722

ISBN: (纸本)9781665469722

Direction of Arrival (DOA) is one of the commonly used measurement for source localization. However, the receiving equipment of modern electronic reconnaissance can not completely intercept the pulse signal in the complex and dense electromagnetic environment. Thus, it is not easy to accurately estimate its DOA, especially in the case of multiple targets. In order to solve this problem, we propose a sparse super-resolution DOA method to achieve DOA estimation incomplete pulse. Combined with compressed sensing theory, the complex DOA estimation problem is transformed into Basis Pursuit (BP) method based on the minimum 1 norm optimization criterion. The method estimates the DOA by solving the optimal sparse vector that constitutes the signal and can detect multiple targets in the same range-azimuth unit. In addition, compared with the traditional direction-finding method using the BP method, our method can guarantee the performance of direction-finding while reducing the requirement of pulse integrity. The simulation results support the theoretical analysis. © 2022 IEEE.

关键词： Direction of arrival

来源：评论

学校读者我要写书评

暂无评论

Human-like conceptual representations emerge from language prediction

arXiv

引用

arXiv 2025年

作者： Xu, Ningyu Zhang, Qi Du, Chao Luo, Qiang Qiu, Xipeng Huang, Xuanjing Zhang, Menghan School of Computer Science Fudan University Shanghai China Institute of Modern Languages and Linguistics Fudan University Shanghai China Shanghai Key Laboratory of Intelligent Information Processing Shanghai China Research Institute of Intelligent Complex Systems Fudan University Shanghai China Shanghai Collaborative Innovation Center of Intelligent Visual Computing Shanghai China Ministry of Education Key Laboratory of Contemporary Anthropology Fudan University Shanghai China

People acquire concepts through rich physical and social experiences and use them to understand the world. In contrast, large language models (LLMs), trained exclusively through next-token prediction over language data, exhibit remarkably human-like behaviors. Are these models developing concepts akin to humans, and if so, how are such concepts represented and organized? To address these questions, we reframed the classic reverse dictionary task to simulate human concept inference in context and investigated the emergence of human-like conceptual representations within LLMs. Our results demonstrate that LLMs can flexibly derive concepts from linguistic descriptions in relation to contextual cues about other concepts. The derived representations converged towards a shared, context-independent structure that effectively predicted human behavior across key psychological phenomena, including computation of similarities, categories and semantic scales. Moreover, these representations aligned well with neural activity patterns in the human brain, even in response to visual rather than linguistic stimuli, providing evidence for biological plausibility. These findings establish that structured, human-like conceptual representations can naturally emerge from language prediction without real-world grounding. More broadly, our work positions LLMs as promising computational tools for understanding complex human cognition and paves the way for better alignment between artificial and human intelligence. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Analysis and Prediction of Overseas Cargo on the China-Laos Railway 11th

Analysis and Prediction of Overseas Cargo on the China-Laos ...

引用

11th International Conference on Traffic and Transportation Studies, ICTTS 2024

作者： Hu, Hengchaung Zhang, Yaqin Li, Wang School of Traffic and Transportation Beijing Jiaotong University Beijing100044 China Institute of Computing Technology China Academy of Railway Sciences CorporationLimited Beijing100081 China Beijing Engineering Research Center of Urban Traffic Information Intelligent Sensing andService Technologies Beijing100044 China Key Laboratory of Active Safety Assurance and Risk Prevention in the Railway Industry Beijing Jiaotong University Beijing100044 China

ISBN: (纸本)9789819796397

This paper makes an in-depth analysis of the characteristics of overseas cargo on the China-Laos Railway and predicts the future freight trend based on historical data, so as to provide decision-making support for enhancing the influence of the China-Laos Railway freight market and promoting the quality and increment of freight transportation. Firstly, the current situation of cargo transportation were analyzed. Then, by using the K-means cluster analysis method, the cluster analysis of the freight volume of major stations outside the China-Laos Railway was carried out, and the characteristics of freight categories between stations were discussed. Finally, based on the method of time series analysis, the total amount of freight and the total amount of major goods are predicted, so as to reveal the development trend of China-Laos railway freight transportation and provide decision-making support for relevant departments and enterprises to formulate industrial development strategies. © Beijing Paike Culture Commu. Co., Ltd. 2025.

关键词： characteristics of the goods China-Laos Railway cluster analysis time series analysis

来源：评论

学校读者我要写书评

暂无评论

Extract Features from Lithium-Ion Battery Electrochemical Impedance Spectra and Estimate State of Health Based on Improved Convolutional Autoencoder-Temporal Convolutional Network

SSRN

引用

SSRN 2024年

作者： Wang, Kai Lou, Cheng Wang, Shi Li, Zhaoting School of Electrical Engineering Weihai Innovation Research Institute Qingdao University Qingdao266000 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Engineering Brown University ProvidenceRI02912 United States Shandong Suoxiang Intelligent Technology Co. Ltd Weifang261101 China

Predicting the State of Health (SOH) of batteries is crucial for understanding their remaining lifespan and formulating more effective maintenance and management strategies. Utilizing electrochemical impedance spectroscopy (EIS) to assess the health status of batteries offers advantages such as high precision, rapid response, non-invasiveness, and reliability for accurately forecasting the remaining lifespan of batteries. This study introduces an innovative deep learning technique that integrates an improved convolutional autoencoder (ICAE) with a temporal convolutional network (TCN) for extracting unsupervised features from 2D imagery derived from EIS data. This approach effectively captures battery feature information closely associated with its operational state. The unsupervised feature extraction process proposed in this work outperforms traditional supervised learning methods, enabling more accurate SOH predictions without reliance on pre-labeled data. Experimental results indicate that the deep learning methodology, employing the unsupervised feature extraction process, achieved a root mean square error (RMSE) of less than 2% in the SOH prediction task, and exhibited a prediction performance enhancement of 55.6% compared to the existing baseline model. © 2024, The Authors. All rights reserved.

关键词： Electrochemical impedance spectroscopy

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：