检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Li, Jiahe Zhang, Jiawei Bai, Xiao Zheng, Jin Ning, Xin Zhou, Jun Gu, Lin School of Computer Science and Engineering State Key Laboratory of Complex & Critical Software Environment Jiangxi Research Institute Beihang University China Institute of Semiconductors Chinese Academy of Sciences China School of Information and Communication Technology Griffith University Australia RIKEN AIP Japan The University of Tokyo Japan

Radiance fields have demonstrated impressive performance in synthesizing lifelike 3D talking heads. However, due to the difficulty in fitting steep appearance changes, the prevailing paradigm that presents facial motions by directly modifying point appearance may lead to distortions in dynamic regions. To tackle this challenge, we introduce TalkingGaussian, a deformation-based radiance fields framework for high-fidelity talking head synthesis. Leveraging the point-based Gaussian Splatting, facial motions can be represented in our method by applying smooth and continuous deformations to persistent Gaussian primitives, without requiring to learn the difficult appearance change like previous methods. Due to this simplification, precise facial motions can be synthesized while keeping a highly intact facial feature. Under such a deformation paradigm, we further identify a face-mouth motion inconsistency that would affect the learning of detailed speaking motions. To address this conflict, we decompose the model into two branches separately for the face and inside mouth areas, therefore simplifying the learning tasks to help reconstruct more accurate motion and structure of the mouth region. Extensive experiments demonstrate that our method renders high-quality lip-synchronized talking head videos, with better facial fidelity and higher efficiency compared with previous methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Detection approach for covert channel based on concurrency conflict interval time

引用

Jisuanji Yanjiu yu Fazhan/computer Research and Development 2011年第8期48卷 1542-1553页

作者： Wang, Yongji Wu, Jingzheng Ding, Liping Zeng, Haitao National Engineering Research Center for Fundamental Software Institute of Software Chinese Academy of Sciences Beijing 100190 China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing 100190 China Graduate University of Chinese Academy of Sciences Beijing 100049 China China Mobile Research Institute Beijing 100053 China

Concurrency conflicts may bring data conflict covert channel in multi-level secure systems. The existing covert channel detection methods have the following flaws: 1) Analyzing conflict records with single point, so the invaders can evade to be detected;2) Using single indicator will bring false positive and false negative. We present a detection method based on conflict interval time called CTIBDA in this paper. This method solves the above problems: 1) Analyzing the conflict records with subject and object can prevent intruders from dispersing;2) Using both the distribution and the sequence of intervals between transactions conflicts as indicators. The experimental results show that this approach can reduce the false positive and false negative and increase the accuracy. CTIBDA is suitable for online implementation and can be universally applied to concurrency conflict covert channels in other scenarios.

关键词： Concurrency control

来源：评论

学校读者我要写书评

暂无评论

Image-based Freeform Handwriting Authentication with Energy-oriented Self-Supervised Learning

arXiv

引用

arXiv 2024年

作者： Wang, Jingyao Mou, Luntian Zheng, Changwen Gao, Wen The University of Chinese Academy of Sciences Beijing100049 China The National Key Laboratory of Space Integrated Information System Institute of Software Chinese Academy of Sciences Beijing100086 China Beijing Institute of Artiicial Intelligence Faculty of Information Beijing University of Technology Beijing100124 China Beijing Key Laboratory of Multimedia and Intelligent Software Technology Beijing100124 China The School of Electronics Engineering and Computer Science Peking University Beijing100871 China

Freeform handwriting authentication verifies a person’s identity from their writing style and habits in messy handwriting data. This technique has gained widespread attention in recent years as a valuable tool for various fields, e.g., fraud prevention and cultural heritage protection. However, it still remains a challenging task in reality due to three reasons: (i) severe damage, (ii) complex high-dimensional features, and (iii) lack of supervision. To address these issues, we propose SherlockNet, an energy-oriented two-branch contrastive self-supervised learning framework for robust and fast freeform handwriting authentication. It consists of four stages: (i) pre-processing: converting manuscripts into energy distributions using a novel plug-and-play energy-oriented operator to eliminate the influence of noise;(ii) generalized pre-training: learning general representation through two-branch momentum-based adaptive contrastive learning with the energy distributions, which handles the high-dimensional features and spatial dependencies of handwriting;(iii) personalized fine-tuning: calibrating the learned knowledge using a small amount of labeled data from downstream tasks;and (iv) practical application: identifying individual handwriting from scrambled, missing, or forged data efficiently and conveniently. Considering the practicality, we construct EN-HA, a novel dataset that simulates data forgery and severe damage in real applications. Finally, we conduct extensive experiments on six benchmark datasets including our EN-HA, and the results prove the robustness and efficiency of SherlockNet. We will release our code and dataset at https://***/WangJingyao07/SherlockNet. Copyright © 2024, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Method for Detecting Jute Pests Using Deep Convolutional Neural Networks

An Intelligent Method for Detecting Jute Pests Using Deep Co...

引用

IoT Based Control Networks and Intelligent Systems (ICICNIS), International Conference on

作者： S. Vignesh S. Prabhu R. Sampathkumar M. Thillai Rani J. Rejina Parvin G. Uma Maheswari R. Saravanakumar Department of Computer Applications Karpagam Academy of Higher Education Coimbatore Tamil Nadu India Department of Mechatronics Engineering KPR Institute of Engineering and Technology Coimbatore Tamil Nadu India Department of Electronics and Communication Engineering Sri Krishna College of Technology Coimbatore Tamil Nadu India Department of Electronics and Communication Engineering Sri Krishna College of Engineering and Technology Coimbatore Tamil Nadu India Department of Computer Science and Engineering RMK College of Engineering and Technology Chennai Tamil Nadu India Iconix Software Solution Tirunelveli Tamil Nadu India

ISBN: (数字)9798331518097

ISBN: (纸本)9798331518103

Pest attacks pose a serious threat to the production of jute and other significant crops. Jute farmers often utilize their visual sense and hands-on expertise to distinguish between multiple diseases that seem to be identical. The intelligent model we built for the identification of jute pests was based on a deep convolutional neural network (DCNN). This practical difficulty led to the development of this concept. The proposed DCNN model can automatically identify jute pest concerns with high speed and accuracy based on image recognition. In addition, images of the four most common jute bugs are included in an organized image graphics collection. Our model yields a DCNN accuracy is 96.72% for the four most significant jute pest kinds. Further proof of the model's effectiveness is provided by the accuracy, recall, F1-score, and confusion matrix metrics.

关键词： Performance evaluation Visualization Accuracy Operating systems Production Pest control Feature extraction software Convolutional neural networks Overfitting

来源：评论

学校读者我要写书评

暂无评论

Approximate calculation of Si-OH SiO2 on Si surface by LDA and GGA method

引用

Shenzhen Daxue Xuebao (Ligong Ban)/Journal of Shenzhen University science and engineering 2008年第2期25卷 187-191页

作者： Yang, Chun Liao, Zi-Yi Yu, Yi Zhou, Ming-Xiu Yu, Wei-Fei Huang, Hui Key Laboratory of Computer Software Science Sichuan Normal University Chengdu 610068 China College of Chemistry and Material Science Chengdu 610068 China China Academy of Engineering Physics Mianyang 621000 China

Two models have been built on 2 × 1 Si (001) surfaces whose structures are Si-OH and Si-O-Si oxygenic bridge. The system energies and surface structures are comparatively calculated by generalized gradient approximation (GGA) and local density approximation (LDA), based on density functional theory (DFT) in k-point space with periodic boundary condition. After analysis of the calculation data in comparison with the experiment data, it is concluded that using GGA method is more suitable than LDA to calculate the surface structure of Si compound materials.

关键词： Porous silicon

来源：评论

学校读者我要写书评

暂无评论

Research on rough set theory and applications in China

引用

Lecture Notes in computer science

作者： Wang, Guoyin Zhang, Qinghua Huang, Houkuan Ye, Dongyi Hu, Qinghua Hu, Xuegang Shi, Zhongzhi Li, Yongli Shang, Lin An, Liping Sai, Ying Chen, Shanben Liang, Jiye Qin, Keyun Zeng, Huanglin Xie, Keming Miao, Duoqian Min, Fan Wu, Zhaocong Wu, Weizhi Dai, Jianhua Institute of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing 400065 China School of Information Science and Technology Southwest Jiaotong University Chengdu 610031 China School of Computer and Information Technology Beijing Jiaotong University Beijing 100044 China College of Math. and Computer Fuzhou University Fuzhou 350002 China Harbin Institute of Technology PO Box 458 Harbin 150006 China School of Computer and Information Hefei University of Technology Hefei 230009 China Institute of Computing Technology Chinese Academy of Sciences Beijing 100080 China Lanzhou University No.222 Tianshui South Rd. Lanzhou 730000 China State Key Laboratory for Novel Software Technology Nanjing University Nanjing 210093 China Management Science and Engineering Department Business School Nankai University Tianjin 300071 China Shandong University of Finance No.40 Shun-geng Road Jinan 250014 China Welding Engineering Institute Shanghai Jiaotong University Shanghai 200030 China School of Computer and Information Technology Shanxi University Taiyuan 030006 China Intelligent Control Development Center Southwest Jiaotong University Chengdu 610031 China Artificial Intelligence of Key Laboratory Sichuan University of Science and Engineering Zigong 643000 China Department of Automation College of Information Engineering Taiyuan University of Technology Taiyuan 030024 China 4800 CaoAn Highway Shanghai 201804 China School of Computer Science and Technology University of Electronic Science and Technology of China Chengdu 610054 China School of Remote Sensing Information Engineering Wuhan University Wuhan 430079 China Institute for Information and System Sciences Faculty of Science Xi'an Jiaotong University Xi'an 710049 China Information College Zhejiang Ocean University Zhejiang 316004 China Institute of Artificial Intelligence Zhejiang University Hangzhou 310027 China

ISBN: (纸本)3540850635

This article gives a capsule view of research on rough set theory and applications ongoing at universities and laboratories in China. Included in this capsule view of rough set research is a brief description of the following things: Chinese research groups on rough set with their URLs for web pages, names of principal researchers (supervisors), numbers of graduate students, and topics being investigated. Statistical summaries showing the growth in the research on rough set theory and application in China are included. In addition, an introduction summarizing the research interests of Chinese researchers is included in this article. The contribution of this article is a complete overview of the principal research directions in rough set theory and its applications in China. © 2008 Springer-Verlag Berlin Heidelberg.

关键词： Rough set theory

来源：评论

学校读者我要写书评

暂无评论

Semantic-Preserving Adversarial Text Attacks

TechRxiv

引用

TechRxiv 2021年

作者： Yang, Xinghao Gong, Yongshun Liu, Weifeng Bailey, James Zhu, Tianqing Tao, Dacheng Liu, Wei The School of Computer Science University of Technology Sydney 15 Broadway UltimoNSW2007 Australia The School of Software Shandong University Jinan China Qingdao266580 China The Department of Computing and Information Systems University of Melbourne Australia The JD Explore Academy China The Digital Science Institute Faculty of Engineering The University of Sydney DarlingtonNSW2008 Australia

Deep learning models are known immensely brittle to adversarial image examples, yet their vulnerability in text classification is insufficiently explored. Existing text adversarial attack strategies can be roughly divided into three categories, i.e., character-level attack, word-level attack, and sentence-level attack. Despite the success brought by recent text attack methods, how to induce misclassification with the minimal text modifications while keeping the lexical correctness, syntactic soundness, and semantic consistency simultaneously is still a challenge. To examine the vulnerability of deep models, we devise a Bigram and Unigram based adaptive Semantic Preservation Optimization (BU-SPO) approach which attacks text documents not only at a unigram word level but also at a bigram level to avoid generating meaningless sentences. We also present a hybrid attack strategy that collects substitution words from both synonyms and sememe candidates, to enrich the potential candidate set. Besides, a Semantic Preservation Optimization (SPO) method is devised to determine the word substitution priority and reduce the perturbation cost. Furthermore, we constraint the SPO with a semantic Filter (dubbed SPOF) to improve the semantic similarity between the input text and the adversarial example. To estimate the effectiveness of our proposed methods, BU-SPO and BU-SPOF, we attack four victim deep learning models trained on three real-world text datasets. Experimental results demonstrate that our approaches accomplish the highest semantics consistency and attack success rates by making the minimal word modifications compared with competitive methods. © 2021, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A Many-Objective Evolutionary Algorithm Assisted by Ideal Hyperplane

SSRN

引用

SSRN 2022年

作者： Zhang, Zhixia Wen, Jie Wang, Hui Cai, Xingjuan Cui, Zhihua Zhang, Wensheng School of Computer Science and Technology Taiyuan University of Science and Technology China School of Information Engineering Nanchang Institute of Technology Nanchang330099 China State Key Laboratory of Intelligent Control and Management of Complex System Institute of Automation Chinese Academy of Sciences China State Key Lab. for Novel Software Technology Nanjing University China

In many-objective optimization problems (MaOPs), it is a difficult task for evolutionary algorithms to balance convergence and diversity while rapidly converging to the Pareto front. As the number of objectives increases, the difficulty of evolutionary algorithms increases with individual selection pressure. To address above problems, we propose a many-objective evolution algorithm assisted by an ideal hyperplane (MaOEA-IH). Firstly, the ideal hyperplane as a reference surface to guide the individual to search the Pareto front, which is established from the extremum of each dimension of the objective space. Secondly, a parallel p -norm mating selection strategy is proposed to improve convergence. In addition, two factors are considered in this strategy: 1) different p -norm are used to measure different spatial scales;2) individual selection uncertainty is defined by incorporating a probabilistic perturbation mechanism. Thirdly, the improved shift-based density estimation strategy is used as the evaluation criterion for environmental selection to improve the convergence and diversity of solution sets and enhance selection pressure. To verify the effectiveness of the proposed algorithm, MAOEA-IH is compared with seven excellent algorithms in three benchmark sets (DTLZ, WFG and MaF). The results show that the proposed MAOEA-IH is highly competitive in solving MaOPs. © 2022, The Authors. All rights reserved.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Improving Sharpness-Aware Minimization with Fisher Mask for Better Generalization on Language Models

arXiv

引用

arXiv 2022年

作者： Zhong, Qihuang Ding, Liang Shen, Li Mi, Peng Liu, Juhua Du, Bo Tao, Dacheng National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence School of Computer Science Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China JD Explore Academy China School of Informatics Xiamen University China Research Center for Graphic Communication Printing and Packaging Institute of Artificial Intelligence Wuhan University China

Fine-tuning large pretrained language models on a limited training corpus usually suffers from poor generalization. Prior works show that the recently-proposed sharpness-aware minimization (SAM) optimization method can improve the model generalization. However, SAM adds a perturbation to each model parameter equally (but not all parameters contribute equally to the optimization of training), which we argue is sub-optimal and will lead to excessive computation. In this paper, we propose a novel optimization procedure, namely FSAM1, which introduces a Fisher mask to improve the efficiency and performance of SAM. In short, instead of adding perturbation to all parameters, FSAM uses the Fisher information to identity the important parameters and formulates a Fisher mask to obtain the sparse perturbation, i.e., making the optimizer focus on these important parameters. Experiments on various tasks in GLUE and SuperGLUE benchmarks show that FSAM consistently outperforms the vanilla SAM by 0.67∼1.98 average score among four different pretrained models. We also empirically show that FSAM works well in other complex scenarios, e.g., fine-tuning on generation tasks or limited training data. Encouragingly, when training data is limited, FSAM improves the SAM by a large margin, i.e., up to 15.1. Copyright © 2022, The Authors. All rights reserved.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Knowledge Graph Augmented Network Towards Multiview Representation Learning for Aspect-based Sentiment Analysis

arXiv

引用

arXiv 2022年

作者： Zhong, Qihuang Ding, Liang Liu, Juhua Du, Bo Jin, Hua Tao, Dacheng The National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence School of Computer Science Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China The Research Center for Graphic Communication Printing and Packaging Institute of Artificial Intelligence Wuhan University Wuhan China The JD Explore Academy *** Beijing China The Affiliated Hospital of Kunming University of Science and Technology Kunming China

Aspect-based sentiment analysis (ABSA) is a fine-grained task of sentiment analysis. To better comprehend long complicated sentences and obtain accurate aspect-specific information, linguistic and commonsense knowledge are generally required in this task. However, most current methods employ complicated and inefficient approaches to incorporate external knowledge, e.g., directly searching the graph nodes. Additionally, the complementarity between external knowledge and linguistic information has not been thoroughly studied. To this end, we propose a knowledge graph augmented network (KGAN), which aims to effectively incorporate external knowledge with explicitly syntactic and contextual information. In particular, KGAN captures the sentiment feature representations from multiple different perspectives, i.e., context-, syntax- and knowledge-based. First, KGAN learns the contextual and syntactic representations in parallel to fully extract the semantic features. Then, KGAN integrates the knowledge graphs into the embedding space, based on which the aspect-specific knowledge representations are further obtained via an attention mechanism. Last, we propose a hierarchical fusion module to complement these multi-view representations in a local-to-global manner. Extensive experiments on five popular ABSA benchmarks demonstrate the effectiveness and robustness of our KGAN. Notably, with the help of the pretrained model of RoBERTa, KGAN achieves a new record of state-of-the-art performance among all datasets. Copyright © 2022, The Authors. All rights reserved.

关键词： Sentiment analysis

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：