检索结果-内蒙古大学图书馆

International Conference on computer Vision (ICCV)

作者： Guodong Wang Yunhong Wang Jie Qin Dongming Zhang Xiuguo Bao Di Huang State Key Laboratory of Software Development Environment Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China College of Computer Science and Technology NUAA Nanjing China Natl. Comp. Net. Emer. Resp. Tech. Team/Coord. Ctr. of China Beijing China

Anomaly detection (AD), aiming to find samples that deviate from the training distribution, is essential in safety-critical applications. Though recent self-supervised learning based attempts achieve promising results by creating virtual outliers, their training objectives are less faithful to AD which requires a concentrated inlier distribution as well as a dispersive outlier distribution. In this paper, we propose Unilaterally Aggregated Contrastive Learning with Hierarchical Augmentation (UniCon-HA), taking into account both the requirements above. Specifically, we explicitly encourage the concentration of inliers and the dispersion of virtual outliers via supervised and unsupervised contrastive losses, respectively. Considering that standard contrastive data augmentation for generating positive views may induce outliers, we additionally introduce a soft mechanism to re-weight each augmented inlier according to its deviation from the inlier distribution, to ensure a purified concentration. Moreover, to prompt a higher concentration, inspired by curriculum learning, we adopt an easy-to-hard hierarchical augmentation strategy and perform contrastive aggregation at different depths of the network based on the strengths of data augmentation. Our method is evaluated under three AD settings including unlabeled one-class, unlabeled multi-class, and labeled multi-class, demonstrating its consistent superiority over other competitors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unilaterally Aggregated Contrastive Learning with Hierarchical Augmentation for Anomaly Detection

arXiv

引用

arXiv 2023年

作者： Wang, Guodong Wang, Yunhong Qin, Jie Zhang, Dongming Bao, Xiuguo Huang, Di State Key Laboratory of Software Development Environment Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China College of Computer Science and Technology NUAA Nanjing China Natl. Comp. Net. Emer. Resp. Tech. Team/Coord. Ctr. of China Beijing China

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Equivariant diffusion for crystal structure prediction 24

Equivariant diffusion for crystal structure prediction

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Peijia Lin Pin Chen Rui Jiao Qing Mo Jianhuan Cen Wenbing Huang Yang Liu Dan Huang Yutong Lu School of Computer Science and Engineering Sun Yat-sen University Guangzhou China School of Computer Science and Engineering Sun Yat-sen University Guangzhou China and National Supercomputer Center in Guangzhou China Dept. of Comp. Sci. Tech. Institute for AI Tsinghua University Beijing China and Institute for AIR Tsinghua University Beijing China National Supercomputer Center in Guangzhou China Gaoling School of Artificial Intelligence Renmin University of China Beijing China and Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China

In addressing the challenge of Crystal Structure Prediction (CSP), symmetry-aware deep learning models, particularly diffusion models, have been extensively studied, which treat CSP as a conditional generation task. However, ensuring permutation, rotation, and periodic translation equivariance during diffusion process remains incompletely addressed. In this work, we propose EquiCSP, a novel equivariant diffusion-based generative model. We not only address the overlooked issue of lattice permutation equivariance in existing models, but also develop a unique noising algorithm that rigorously maintains periodic translation equivariance throughout both training and inference processes. Our experiments indicate that EquiCSP significantly surpasses existing models in terms of generating accurate structures and demonstrates faster convergence during the training process. Code is available at https://***/EmperorJia/EquiCSP.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Revocable Registered Attribute-Based Encryption With User Deregistration

引用

IEEE Internet of Things Journal 2025年

作者： Li, Jiguo Chen, Shaobo Lu, Yang Ning, Jianting Shen, Jian Zhang, Yichen Fujian Normal University College of Computer and Cyber Security Fuzhou350117 China Fuzhou350117 China Fujian Provincial Key Laboratory of Network Security and Cryptology Fuzhou350117 China Nanjing Normal University School of Computer and Electronic Information Nanjing210023 China Fujian Provincial Key Laboratory of Network Security and Cryptology College of Computer and Cyber Security Fuzhou350117 China Zhejiang Sci-Tech University School of Information Science and Engineering Hangzhou310018 China

Many businesses are putting their sensitive data in the cloud with the fast growth of cloud computing and storage. To ensure user privacy, it is necessary to keep encrypted data only in the cloud. Attribute-based encryption (ABE) is a popular mean in cloud storage scenarios. ABE is not only faced with key escrow problem but also suffers from user revocation issue when he or she is no longer authorized to access to encrypted data. In order to address these two issues, we propose a revocable registered attribute-based encryption scheme, which not only avoids key escrow problem but also supports precise revocation of a user’s access to a file as well as permanent deregistration of a user from the system. Furthermore, we prove the semantic security of the scheme and conduct a performance experiment to show the efficiency. © 2014 IEEE.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

Effect of Different Ultrasound Powers on the Stability of Native/Thermally Denatured Myofibrillar Protein-Inulin Emulsion

SSRN

引用

SSRN 2024年

作者： Wang, Mengman Ma, Chaowei Li, Yan Zhang, Zhiguo Huang, Ming Sun, Jingxin College of Food Science & Engineering Qingdao Agricultural University Qingdao266109 China Shandong Research Center for Meat Food Quality Control Qingdao Agricultural University Zhucheng Waimao Co. Ltd. Qingdao266109 China School of Food Science and Engineering Qilu University of Technology Shandong Academy of Sciences Ji’nan250353 China Nanjing210095 China National R&D Branch Center for Poultry Meat Processing Technology Nanjing Huangjiaoshou Food Sci. & Tech. Co. Ltd. Nanjing210095 China

Native/thermally denatured myofibrillar protein ( MPs/TMPs) combined with inulin (In) can improve its stability in water, but it also has certain limitations. The stability of MPs/TMPs-In emulsion was studied by applying ultrasound at different powers (200-800 W). After ultrasound treatment, the droplet size decreased, especially the particle size of MPs-600 W inulin emulsion reached 1 µm. In addition, by measuring the oxidation stability of oil, it was found that ultrasound could inhibit emulsion oxidation, and the PV of MPs-600 W droplets reached 5.37 ± 0.18 mmol/Kg and TBSAT reached 2.37 ± 0.19 µmol/Kg. However, at the same ultrasound power, the dispersion of TMPs-In droplets is not as good as that of MPs-In droplets, indicating that thermal denaturing is not conducive to emulsion stability. Therefore, the introduce of ultrasound to ameliorate the stability of MPs/TMPs-In emulsion is effective, especially at 600 W ultrasound power, the emulsion shows good stability. © 2024, The Authors. All rights reserved.

关键词： Emulsification

来源：评论

学校读者我要写书评

暂无评论

DEEPSCAN: Integrating Vision Transformers for Advanced Skin Lesion Diagnostics

引用

Open Dermatology Journal 2024年 18卷

作者： Jenefa, A. Edward Naveen, V. Ravi, Vinayakumar Punitha, S. Alahmadi, Tahani Jaser Stephan, Thompson Singh, Prabhishek Diwakar, Manoj Department of Computer Science Karunya Institute of Tech. and Sci Coimbatore India Department of computer science Sri Shakthi Institute of Engg. and Tech Coimbatore India Department of Computer Science Graphic Era Deemed to be University Uttarakhand Dehradun India School of Computer Science Engineering and Technology Bennett University Greater Noida India Center for Artificial Intelligence Prince Mohammad Bin Fahd University Khobar Saudi Arabia Department of Information Systems Princess Nourah bint Abdulrahman University P.O. Box 84428 Riyadh 11671 Saudi Arabia

Introduction/Background: The rise in dermatological conditions, especially skin cancers, highlights the urgency for accurate diagnostics. Traditional imaging methods face challenges in capturing complex skin lesion patterns, risking misdiagnoses. Classical CNNs, though effective, often miss intricate patterns and contextual nuances. Materials and Methods: Our research investigates the adoption of Vision Transformers (ViTs) in diagnosing skin lesions, capitalizing on their attention mechanisms and global contextual insights. Utilizing the fictional Dermatological Vision Dataset (DermVisD) with over 15,000 annotated images, we compare ViTs against traditional CNNs. This approach aims to assess the potential benefits of ViTs in dermatology. Results: Initial experiments showcase an 18% improvement in diagnostic accuracy using ViTs over CNNs, with ViTs achieving a remarkable 97.8% accuracy on the validation set. These findings suggest that ViTs are significantly more adept at recognizing complex lesion patterns. Discussion: The integration of Vision Transformers into dermatological imaging marks a promising shift towards more accurate diagnostics. By leveraging global contextual understanding and attention mechanisms, ViTs offer a nuanced approach that could surpass traditional methods. This advancement indicates a potential for setting new accuracy benchmarks in skin lesion diagnostics. Conclusion: ViTs present a significant advancement in the field of dermatological imaging, potentially redefining accuracy and reliability standards. This study underscores the transformative impact of ViTs on the detection and diagnosis of skin conditions, advocating for their broader adoption in clinical settings. © 2024 The Author(s). Published by Bentham Open.

关键词： Deep learning Health system Human and disease Medical image analysis Skin lesion diagnostics Vision transformers (ViTs)

来源：评论

学校读者我要写书评

暂无评论

Improved PSP-Net Segmentation Network for Automatic Detection of Neovascularization in Color Fundus Images

Improved PSP-Net Segmentation Network for Automatic Detectio...

引用

IEEE Visual Communications and Image Processing (VCIP)

作者： Qiuming Liu Shen Wang Yulan Dai Jintao Zhang Yichen Wang Ruoxuan Zhou School of Software Engineering Jiangxi Univ. of Sci. and Tech. Jiangxi China School of Computer Science and Engineering Central South University Changsha China School of Computer Info. Engineering Jiangxi Normal University Jiangxi China Factory and Cultural Communications Nanchang Key lab. of Virtual Digital Jiangxi China

ISBN: (纸本)9781665475938

Proliferative Diabetic Retinopathy (PDR) is a seri-ous retinal disease threatening diabetic patients. Intense retinal neovascularization in the retinal image is the most important clinical symptom of PDR, leading to visual distortion if not controlled. Accurate and timely detection of neovascularization from retinal images allows patients to receive adequate treatment to avoid further vision loss. In this work, we propose a retinal neovascularization automatic segmentation model based on im-proved Pyramid Scene Parsing Network (PSP-Net). To improve the accuracy of the model, we introduce the proposed channel attention module into the model. The network is evaluated with color fundus images from practice. Evaluation results show the network is superior to FCN, SegNet, U-Net and PSP-Net in accuracy and sensitivity. The model could achieve accuracy, sensitivity, specificity, precision and Jaccard similarity score of 0.9832,0.9265,0.9897,0.9116 and 0.8501, respectively. This paper proves through plenty of experimental results that the network model is able to improve the accuracy of segmentation, relieve the workload of doctors, and is worthy of further clinical promotion.

关键词： Visualization Sensitivity Image color analysis Visual communication Retinopathy Semantic segmentation Neural networks

来源：评论

学校读者我要写书评

暂无评论

Double Deep RL-Based Strategy for UAV-Assisted Energy Harvesting Optimization in Disaster-Resilient IoT Networks

Double Deep RL-Based Strategy for UAV-Assisted Energy Harves...

引用

International Conference on Mechatronics (ICOM)

作者： Nahla Nur Elmadina Rashid A. Saeed Elsadig Saeid Elmustafa Sayed Ali Ibtehal Nafea Mayada A. Ahmed Rania A. Mokhtar Othman O. Khalifa Department of Electrical Engineering Alzaiem Alazhari University Khartoum Sudan Electronics Department Sudan University of Science and Technology Khartoum Sudan College of Computer Science and Engineering Taibah University Medina Saudi Arabia Faculty of Eng. School of ElecsEng. Sudan Uni. of Sci. and Tech. Khartoum Sudan Dept of Elec and Comp Eng Inter. Islamic Uni. Malaysia KL Malaysia Libyan Center for Engineering Research and Information Technology Bani Walid Libya

ISBN: (数字)9798350349788

ISBN: (纸本)9798350349795

Unmanned Aerial Vehicles (UAVs) are increasingly crucial for emergency-response scenarios, including tasks like wireless power transfer (WPT) and data collection in disaster zones. This paper proposes a Double Deep Reinforcement Learning (DDRL) framework for energy harvesting (EH) in such scenarios. Our framework involves a UAV swarm navigating an area to provide WPT. The primary goal is to enhance service quality in critical areas while enabling dynamic swarm management for tasks like recharging. We formulate this as a nonlinear programming (NLP) optimization problem, maximizing EH from IoT devices and optimizing UAV trajectories under constraints like mission duration and energy limits. Due to the problem's complexity, we propose a lightweight DDRL solution capable of efficiently learning system dynamics. Extensive simulations and comparisons with Deep RL and DDPG algorithms demonstrate the superior performance of DDRL in enhancing EH, covering strategic locations effectively, and achieving high satisfaction and accuracy rates.

关键词： Wireless power transfer Programming Autonomous aerial vehicles Nonlinear dynamical systems Trajectory Internet of Things Energy harvesting

来源：评论

学校读者我要写书评

暂无评论

Decoding the Obfuscated: Advanced NER tech.iques on Commercial Sex Advertisement Data

Decoding the Obfuscated: Advanced NER Techniques on Commerci...

引用

International Conference on Computational science and Computational Intelligence (Csci)

作者： Alejandro Rodriguez Perez Pablo Rivas Javier Turek Korn Sooksatra Ernesto Quevedo Gisela Bichler Tomas Cerny Laurie Giddens Stacie Petter Dept. of Computer Science School of Eng. & Computer Science Baylor University Human-Robot Collaboration Lab Intelligent Systems Research Intel Labs School of Criminology & Criminal Justice California State University San Bernardino Dept. of Systems and Industrial Eng. College of Engineering The University of Arizona Information Tech. & Decisions Sci. Dept. G. Brint Ryan College of Business University of North Texas School of Business Wake Forest University

ISBN: (数字)9798350361513

ISBN: (纸本)9798350372304

Detecting potential human trafficking activity within online Commercial Sex Advertisements (CSAs) presents unique challenges for Named Entity Recognition (NER) due to the complex and often obfuscated textual content. This paper thoroughly evaluates state-of-the-art language models and tokenization tech.iques, focusing on their efficacy in the NER task within the context of CSAs. Our results indicate that the Longformer model, equipped with byte-level BPE tokenization, outperforms other models regarding precision, recall, and the $F$ 1 score. The study also uncovers specific areas for improvement, offering avenues for future research. Our findings have significant implications for the automated analysis and monitoring of CSAs for suspected human trafficking activity, which contributes to developing more robust and transparent online ecosystems.

关键词： Adaptation models Biological system modeling Focusing Named entity recognition Tokenization Data models Web sites

来源：评论

学校读者我要写书评

暂无评论

Crystal structure prediction by joint equivariant diffusion 23

Crystal structure prediction by joint equivariant diffusion

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Rui Jiao Wenbing Huang Peijia Lin Jiaqi Han Pin Chen Yutong Lu Yang Liu Dept. of Comp. Sci. & Tech. Institute for AI Tsinghua University and Institute for AIR Tsinghua University Gaoling School of Artificial Intelligence Renmin University of China and Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China National Supercomputer Center in Guangzhou School of Computer Science and Engineering Sun Yat-sen University Stanford University

Crystal Structure Prediction (CSP) is crucial in various scientific disciplines. While CSP can be addressed by employing currently-prevailing generative models (e.g. diffusion models), this task encounters unique challenges owing to the symmetric geometry of crystal structures—the invariance of translation, rotation, and periodicity. To incorporate the above symmetries, this paper proposes DiffCSP, a novel diffusion model to learn the structure distribution from stable crystals. To be specific, DiffCSP jointly generates the lattice and atom coordinates for each crystal by employing a periodic-E(3)-equivariant denoising model, to better model the crystal geometry. Notably, different from related equivariant generative approaches, DiffCSP leverages fractional coordinates other than Cartesian coordinates to represent crystals, remarkably promoting the diffusion and the generation process of atom positions. Extensive experiments verify that our DiffCSP significantly outperforms existing CSP methods, with a much lower computation cost in contrast to DFT-based methods. Moreover, the superiority of DiffCSP is also observed when it is extended for ab initio crystal generation. Code is available at https://***/jiaor17/DiffCSP.

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：