检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Hu, Kun Chen, Qicai Lu, Zilong Zhang, Wenzhuo Chen, Bihuan Lu, You Jiang, Haowen Sun, Bingkun Peng, Xin Zhao, Wenyun School of Computer Science Shanghai Key Laboratory of Data Science Fudan University Shanghai China

Vulnerabilities in open-source operating systems (OSs) pose substantial security risks to software systems, making their detection crucial. While fuzzing has been an effective vulnerability detection technique in various domains, OS fuzzing (OSF) faces unique challenges due to OS complexity and multi-layered interaction, and has not been comprehensively reviewed. Therefore, this work systematically surveys the state-of-the-art OSF techniques, categorizes them based on the general fuzzing process, and investigates challenges specific to kernel, file system, driver, and hypervisor fuzzing. Finally, future research directions for OSF are discussed. GitHub: https://***/pghk13/Survey-OSF. Copyright © 2025, The Authors. All rights reserved.

关键词： Open systems

来源：评论

学校读者我要写书评

暂无评论

Enhancing Weakly Supervised Medical Segmentation via Heterogeneous Co-training with Box-Wise Augmentation and Pseudo-Label Filtering 6th

Enhancing Weakly Supervised Medical Segmentation via Hetero...

引用

6th IFIP TC 12 International Conference on Intelligence science, ICIS 2024

作者： Wang, You Qi, Lei Yu, Qian Shi, Yinghuan Gao, Yang State Key Laboratory of Novel Software Technology National Insititute of Health-care Data Science Nanjing University Nanjing China School of Computer Science and Engineering Southeast University Nanjing China School of Data and Computer Science Shandong Woman’s University Jinan China

ISBN: (纸本)9783031712524

In this paper, we introduce an innovative approach to weakly supervised medical image segmentation with box annotations. Different from the previous methods which simply utilize a single conventional network with the same augmentation techniques widely used in supervised segmentation, we aim to introduce diverse augmentations and heterogenous networks to leverage the box annotations for promising generalization ability. Specifically, to amplify the diversity between the contents within the box and its surroundings, we propose the interior and exterior box augmentation (IEBA) technique, in which distinct augmentation techniques are employed for regions inside and outside the bounding boxes. Also, for the purpose of selecting pseudo-labels of superior quality, we propose the pseudo-label filter module (PLFM) to eliminate unreliable pseudo-labels. Besides, as CNN demonstrates superior capabilities in acquiring local information, and ViT specializes in capturing global context, we facilitate a bidirectional learning process between CNN and ViT through quadruple cross consistency losses (QCCL). In inference, we only employ the superior model from the validation set to obtain parameter efficiency. Our approach is evaluated across four tasks on two public datasets, utilizing the 3D dice similarity coefficient as the evaluation metric. The experimental results show that the proposed method outperforms the state-of-the-art comparison methods. © IFIP International Federation for Information Processing 2025.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Bit-mask Robust Contrastive Knowledge Distillation for Unsupervised Semantic Hashing 24

Bit-mask Robust Contrastive Knowledge Distillation for Unsup...

引用

33rd ACM Web Conference, WWW 2024

作者： He, Liyang Huang, Zhenya Liu, Jiayu Chen, Enhong Wang, Fei Sha, Jing Wang, Shijin School of Computer Science and Technology University of Science and Technology of China State Key Laboratory of Cognitive Intelligence Hefei China School of Data Science University of Science and Technology of China State Key Laboratory of Cognitive Intelligence Hefei China Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China State Key Laboratory of Cognitive Intelligence Hefei China State Key Laboratory of Cognitive Intelligence Hefei China

ISBN: (纸本)9798400701719

Unsupervised semantic hashing has emerged as an indispensable technique for fast image search, which aims to convert images into binary hash codes without relying on labels. Recent advancements in the field demonstrate that employing large-scale backbones (e.g., ViT) in unsupervised semantic hashing models can yield substantial improvements. However, the inference delay has become increasingly difficult to overlook. Knowledge distillation provides a means for practical model compression to alleviate this delay. Nevertheless, the prevailing knowledge distillation approaches are not explicitly designed for semantic hashing. They ignore the unique search paradigm of semantic hashing, the inherent necessities of the distillation process, and the property of hash codes. In this paper, we propose an innovative Bit-mask Robust Contrastive knowledge Distillation (BRCD) method, specifically devised for the distillation of semantic hashing models. To ensure the effectiveness of two kinds of search paradigms in the context of semantic hashing, BRCD first aligns the semantic spaces between the teacher and student models through a contrastive knowledge distillation objective. Additionally, to eliminate noisy augmentations and ensure robust optimization, a cluster-based method within the knowledge distillation process is introduced. Furthermore, through a bit-level analysis, we uncover the presence of redundancy bits resulting from the bit independence property. To mitigate these effects, we introduce a bit mask mechanism in our knowledge distillation objective. Finally, extensive experiments not only showcase the noteworthy performance of our BRCD method in comparison to other knowledge distillation methods but also substantiate the generality of our methods across diverse semantic hashing models and backbones. The code for BRCD is available at https://***/hly1998/BRCD. © 2024 Owner/Author.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Enhancing Quantitative Reasoning Skills of Large Language Models through Dimension Perception 40

Enhancing Quantitative Reasoning Skills of Large Language Mo...

引用

40th IEEE International Conference on data Engineering, ICDE 2024

作者： Huang, Yuncheng He, Qianyu Liang, Jiaqing Jiang, Sihang Xiao, Yanghua Chen, Yunwen School of Computer Science Shanghai Key Laboratory of Data Science Fudan University China School of Data Science Fudan University China DataGrand Co. LTD. Research Group of Computational and AI Communication Institute for Global Communications and Integrated Media Fudan University China

ISBN: (纸本)9798350317152

Quantities are distinct and critical components of texts that characterize the magnitude properties of entities, providing a precise perspective for the understanding of natural language, especially for reasoning tasks. In recent years, there has been a flurry of research on reasoning tasks based on large language models (LLMs), most of which solely focus on numerical values, neglecting the dimensional concept of quantities with units despite its importance. We argue that the concept of dimension is essential for precisely understanding quantities and of great significance for LLMs to perform quantitative reasoning. However, the lack of dimension knowledge and quantity-related benchmarks has resulted in low performance of LLMs. Hence, we present a framework to enhance the quantitative reasoning ability of language models based on dimension perception. We first construct a dimensional unit knowledge base (DimUnitKB) to address the knowledge gap in this area. We propose a benchmark DimEval consisting of seven tasks of three categories to probe and enhance the dimension perception skills of LLMs. To evaluate the effectiveness of our methods, we propose a quantitative reasoning task and conduct experiments. The experimental results show that our dimension perception method dramatically improves accuracy (43.55%→50.67%) on quantitative reasoning tasks compared to GPT-4. © 2024 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Research progress of quantum artificial intelligence in smart city

引用

Intelligent and Converged Networks 2024年第2期5卷 116-133页

作者： Sumin Wang Ning Wang Tongyu Ji Yiyun Shi Chao Wang the Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication Shanghai UniversityShanghai 200444China School of Information Engineering Ganzhou Key Laboratory of Cloud Computing and Big Data ResearchGannan University of Science and TechnologyGanzhou 341000China

The rapid accumulation of big data in the Internet era has gradually decelerated the progress of Artificial Intelligence(AI).As Moore’s Law approaches its limit,it is imperative to break the constraints that are holding back artificial *** computing and artificial intelligence have been advancing along the highway of human civilization for many years,emerging as new engines driving economic and social *** article delves into the integration of quantum computing and artificial intelligence in both research and *** introduces the capabilities of both universal quantum computers and special-purpose quantum computers that leverage quantum *** discussion further explores how quantum computing enhances classical artificial intelligence from four perspectives:quantum supervised learning,quantum unsupervised learning,quantum reinforcement learning,and quantum deep *** an effort to address the limitations of smart cities,this article explores the formidable potential of quantum artificial intelligence in the realm of smart *** does so by examining aspects such as intelligent transportation,urban operation assurance,urban planning,and information communication,showcasing a plethora of practical achievements in the *** the foreseeable future,Quantum Artificial Intelligence(QAI)is poised to bring about revolutionary development to smart *** urgency lies in developing quantum artificial intelligence algorithms that are compatible with quantum computers,constructing an efficient,stable,and adaptive hybrid computing architecture that integrates quantum and classical computing,preparing quantum data as needed,and advancing controllable qubit hardware equipment to meet actual *** ultimate goal is to shape the next generation of artificial intelligence that possesses common sense cognitive abilities,robustness,excellent generalization capabilities,and interpretability.

关键词： quantum artificial intelligence smart city D-Wave quantum computer

来源：评论

学校读者我要写书评

暂无评论

Predicting Rollback Edits on Stack Overflow Based on Deep Fusion of Metadata and Text 25

Predicting Rollback Edits on Stack Overflow Based on Deep Fu...

引用

25th IEEE International Conference on computer Supported Cooperative Work in Design, CSCWD 2022

作者： Jiang, Ting Zhang, Peng Lu, Tun Gu, Ning Fudan University School of Computer Science Shanghai China Fudan University Shanghai Key Laboratory of Data Science Shanghai China

ISBN: (纸本)9781665405270

Online question and answer (Q&A) communities have become an important platform for sharing and gaining knowledge. To ensure the quality of posts, Q&A sites support and encourage collaborative editing. However, some undesired, inaccurate, or poor quality edits will be rejected by rollbacks. Most Q&A communities identify rollback edits by human review, which is not efficient and timely enough. To address this problem, we aim to construct a model that can automatically predict whether an edit should be rolled back. Considering that in addition to changing the content of a post, editing activities usually generate metadata information. Therefore, we first conduct an empirical study to investigate the metadata factors that may be associated with edit rollbacks. The analysis results indicate that metadata features from multiple dimensions have different levels of significant effects on edit rollback, and edit textual contents are dependent on metadata. Based on these results, we propose a deep learning model, namely DFMT (Deep Fusion of Metadata and Text), for rollback prediction. Experimental results on a real Stack Overflow dataset demonstrates the effectiveness of DFMT compared to several baselines. © 2022 IEEE.

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

Skeleton-Based Action Recognition Using Graph Convolutional Network with Pose Correction and Channel Topology Refinement

引用

computers, Materials & Continua 2025年第4期83卷 701-718页

作者： Yuxin Gao Xiaodong Duan Qiguo Dai School of Engineering Guangzhou College of Technology and BusinessFoshan528138China School of Computer Science and Engineering Dalian Minzu UniversityDalian116000China SEAC key Laboratory of Big Data Applied Technology Dalian Minzu UniversityDalian116000China

Graph convolutional network(GCN)as an essential tool in human action recognition tasks have achieved excellent performance in previous ***,most current skeleton-based action recognition using GCN methods use a shared topology,which cannot flexibly adapt to the diverse correlations between joints under different motion *** video-shooting angle or the occlusion of the body parts may bring about errors when extracting the human pose coordinates with estimation *** this work,we propose a novel graph convolutional learning framework,called PCCTR-GCN,which integrates pose correction and channel topology refinement for skeleton-based human action ***,a pose correction module(PCM)is introduced,which corrects the pose coordinates of the input network to reduce the error in pose feature ***,channel topology refinement graph convolution(CTR-GC)is employed,which can dynamically learn the topology features and aggregate joint features in different channel dimensions so as to enhance the performance of graph convolution networks in feature ***,considering that the joint stream and bone stream of skeleton data and their dynamic information are also important for distinguishing different actions,we employ a multi-stream data fusion approach to improve the network’s recognition *** evaluate the model using top-1 and top-5 classification *** the benchmark datasets iMiGUE and Kinetics,the top-1 classification accuracy reaches 55.08%and 36.5%,respectively,while the top-5 classification accuracy reaches 89.98%and 59.2%,*** the NTU dataset,for the two benchmark RGB+Dsettings(X-Sub and X-View),the classification accuracy achieves 89.7%and 95.4%,respectively.

关键词： Pose correction multi-stream fusion GCN action recognition

来源：评论

学校读者我要写书评

暂无评论

Non-IID federated learning via random exchange of local feature maps for textile IIoT secure computing

引用

science China(Information sciences) 2022年第7期65卷 16-31页

作者： Bo PENG Mingmin CHI Chao LIU School of Computer Science Shanghai Key Laboratory of Data Science Fudan University Zhongshan Pool Net Technology Co.Ltd. Zhongshan Fudan Joint Innovation Center Zhengzhou Zhongke Institute of Integrated Circuit and System Application

With the fast development of artificial intelligence(AI) and industrial Internet of Things(IIoT)technologies, it is challenging to deal with the problems of data privacy protection and secure *** recent years, federated learning(FL) is proposed to attack the challenges of learning shared models collaboratively while protecting security based on the data from cross-domain clients. However, data in the real environment is usually not independent and identically distributed(Non-IID) due to the differences in business, working environments, and data acquisition, and thus classic federated methods suffer from significant performance degradation. In this paper, a novel federated framework is proposed for secure textile fiber identification(Fed TFI) via cross-domain texture representation based on high-definition fabric images. In addition to sharing the gradient of Fed TFI, the local patch of feature maps between crossdomain clients is randomly exchanged to build a richer image texture feature distribution while protecting data security simultaneously for secure computing. Furthermore, a texture embedding layer is designed to provide a joint representation through similarity measure between triplet samples in low-dimensional *** verify the effectiveness of the proposed framework, two textile image datasets, i.e., one public and the other we collected, are utilized to construct four Non-IID scenarios, including label skew, feature skew, and two combined skew scenarios. The experimental results confirm the effectiveness of our model to obtain better detection accuracies than benchmarks in four Non-IID scenarios by keeping data privacy for secure computing in fabric IIoT.

关键词： federated learning secure computing industrial Internet of Things (IIoT) machine vision texture encoding image classification Non-IID

来源：评论

学校读者我要写书评

暂无评论

Producing focused extreme ultraviolet vortex with Fermat-spiral photon sieves

引用

PhotoniX 2024年第1期5卷 476-483页

作者： Junyong Zhang Huaiyu Cui Yuanyuan Liu Xiuping Zhang You Li Dongdi Zhao Yongpeng Zhao Qiwen Zhan Key Laboratory of High Power Laser and Physics Shanghai Institute of Optics and Fine MechanicsQinghe Road201800 ShanghaiChina National Key Laboratory of Science and Technology on Tunable Laser Harbin Institute of TechnologyXidazhi Road150001 HarbinChina School of Optical-Electrical and Computer Engineering University of Shanghai for Science and TechnologyJungong Road200093 ShanghaiChina Zhangjiang Laboratory 100Haike Road201204 ShanghaiChina Westlake Institute for Optoelectronics 311421 FuyangHangzhouChina

Extreme ultraviolet(EUV)light is difficult to focus due to strong absorption of most *** sieves(PS),rather than Fresnel zone plates(FZP),can focus EUV to smaller spot and suppress the higher orders of secondary maxima by several orders of *** number of pinholes used in PS is far more than that of transparent rings used in FZP,providing a great flexibility to manipulate structured focusing in *** this work we investigate the Fermat-spiral PS to produce focused vortices with different topological *** at the wavelength of 46.9 nm is carried out and multi-planar coherent diffractive imaging is used to retrieve the phase map of the focused EUV *** results show the enormous potential of PS for manipulating EUV *** study not only provides a compact,affordable substitute to focusing vortices where transmissive optics materials are unavailable,but also provides a route of converting various complex light manipulation ranging from visible light to EUV and soft x-ray.

关键词： Extreme ultraviolet focusing Orbital angular momentum Photon sieves Coherent diffraction imaing

来源：评论

学校读者我要写书评

暂无评论

Early fire detection technology based on improved transformers in aircraft cargo compartments

引用

Journal of Safety science and Resilience 2024年第2期5卷 194-203页

作者： Hongzhou Ai Dong Han Xinzhi Wang Quanyi Liu Yue Wang Mengyue Li Pei Zhu College of Civil Aviation Safety Engineering Civil Aviation Flight University of ChinaGuanghan618307China CivilAircraf Fire Science and Safety Enginring Key Laboratory of Sichuan CivilAviation Flight University of ChinaGuanghan 618307China School of Computer Engineering and Science Shanghai UniversityShanghai 200444China Key Laboratory of Civil Aviation Emergency Science&Technology Nanjing University of Aeronautics and AstronauticsNanjing 210000China

The implementation of early and accurate detection of aircraft cargo compartment fire is of great significance to ensure flight *** current airborne fire detection technology mostly relies on single-parameter smoke detection using infrared *** often results in a high false alarm rate in complex air transportation *** traditional deep learning model struggles to effectively address the issue of long-term dependency in multivariate fire *** paper proposes a multi-technology collaborative fire detection method based on an improved transformers ***-wavelength optical sensors,flue gas analyzers,and other equipment are used to carry out multi-technology collaborative detection methods and characterize various feature dimensions of fire to improve detection *** improved Transformer model which integrates the self-attention mechanism and position encoding mechanism is applied to the problem of long-time series modeling of fire information from a global perspective,which effectively solves the problem of gradient disappearance and gradient explosion in traditional RNN(recurrent neural network)and CNN(convolutional neural network).Two different multi-head self-attention mechanisms are used to classify and model multivariate fire information,respectively,which solves the problem of confusing time series modeling and classification modeling in dealing with multivariate classification tasks by a single attention ***,the output results of the two models are fused through the gate *** research results show that,compared with the traditional single-feature detection technology,the multi-technology collaborative fire detection method can better capture fire *** with the traditional deep learning model,the multivariate fire pre-diction model constructed by the improved Transformer can better detect fires,and the accuracy rate is 0.995.

关键词： Deep learning Aircraft cargo compartment Attentionmechanism Firedetection Multi-sourcedata fusion

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：