检索结果-内蒙古大学图书馆

30th International Conference on MultiMedia Modeling, MMM 2024

作者： Hong, Zixuan Cao, Weipeng Xu, Zhiwu Chen, Zhenru Tao, Xi Ming, Zhong Cao, Chuqing Zheng, Liang College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Shenzhen518107 China Anhui Province Key Laboratory of Machine Vision Inspection Yangtze River Delta HIT Robot Technology Research Institute Wuhu241000 China

ISBN: (纸本)9783031533044

Video super-resolution is a pivotal task that involves the recovery of high-resolution video frames from their low-resolution counterparts, possessing a multitude of applications in real-world scenarios. Within the domain of prevailing video super-resolution models, a majority of these models are tailored to specific magnification factors, thereby lacking a cohesive architecture capable of accommodating arbitrary magnifications. In response to this lacuna, this study introduces "MetaVSR", a novel video super-resolution model devised to handle arbitrary magnifications. This model is structured around three distinct modules: inter-frame alignment, feature extraction, and upsampling. In the inter-frame alignment module, a bidirectional propagation technique is employed to attain the alignment of adjacent frames. The feature extraction module amalgamates superficial and profound video features to enhance the model’s representational prowess. The upsampling module serves to establish a mapping correlation between the desired target resolution and the input provided in lower resolution. An array of empirical findings attests to the efficacy of the proposed MetaVSR model in addressing this challenge. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Hybrid Feature Measurement based on Linear and Nonlinear Nonnegative Matrix Factorization 5

Hybrid Feature Measurement based on Linear and Nonlinear Non...

引用

5th International Conference on Algorithms, Computing and Artificial Intelligence, ACAI 2022

作者： Ye, Sicong Zhao, Yang Pei, Jihong The Guangdong Key Laboratory of Intelligent Information Processing College of Electronics and Information Engineering in Shenzhen University China College of Computer Science and Software Engineering Shenzhen University China

ISBN: (纸本)9781450398343

The nonnegative matrix factorization algorithm is an effective data dimensionality reduction method. The principle is to convert the image into a nonnegative linear combination of low dimensional basis images. Nonnegative matrix factorization can be divided into linear algorithm and nonlinear algorithm. Because of different decomposition theory, linear NMF algorithms mainly extract first-order features of data, while nonlinear NMF algorithms mainly extract high-order features. Most of the current studies only focus on one of the models without combining the two together, which leads to the lack of data features. Therefore it is necessary to integrate the two types of algorithms for research. The paper proposes hybrid feature measurement based on linear and nonlinear nonnegative matrix factorization. The algorithm utilizes the idea of feature fusion. The basis image features of the two algorithms are mixed in the model. Finally a feature similarity measurement is obtained as the measure method. The proposed algorithm has good performance on the public datasets and effectively improves the recognition. © 2022 ACM.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

An End-to-End Graph Attention Network Hashing for Cross-Modal Retrieval 38

An End-to-End Graph Attention Network Hashing for Cross-Moda...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Jin, Huilong Zhang, Yingxue Shi, Lei Zhang, Shuang Kou, Feifei Yang, Jiapeng Zhu, Chuangying Luo, Jia College of Engineering Hebei Normal University China College of Computer and Cyber Security Hebei Normal University China State Key Laboratory of Media Convergence and Communication Communication University of China China Key Laboratory of Education Informatization for Nationalities Yunnan Normal University Ministry of Education China School of Computer Science Beijing University of Posts and Telecommunications China Guangxi Key Laboratory of Trusted Software Guilin University of Electronic Technology China Chongqing Research Institute Beijing University of Technology China

Due to its low storage cost and fast search speed, cross-modal retrieval based on hashing has attracted widespread attention and is widely used in real-world applications of social media search. However, most existing hashing methods are often limited by uncomprehensive feature representations and semantic associations, which greatly restricts their performance and applicability in practical applications. To deal with this challenge, in this paper, we propose an end-to-end graph attention network hashing (EGATH) for cross-modal retrieval, which can not only capture direct semantic associations between images and texts but also match semantic content between different modalities. We adopt the contrastive language image pretraining (CLIP) combined with the Transformer to improve understanding and generalization ability in semantic consistency across different data modalities. The classifier based on graph attention network is applied to obtain predicted labels to enhance cross-modal feature representation. We construct hash codes using an optimization strategy and loss function to preserve the semantic information and compactness of the hash code. Comprehensive experiments on the NUS-WIDE, MIRFlickr25K, and MS-COCO benchmark datasets show that our EGATH significantly outperforms against several state-of-the-art methods. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Designing Uncorrelated Address Constrain for DNA Storage by DMVO Algorithm

引用

IEEE/ACM Transactions on Computational Biology and Bioinformatics 2022年第2期19卷 866-877页

作者： Cao, Ben Ii, Xue Zhang, Xiaokang Wang, Bin Zhang, Qiang Wei, Xiaopeng Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education Ministry of Education School of Software Engineering Dalian University Dalian116622 China School of Computer Science and Technology Dalian University of Technology Dalian116024 China

At present, huge amounts of data are being produced every second, a situation that will gradually overwhelm current storage technology. DNA is a storage medium that features high storage density and long-term stability and is now considered to be a feasible storage solution. Errors are easily made during the sequencing and synthesis of DNA, however. In order to reduce the error rate, novel uncorrelated address constrain are reported, and a Damping Multi-Verse Optimizer (DMVO)algorithm is proposed to construct a set of DNA coding, which is used as the non-payload. The DMVO algorithm exchanges objects through black/white holes in order to achieve a stable state and adds damping factors as disturbances. Compared with previous work, the coding set obtained by the DMVO algorithm is larger in size and of higher quality. The results of this study reveal that the size of the DNA storage coding set obtained by the DMVO algorithm increased by 4-16 percent, and the variance of the melting temperature decreased by 3-18 percent. © 2004-2012 IEEE.

关键词： Damping

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence for Edge Service Optimization in Internet of Vehicles:A Survey

引用

Tsinghua Science and Technology 2022年第2期27卷 270-287页

作者： Xiaolong Xu Haoyuan Li Weijie Xu Zhongjian Liu Liang Yao Fei Dai the School of Computer and Software Nanjing University of Information Science and TechnologyNanjing 210044China the Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology(CICAEET) Nanjing University of Information Science and Technology and EngineeringNanjing 210044China the State Key Laboratory for Novel Software Technology Nanjing UniversityNanjing 210023China the School of Big Data and Intelligence Engineering Southwest Forestry UniversityKunming 650233China

The Internet of Vehicles(IoV)plays a crucial role in providing diversified services because of its powerful capability of collecting real-time ***,collected information is transmitted to a centralized resourceintensive cloud platform for service *** Computing(EC)that deploys physical resources near road-side units is involved in IoV to support real-time services for vehicular ***,many measures are adopted to optimize the performance of EC-enabled IoV,but they hardly help make dynamic decisions according to real-time *** Intelligence(AI)is capable of enhancing the learning capacity of edge devices and thus assists in allocating resources *** extensive research has employed AI to optimize EC performance,summaries with relative concepts or prospects are quite *** address this gap,we conduct an exhaustive survey about utilizing AI in edge service optimization in ***,we establish the general condition and relative concepts about IoV,EC,and ***,we review the edge service frameworks for IoV and explore the use of AI in edge server placement and service ***,we discuss a number of open issues in optimizing edge services with AI.

关键词： edge service internet of vehicles artificial intel igence

来源：评论

学校读者我要写书评

暂无评论

Diving into Continual Ultra-fine-grained Visual Categorization

Diving into Continual Ultra-fine-grained Visual Categorizati...

引用

2023 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2023

作者： Zhang, Pengcheng Yu, Xiaohan Bai, Xiao Zheng, Jin Wu, Xiaoyu Gao, Yongsheng Beihang University School of Computer Science and Engineering State Key Laboratory of Software Development Environment Jiangxi Research Institute Beijing China Griffith University Institute for Integrated and Intelligent Systems Nathan4111 Australia

ISBN: (纸本)9798350382204

Recent advance in ultra-fine-grained visual categorization (ultra-FGVC) has significantly boosted the capability of deep neural networks for ultra-FGVC tasks. However, building models for continually learning to recognize increasing ultra-fine-grained categories is still under-explored. This limits the application of ultra-FGVC techniques in real-world production. To this, we take the first attempt for continual ultra-FGVC. By evaluating existing continual learning methods on the constructed continual ultra-FGVC benchmark, we observe that the main bottleneck lies in the limited model plasticity for incrementally adapting to new tasks. This can be caused by excessive anti-forgetting constraints as the difficult ultra-FGVC task requires substantial update of parameters, and over-fitting on early tasks given that the ultra-fine-grained categories are with very few training samples. To tackle these problems, we propose a joint self-supervised learning and prompting model. The prompt-based continual learning framework offers proper anti-forgetting operation by fixed pretrained vision transformer and adaptive prompt selection. By jointly optimizing the learnable prompts with an adversarial self-supervised loss, the over-fitting on each continual learning task is mitigated. Extensive experiments demonstrate that the proposed method outperforms existing continual learning methods on the challenging continual ultra-FGVC problem. © 2023 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

eSROP Attack: Leveraging Signal Handler to Implement Turing-Complete Attack Under CFI Defense 1

引用

18th EAI International Conference on Security and Privacy in Communication Networks, SecureComm 2022

作者： Zhang, Tianning Cai, Miao Zhang, Diming Huang, Hao Department of Computer Science and Technology Nanjing University Nanjing China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing China School of Computer and Information Hohai University Nanjing China College of Computer Engineering Jiangsu University of Science and Technology Nanjing China

ISBN: (数字)9783031255380

ISBN: (纸本)9783031255373

Signal Return Oriented Programming (SROP) is a dangerous code reuse attack method. Recently, defense techniques have been proposed to defeat SROP attacks. In this paper, we leverage the signal nesting mechanism provided by current operating systems and propose a new variant of SROP attack called enhanced SROP (eSROP) attack. eSROP provides the ability of invoking arbitrary system calls, simulating Turing-complete computation, and even bypassing the fine-grained label-based CFI defense, without modifying the return address and instruction register in the signal frame. Because the signal returns to the interrupted instruction, the shadow stack defense can hardly detect our attack. Signal has strong flexibility which can interrupt the normal control flow. We leverage such flexibility to design a new code reuse attack. To evaluate eSROP, we perform two exploits on two real-world programs, namely Proftpd and Wu-ftpd. In our attacks, adversaries can invoke arbitrary system calls and obtain a root shell. Both attacks succeed within 10 min under strict system defense such as data execution prevention, address space layout randomization, and coarse-grained control flow integrity. © 2023, ICST Institute for computer Sciences, Social Informatics and Telecommunications engineering.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Prompting Continual Person Search 24

Prompting Continual Person Search

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Zhang, Pengcheng Yu, Xiaohan Bai, Xiao Zheng, Jin Ning, Xin School of Computer Science and Engineering State Key Laboratory of Complex & Critical Software Environment Jiangxi Research Institute Beihang University Beijing China School of Computing Macquarie University Sydney Australia Institute of Semiconductors Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798400706868

The development of person search techniques has been greatly promoted in recent years for its superior practicality and challenging goals. Despite their significant progress, existing person search models still lack the ability to continually learn from increasing real-world data and adaptively process input from different domains. To this end, this work introduces the continual person search task that sequentially learns on multiple domains and then performs person search on all seen domains. This requires balancing the stability and plasticity of the model to continually learn new knowledge without catastrophic forgetting. For this, we propose a Prompt-based Continual Person Search (PoPS) model in this paper. First, we design a compositional person search transformer to construct an effective pre-trained transformer without exhaustive pre-training from scratch on large-scale person search data. This serves as the fundamental for prompt-based continual learning. On top of that, we design a domain incremental prompt pool with a diverse attribute matching module. For each domain, we independently learn a set of prompts to encode the domain-oriented knowledge. Meanwhile, we jointly learn a group of diverse attribute projections and prototype embeddings to capture discriminative domain attributes. By matching an input image with the learned attributes across domains, the learned prompts can be properly selected for model inference. Extensive experiments are conducted to validate the proposed method for continual person search. The source code is available at https://***/PatrickZad/PoPS. © 2024 ACM.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Method for Statistical Downscaling of CLDAS Relative Humidity with Different Sources of Data:Sensitivity Analysis

引用

Journal of Meteorological Research 2023年第6期37卷 878-895页

作者： Bin BAI Chunxiang SHI Ling YANG Lingling GE Luhui YUE Guangyu LIU College of Electronic Engineering Chengdu University of Information TechnologyChengdu610225China Key Laboratory of Atmospheric Sounding of China Meteorological Administration Chengdu610225China National Meteorological Information Centre China Meteorological AdministrationBeijing100081China School of Computer and Software Nanjing University of Information Science&TechnologyNanjing210044China

High-resolution relative humidity(RH)data are essential in studies of climate change and in numerical meteorological ***,because high-resolution meteorological grid data require a large number of stations,the sparse distribution of ground meteorological stations in China before 2008 has limited the development of long-term and high-resolution RH products in the China Meteorological Administration’s Land Assimilation System(CLDAS)*** retrieve high-quality and high-resolution RH data before 2008,we propose a statistical downscaling model(SDM)based on a generative adversarial network(GAN)to transform the original RH data from a resolution of0.05°to 0.01°.The GAN-based SDM(GSDM)is trained with the RH of the CLDAS(0.05°)dataset after 2008 as its input,and the RH of the high-resolution CLDAS(HRCLDAS,0.01°)dataset after 2008 as its target for ***2-m air temperature data from the HRCLDAS dataset are also included in the input,and the station observations of RH are incorporated in the target for *** select the optimum data combination for the model,we compared three methods:(1)incorporating without auxiliary data(GSDM),(2)incorporating air temperature as an additional input(GSDM_T),and(3)incorporating air temperature as an additional input and the RH data at stations as an additional target for training(GSDM_TO).Taking the Beijing–Tianjin–Hebei region as an example,we trained the GSDM by using data from 2018 and tested the model performance in *** experimental results showed that the GSDM_TO algorithm achieved the lowest root-mean-square error(3.85%),followed by the GSDM_T(4.01%)and GSDM(4.95%)*** proposed models showed a competitive performance and captured more local details of the RH fields than other deep learning models and traditional bilinear *** general,the GSDM_TO algorithm using a combination of different sources of data(air temperature and observed RH)achieved the best results among the various d

关键词： relative humidity statistical downscaling generative adversarial network(GAN) temperature

来源：评论

学校读者我要写书评

暂无评论

Meter Location System Base on Jetson NX 1

引用

7th International Conference on Smart Computing and Communication, SmartCom 2022

作者： Yang, Chengjun zhou, Ling Yang, Ce Hechi University Guangxi Hechi China School of Computer Science and Engineering Hunan University of Science and Technology Hunan Xiangtan China Hunan Key Laboratory for Service computing and Novel Software Technology Xiangtan China

ISBN: (数字)9783031281242

ISBN: (纸本)9783031281235

Analog meter is still widely used due to their mechanical stability and electromagnetic impedance. Relying on humans to read mechanical meters in some industrial scenarios is time-consuming or dangerous, it is difficult for current meter reading robots to operate quickly and maintain high accuracy in edge computing devices. computer vision-based meter reading systems can solve such dilemmas. We designed an SSD network-based meter image acquisition system that can run in real time in an NVIDIA Jetson NX development board. Moreover, the model can quickly classify meter types and locate meter coordinates in the presence of light changes, complex backgrounds, and camera angle deflection. Tested on NVIDIA Jetson NX using TensorRT acceleration, the inference speed and accuracy reached 9.238 FPS and 53.95 mAP, respectively. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： computer vision

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：