检索结果-内蒙古大学图书馆

7th Asian Conference on Pattern Recognition, ACPR 2023

作者： Huang, Shenyuan Huang, Huaibo Wang, Zi Xu, Nan Zheng, Aihua He, Ran School of Computer Science and Technology Anhui University Hefei China Information Materials and Intelligent Sensing Laboratory of Anhui Province Hefei China Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Hefei China School of Artificial Intelligence Anhui University Hefei China NLPR CRIPAC CASIA Beijing China

ISBN: (纸本)9783031476365

Face forgery detection is becoming increasingly important in computer vision as facial manipulation technologies cause serious concerns. Recent works have resorted to the frequency domain to develop face forgery detectors and achieved better generalization achievements. However, there are still unignorable problems: a) the role of frequency is not always sufficiently effective and generalized to different forgery technologies;and b) the network trained on public datasets is unable to effectively quantify its uncertainty. To address the generalization issue, we design a Dynamic Dual-spectrum Interaction Network (DDIN) that allows test-time training with uncertainty guidance. RGB and frequency features are first interacted in multi-level by using a Frequency-guided Attention Module (FAM). Then these multi-modal features are merged with a Dynamic Fusion Module (DFM). Moreover, we further exploit uncertain perturbations as guidance during the test-time training phase. The network can dynamically fuse the features with quality discrepancies, thus improving the generalization of forgery detection. Comprehensive evaluations of several benchmark databases corroborate the superior generalization performance of DDIN. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

SIEDOB: Semantic Image Editing by Disentangling Object and Background

SIEDOB: Semantic Image Editing by Disentangling Object and B...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Wuyang Luo Su Yang Xinjian Zhang Weishan Zhang Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University School of Computer Science and Technology China University of Petroleum

Semantic image editing provides users with a flexible tool to modify a given image guided by a corresponding segmentation map. In this task, the features of the foreground objects and the backgrounds are quite different. However, all previous methods handle backgrounds and objects as a whole using a monolithic model. Consequently, they remain limited in processing content-rich images and suffer from generating unrealistic objects and texture-inconsistent backgrounds. To address this issue, we propose a novel paradigm, Semantic Image Editing by Disentangling Object and Background (SIEDOB), the core idea of which is to explicitly leverages several heterogeneous subnetworks for objects and backgrounds. First, SIEDOB disassembles the edited input into background regions and instance-level objects. Then, we feed them into the dedicated generators. Finally, all synthesized parts are embedded in their original locations and utilize a fusion network to obtain a harmonized result. Moreover, to produce high-quality edited images, we propose some innovative designs, including Semantic-Aware Self-Propagation Module, Boundary-Anchored Patch Discriminator, and Style-Diversity Object Generator, and integrate them into SIEDOB. We conduct extensive experiments on Cityscapes and ADE20K-Room datasets and exhibit that our method remarkably outperforms the baselines, especially in synthesizing realistic and diverse objects and texture-consistent backgrounds. Code is available at https://***/WuyangLuo/SIEDOB.

关键词：

来源：评论

学校读者我要写书评

暂无评论

H-Plane Radiation Pattern Decoupled Patch Antennas with Zero Edge-to-Edge Spacing Using Three-Pair Vias

H-Plane Radiation Pattern Decoupled Patch Antennas with Zero...

引用

2022 IEEE Region 10 International Conference, TENCON 2022

作者： Tong, Changwu Yang, Nan Leung, Kwok Wa Wu, Zehai Lu, Kai School of Electronics and Information Technology School of Microelectronics Sun Yat-Sen University Guangzhou China Guangdong Provincial Key Laboratory of Optoelectronic Information Processing Chips and Systems China State Key Laboratory of Terahertz and Millimeter Waves Department of Electronic Engineering City University of Hong Kong Hong Kong Guangdong Broadradio Communication Technology Co. Ltd China

ISBN: (数字)9781665450959

ISBN: (纸本)9781665450959

An H-plane radiation pattern decoupled patch antennas with zero edge-to-edge spacing is presented in this paper. When the two patches are placed together, a higher-order TM11 mode can be excited, and the mutual coupling between the two patch antennas is high with tilted radiation patterns. Therefore, three pairs of metallic vias are inserted into the interface to obtain a radiation pattern decoupling effect, namely a high isolation and boresight radiations simultaneously. To verify the idea, a prototype with zero edge-to-edge spacing is designed at 2.4-GHz WLAN band. Simulation results show that the proposed patch antennas have an isolation larger than 15 dB, whereas the radiation patterns also show symmetry and retain maximum radiation direction along z-axis. © 2022 IEEE.

关键词： Microstrip antennas

来源：评论

学校读者我要写书评

暂无评论

MFGB: Molecular Properties Prediction leveraging Self-supervised Morgan Fingerprint Representation Learning

MFGB: Molecular Properties Prediction leveraging Self-superv...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Shuyan Fang Yu Liu Song Liu School of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Provincial Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan University of Science and Technology Wuhan China Hubei Provincial Key Laboratory of Occupational Hazard Identification and Control Hubei Province Wuhan University of Science and Technology Wuhan China

Simple molecular graphs or molecular line notations are insufficient for molecular representation learning models that automatically learn molecule representations to acquire deep semantic features about chemistry. Therefore, we proposed the Morgan Fingerprint Graph, a novel molecular graph model constructed with the nodes of the Morgan Fingerprint Identifier, whose nodes incorporate various properties of the atom neighborhood. Based on our Morgan Fingerprint Graph, we trained a BERT-based molecular representation model MFGB which employs a local rather than global attention module to adapt the model to the Morgan Fingerprint Graph. The attention module of MFGB regulates the exchange of information in the attention layer based on the connection information of the atoms in the molecules. To verify the effectiveness of MFGB, we selected several mainstream datasets for evaluation. The results demonstrated that our method improve the performance of molecular properties prediction. In addition, we analyzed MFGB from both the over-smoothing and the attention perspectives. The analysis indicates that the node vector representations learned from the Morgan Fingerprint Graph are generally less smoothing, and the attention distributions of MFGB match the partial charge density distribution of the molecules.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning to Learn Transferable Generative Attack for Person Re-Identification

引用

IEEE Transactions on Image processing 2025年 PP卷 PP页

作者： Bian, Yuan Liu, Min Wang, Xueping Ma, Yunfeng Wang, Yaonan Hunan University National Engineering Research Center of Robot Visual Perception and Control Technology College of Electrical and Information Engineering Hunan Changsha China Hunan Normal University Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing College of Information Science and Engineering Hunan Changsha China

Deep learning-based person re-identification (reid) models are widely employed in surveillance systems and inevitably inherit the vulnerability of deep networks to adversarial attacks. Existing attacks merely consider cross-dataset and cross-model transferability, ignoring the cross-test capability to perturb models trained in different domains. To powerfully examine the robustness of real-world re-id models, the Meta Transferable Generative Attack (MTGA) method is proposed, which adopts meta-learning optimization to promote the generative attacker producing highly transferable adversarial examples by learning comprehensively simulated transfer-based crossmodel&dataset&test black-box meta attack tasks. Specifically, cross-model&dataset black-box attack tasks are first mimicked by selecting different re-id models and datasets for meta-train and meta-test attack processes. As different models may focus on different feature regions, the Perturbation Random Erasing module is further devised to prevent the attacker from learning to only corrupt model-specific features. To boost the attacker learning to possess cross-test transferability, the Normalization Mix strategy is introduced to imitate diverse feature embedding spaces by mixing multi-domain statistics of target models. Extensive experiments show the superiority of MTGA, especially in cross-model&dataset and cross-model&dataset&test attacks, our MTGA outperforms the SOTA methods by 20.0% and 11.3% on mean mAP drop rate, respectively. © 1992-2012 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Improving Global Precipitation in Numerical Weather Prediction Systems based on Deep Learning Techniques

Improving Global Precipitation in Numerical Weather Predicti...

引用

IEEE International Conference on High Performance Computing and Communications (HPCC)

作者： Haixiang Zhao Guojing Zhang Ming Du Xiaoying Wang Department of Computer Technology and Applications Qinghai University Xining China Geospatial Information Technology and Application Qinghai Provincial Key Laboratory Xining China

Accurate weather forecasts are crucial for many aspects of people's lives. Traditional short-term precipitation forecasting methods mainly rely on numerical weather predictions based on meteorological dynamics modelling. However, numerical weather predictions based on high-resolution physical models require hours of computation on supercomputers. Deep learning networks possess strong feature extraction capabilities, directly mapping images, meteorological data, and other information to high-dimensional feature spaces. Neurons extract abstract features, enabling continuous training and learning for predictions. Therefore, deep learning provides a new solution for short-term precipitation forecasting. In the past, deep learning has been used for precipitation forecasting by employing radar echo extension methods; however, these methods are limited to short-term forecasts and do not utilize other meteorological data, resulting in inaccurate predictions. This study proposes a model containing an attention mechanism, a convolutional extended short-term neural network (Att-PredRNN), based on 5.625° (32×64 grid points) resolution ECMWF reanalysis data and three years of global meteorological and daily precipitation data. The network uses multiple meteorological fields as input factors to predict spatial precipitation distribution for 24-hour precipitation forecasting. The model significantly improves the capture of spatial and temporal correlations through the attention matrices focusing on different parts of the input sequence. Experimental results show that the proposed Att-PredRNN model outperforms other comparison models in terms of RMSE, CSI, POD, and FAR overall and dramatically enhances the accuracy of short-term precipitation forecasts. Our code and data are publicly available.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Incomplete multi-view clustering via local and global co-regularization

引用

Science China(information Sciences) 2022年第5期65卷 96-111页

作者： Jiye LIANG Xiaolin LIU Liang BAI Fuyuan CAO Dianhui WANG Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education School of Computer and Information Technology Shanxi University Artificial Intelligence Research Institute China University of Mining and Technology Department of Computer Science and Computer Engineering La Trobe University

The incompleteness of multi-view data is a phenomenon associated with real-world data mining applications, which brings a huge challenge for multi-view clustering. Although various types of clustering methods, which try to obtain a complete and consensus clustering result from a latent subspace, have been developed to overcome this problem, most methods excessively rely on views-public instances to bridge the connection with view-private instances. When lacking sufficient views-public instances, existing methods fail to transmit the information among incomplete views effectively. To overcome this limitation, we propose an incomplete multi-view clustering algorithm via local and global co-regularization(IMVC-LG). In this algorithm, we define a new objective function that is composed of two terms: local clustering from each view and global clustering from multiple views, which constrain each other to exploit the local clustering information from different incomplete views and determine a global consensus clustering result, ***, an iterative optimization method is proposed to minimize the objective function. Finally, we compare the proposed algorithm with other state-of-the-art incomplete multi-view clustering methods on several benchmark datasets to illustrate its effectiveness.

关键词： incompleteness multi-view clustering local clustering global clustering co-regularization

来源：评论

学校读者我要写书评

暂无评论

Using Rough Sets to Improve the High-dimensional Data Anomaly Detection Method Based on Extended Isolation Forest 26

Using Rough Sets to Improve the High-dimensional Data Anomal...

引用

26th International Conference on computer Supported Cooperative Work in Design, CSCWD 2023

作者： Liu, Hanlin Zhou, Jiantao Li, Hua Inner Mongolia University College of Computer Science Hohhot China Natl. Loc. Jt. Eng. Research Center of Intelligent Information Processing Technology for Mongolian Engineering Research Center of Ecological Big Data Ministry of Education Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software Inner Mongolia Key Laboratory of Social Computing and Data Processing Inner Mongolia Key Laboratory of Discipline Inspection and Supervision Big Data Inner Mongolia Engineering Laboratory for Big Data Analysis Technology Hohhot China

ISBN: (纸本)9798350331684

Anomaly detection refers to the identification of data objects that deviate from the general data distribution. One of the important challenges in anomaly detection is handling high-dimensional data, especially when it contains a large number of redundant attributes. Although traditional Isolation Forest (iForest) and Extended Isolation Forest (EIF) have performed well in anomaly detection, the detection accuracy is still extremely influenced by redundant attributes. In this paper, we propose a two-tier architecture named RS-EIF, to alleviate the negative impact of redundant attributes. Specifically, the RS-EIF combines the rough set theory and EIF algorithm and provides an effective basis for the EIF-based anomaly detection method by removing redundant attributes with rough set theory. Experimental results show that the RS-EIF algorithm performs better than the iForest and EIF algorithms in terms of anomaly detection rate, and the results of the combination of rough set theory and EIF are more prominent compared to the other combination methods. © 2023 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Efficient survivable mapping algorithm for logical topology in IP-over-WDM optical networks against node failure

引用

Journal of Supercomputing 2023年第5期79卷 5037-5063页

作者： Cheng, Dun-Wei Chang, Jo-Yi Lin, Chen-Yen Lin, Limei Huang, Yanze Thulasiraman, Krishnaiyan Hsieh, Sun-Yuan Department of Computer Science and Information Engineering National Yunlin University of Science and Technology 123 University Road Yunlin64002 Taiwan Department of Computer Science and Information Engineering National Cheng Kung University No. 1 University Road Tainan701 Taiwan College of Mathematics and Informatics and the Key Laboratory of Network Security and Cryptology Fujian Normal University Fujian Fuzhou350117 China Fujian Provincial Key Laboratory of Big Data Mining and Applications School of Mathematics and Physics Fujian University of Technology Fujian Fuzhou350118 China Department of Computer Science University of Oklahoma 660 Parrington Oval NormanOK73019 United States Department of Computer Science and Information Engineering National Chi Nan University No. 1 Daxue Rd Nantou County Puli Township54561 Taiwan

The survivable mapping problem in an IP-over-WDM network with a logical graph and physical graph is the problem of finding a mapping of a logical network in a physical layer so that any failure in physical topology does not break the logical topology’s connection. Determining whether a survivable mapping against failure exists is an NP-complete problem, and therefore many heuristic algorithms have been proposed in the literature. In this paper, a heuristic mapping design strategy is proposed to enable the lightpaths to more efficiently endure a node failure. We individually consider the logical topology by building a Hamiltonian cycle and then deal with the mapping problem for disjoint physical paths. Experimental results demonstrate that the proposed algorithm can provide efficient survivable mapping in IP-over-WDM networks. The simulation shows that the survivability of previous methods (SNF and SMART-Node) is around 60–80%, but our proposed algorithm can build survivable mapping in all kinds of situations. © 2022, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

A Genuine-Equilibrium Monte Carlo Sampling-Based Effective Algorithm for Fully-Connected Ising Models

A Genuine-Equilibrium Monte Carlo Sampling-Based Effective A...

引用

IEEE International Conference on Integrated Circuits, Technologies and Applications (ICTA)

作者： Xiangrui Wang Dong Jiang Yang Zhang Hongyuan Kang Enyi Yao School of Microelectronics South China University of Technology Guangzhou China Guangdong Provincial Key Laboratory of Optoelectronic Information Processing Chips and Systems Guangzhou China

Ising machines have emerged as a potential technique for hardware acceleration in solving combinatorial optimization problems. However, an effective and hardware-implementation-friendly algorithm is still required to further enhance the fully-connected Ising machine's performance. Parallel momentum-tempering (PMT) algorithm is proposed in this paper, incorporating the full parallel updating capability of momentum annealing (MA) with the global exploration in the solution space provided by parallel tempering (PT). PMT exhibits an excellent performance, and a PMT with 8 replicas surpasses MA on the WK2000 max-cut benchmark, achieving a considerable 80%(1k/6k) reduction in required iteration steps while obtaining a mean cut value of 33,160. Besides, PMT is well-matched for hardware implementation versus MA, benefiting from invariant parameters in each replica.

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：