检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Wu, Chenxu Kong, Qingpeng Jiang, Zihang Kevin Zhou, S. School of Biomedical Engineering Division of Life Sciences and Medicine USTC China MIRACLE Center Suzhou Institute for Advance Research USTC China State Key Laboratory of Precision and Intelligent Chemistry USTC China Key Laboratory of Intelligent Information Processing of CAS Institute of Computing Technology CAS China

Magnetic Resonance Imaging (MRI), including diffusion MRI (dMRI), serves as a "microscope" for anatomical structures and routinely mitigates the influence of low signal-to-noise ratio scans by compromising temporal or spatial resolution. However, these compromises fail to meet clinical demands for both efficiency and precision. Consequently, denoising is a vital preprocessing step, particularly for dMRI, where clean data is unavailable. In this paper, we introduce Di-Fusion, a fully self-supervised denoising method that leverages the latter diffusion steps and an adaptive sampling process. Unlike previous approaches, our single-stage framework achieves efficient and stable training without extra noise model training and offers adaptive and controllable results in the sampling process. Our thorough experiments on real and simulated data demonstrate that Di-Fusion achieves state-of-the-art performance in microstructure modeling, tractography tracking, and other downstream tasks. Code is available at https://***/FouierL/Di-Fusion. Copyright © 2025, The Authors. All rights reserved.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Distributed Signal Detection with Multi-shot Weighted Combining

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Pan, Xuesong Zheng, Zhong Liu, Chang Fei, Zesong Beijing Institute of Technology School of Information and Electronics Beijing100081 China Beijing Institute of Technology School of Information and Electronics The Natl. Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing100081 China Guangdong University of Technology School of Information Engineering Guangzhou510006 China

Recently, the distributed multiple-input multiple-output (MIMO) systems have been widely investigated, where several physically separated access points (APs) connect to a central processing unit (CPU) via fronthaul links to realize joint signal processing. Although appreciable spatial degrees of freedom can be exploited, the huge interaction overhead between APs and CPU is inevitable and prevents this architecture from being practically implemented. To achieve high signal detection accuracy while reducing interaction overhead, we propose a distributed signal detection scheme with multi-shot weighted combining, where the detected signals are iteratively refined via AP detections and subsequent CPU combining. Specifically, the regularized detection is carried out at the APs by penalizing any discrepancies between the local least-square detected signals at the AP and the weighted combined signals fed back from the CPU. The regularized detections are then collected and combined at the CPU for a refined joint detection. Using the operator-valued free probability theory, the combining weights at the CPU only depend on the statistical channel state information between APs and UEs, which alleviates the interaction overhead of fronthaul links. Numerical results demonstrate that the proposed distributed detection with multi-shot combining scheme rapidly converges and achieves improved detection accuracy compared to the detection schemes with one-shot combining. © 1967-2012 IEEE.

关键词： Communication channels (information theory)

来源：评论

学校读者我要写书评

暂无评论

CLIMS++: Cross Language Image Matching with Automatic Context Discovery for Weakly Supervised Semantic Segmentation

引用

International Journal of Computer Vision 2025年 1-20页

作者： Xie, Jinheng Deng, Songhe Hou, Xianxu Luo, Zhaochuan Shen, Linlin Huang, Yawen Zheng, Yefeng Shou, Mike Zheng Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Department of Computer Science Wenzhou-Kean University Wenzhou325060 China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China Show Lab National University of Singapore Singapore639798 Singapore School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University Suzhou215400 China Jarvis Research Center Tencent YouTu Lab Shenzhen518703 China

While promising results have been achieved in weakly-supervised semantic segmentation (WSSS), limited supervision from image-level tags inevitably induces discriminative reliance and spurious relations between target classes and background regions. Thus, Class Activation Map (CAM) usually tends to activate discriminative object regions and falsely includes lots of class-related backgrounds. Without pixel-level supervisions, it could be very difficult to enlarge the foreground activation and suppress those false activation of background regions. In this paper, we propose a novel framework of Cross Language Image Matching with Automatic Context Discovery (CLIMS++), based on the recently introduced Contrastive Language-Image Pre-training (CLIP) model, for WSSS. The core idea of our framework is to introduce natural language supervision to activate more complete object regions and suppress class-related background regions in CAM. In particular, we design object, background region, and text label matching losses to guide the model to excite more reasonable object regions of each category. In addition, we propose to automatically find spurious relations between foreground categories and backgrounds, through which a background suppression loss is designed to suppress the activation of class-related backgrounds. The above designs enable the proposed CLIMS++ to generate a more complete and compact activation map for the target objects. Extensive experiments on PASCAL VOC 2012 and MS COCO 2014 datasets show that our CLIMS++ significantly outperforms the previous state-of-the-art methods. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

The Enhancing Effect of the East Asian Subtropical Westerly Jet on Summer Extreme High-Temperature Events over Central-Eastern China Since the Late 1990s

引用

Advances in Atmospheric Sciences 2025年第3期42卷 453-466页

作者： Chujie GAO Yuyu NIU Gen LI Shanlei SUN Bo LU Chaofan LI Bei XU Jinglong HUANG Xiubao SUN College of Oceanography&Key Laboratory of Marine Hazards Forecasting Ministry of Natural ResourcesHohai UniversityNanjing 210098China Key Laboratory of Meteorological Disaster Ministry of Education(KLME)&Collaborative Innovation Center on Forecast and Evaluation of Meteorological Disasters(CIC-FEMD)Nanjing University of Information Science and TechnologyNanjing 210044China State Key Laboratory of Tropical Oceanography South China Sea Institute of OceanologyChinese Academy of SciencesGuangzhou 510301China Laboratory for Climate Studies and CMA-NJU Joint Laboratory for Climate Prediction Studies National Climate CenterChina Meteorological AdministrationBeijing 100081China Xiong’an Institute of Meteorological Artificial Intellegence Xiong'an 071708China Center for Monsoon System Research Institute of Atmospheric PhysicsChinese Academy of SciencesBeijing 100029China College of Earth and Planetary Sciences University of the Chinese Academy of SciencesBeijing 100049China College of Intelligent Science and Control Engineering Jinling Institute of TechnologyNanjing 211169China

The increase in frequency and intensity of Extreme High-temperature Events(EHEs)over Central-Eastern China(CEC)in recent decades has severely impacted social development and *** observation and reanalysis datasets,this study explores the effect of the East Asian subtropical westerly jet stream(EAJ)on the CEC EHEs for the summers spanning 1979–*** its general relative location to the right side of the upper-level jet stream exit region,CEC would theoretically suffer more EHEs with a stronger and northwardly-shifted EAJ in summer due to the likelihood of abnormal subsidence induced by the ***,such an EAJ–EHE connection has been unstable over the past four decades but has displayed an evident interdecadal *** the late 1990s,the interannual variation of the EAJ was manifested mainly by its meridional displacement in the northeastern part of East Asia;thus,the atmospheric responses were essentially located to the east of CEC,exerting less of an influence on the CEC ***,since the late 1990s,the EAJ variation has featured an intensity change in its center over the northwest portion of the CEC,which has resulted in a westward shift in atmospheric responses to cover the CEC ***,the EAJ could potentially affect the summer CEC EHEs during 2000–*** findings offer support for an in-depth understanding of the formation mechanisms of extreme weather/climate events of this nature and thus provide a scientific reference for seasonal climate predictions.

关键词： summer extreme high-temperature events East Asian subtropical jet atmospheric circulation central-eastern China interdecadal change

来源：评论

学校读者我要写书评

暂无评论

Robust Deep Matrix Factorization with Low-rank and Hypergraph Learning for Multi-view Data processing

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Pan, Baicheng Che, Hangjun Li, Chenglu Li, Hongfei Southwest University College of Electronic and Information Engineering Chongqing400715 China Hong Kong Baptist University Department of Mathematics Kowloon Tong Hong Kong Southwest University Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing Chongqing400715 China

As the advancement of sensing technology and cyber-physical equipment, the complexity and dimensionality of the data from consumer internet of things have increased dramatically. processing the complex and multi-view data to analyze the consumption characteristics becomes a significant issue. Deep matrix factorization (DMF) is a widely spread method with the ability to learn intrinsic components in data based on its multiple-layers structures. However, the multiple-layers structures may magnify noises in data and the standard DMF cannot reflect the manifold and low-rank structures on the coefficient matrix well. In the paper, a robust deep matrix factorization with low-rank and hypergraph learning (RDMFLRH) model is proposed for multi-view data processing. Firstly, an arc tangent loss function with less sensitivity to noises and outlines is introduced to enhance robustness. Additionally, low-rank and hypergraph learning are adopted to extract the relationships between clusters and maintain the binary manifold structures from the original space. Then, an optimization algorithm based on the multiplicative update rule is developed to solve the proposed model with convergence proven theoretically and experimentally. Finally, abundant experiments on real-world and noisy datasets validate the superiority of the proposed method, improving around 1% to 10% performance compared with the comparison state-of-the-art methods. © 1975-2011 IEEE.

关键词： Matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Secure Communication Against Active UAV Eavesdropper: A Fingerprint-Localization and Channel Tracking Approach

引用

IEEE Transactions on Communications 2025年

作者： Wang, Xinyao Zheng, Zhong Fei, Zesong Wu, Qingqing Beijing Institute of Technology School of Information and Electronics Beijing100081 China National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing100081 China Shanghai Jiao Tong University Department of Electronic Engineering Shanghai200240 China

Unmanned aerial vehicle (UAV) can be threatening to the information security of wireless communications. By launching the pilot spoofing attack (PSA), a UAV, operating as the active aerial-eavesdropper (A-Eve), is able to intercept the confidential messages sent over the air. On one hand, it is difficult to distinguish the channel state information (CSI) of the ground users (GUs) and the CSI of A-Eve in the contaminated pilots. On the other hand, due to the high-mobility of A-Eve, the CSI of A-Eve is rapidly changing, making the design of secure transmissions challenging. To address these issues, we first propose a location-based minimum mean square error (MMSE) channel estimation algorithm to separate the CSI of GUs and the CSI of A-Eve, where the location of A-Eve is obtained by designing a cooperative localization neural network (CLNet), leveraging its angular-domain channel fingerprint (CF) of A-Eve. Furthermore, we propose an artificial noise (AN) injected MMSE precoding scheme to maximize the worst-case secrecy rate of the multi-user communications, where the power allocation between signal and AN is optimized via a long short-term memory (LSTM)-based secure predictive beamforming neural network (SPBNet). Numerical results verify the secrecy performance gain of the proposed scheme achieved by utilizing the localization ability via the CLNet and the channel tracking ability via the SPBNet, compared to the canonical nullspace AN injection scheme without prior knowledge of A-Eve’s location. © 2025 IEEE. All rights reserved.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Anomize: Better Open Vocabulary Video Anomaly Detection

arXiv

引用

arXiv 2025年

作者： Li, Fei Liu, Wenxuan Chen, Jingjing Zhang, Ruixu Wang, Yuran Zhong, Xian Wang, Zheng National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University China Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China State Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China Hubei Key Laboratory of Transportation Internet of Things Wuhan University of Technology China

Open Vocabulary Video Anomaly Detection (OVVAD) seeks to detect and classify both base and novel anomalies. However, existing methods face two specific challenges related to novel anomalies. The first challenge is detection ambiguity, where the model struggles to assign accurate anomaly scores to unfamiliar anomalies. The second challenge is categorization confusion, where novel anomalies are often misclassified as visually similar base instances. To address these challenges, we explore supplementary information from multiple sources to mitigate detection ambiguity by leveraging multiple levels of visual data alongside matching textual information. Furthermore, we propose incorporating label relations to guide the encoding of new labels, thereby improving alignment between novel videos and their corresponding labels, which helps reduce categorization confusion. The resulting Anomize framework effectively tackles these issues, achieving superior performance on UCF-CRIME and XD-VIOLENCE datasets, demonstrating its effectiveness in OVVAD. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MoME: Mixture of Multi-Domain Experts for Multivariate Long-Term Series Forecasting

MoME: Mixture of Multi-Domain Experts for Multivariate Long-...

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Xinyu Li Zhiheng Yang Hao Xu Yunqi Cai Hong Lu Xin Wang Jin Zhao Fenglin Qi Jiajie Shen School of Computer Science Fudan University Shanghai China Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai China Informatization Office Fudan University Shanghai China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Time series forecasting is always important, with multivariate long-term series forecasting being its most challenging task. Here, the existing methods typically learn only in a single domain and focus on optimizing model structures, leading to incomplete information mining and imprecise predictions. To address this, we propose a generalized Mixture of Multi-Domain Experts (MoME) for multivariate long-term series forecasting. Unlike most existing methods, MoME focuses on multi-perspective information mining and fusing. To this end, MoME transforms time series into the frequency and spatial domains to learn their respective representations. MoME regards variates information as embedded features and applies fast Fourier transform to the time dimension. Then it learns embedded features in the frequency domain. In spatial domain learning, MoME applies self-attention mechanism on the variates dimension to efficiently capture dependencies among multiple variates. Finally, MoME fuses the outputs from all domains, reinterprets and integrates information across multiple domains, and predicts future time series. Extensive experiments prove that MoME outperforms state-of-the-art (SOTA) methods. Code is available at: https://***/lxy-PhD2022/MoME

关键词： Time-frequency analysis Fuses Time series analysis Transforms Signal processing Predictive models Frequency conversion Forecasting Speech processing Periodic structures

来源：评论

学校读者我要写书评

暂无评论

An End-to-End Autoencoder-based Probabilistic Shaping Method for Optical Communication 7

An End-to-End Autoencoder-based Probabilistic Shaping Method...

引用

7th Optics Young Scientist Summit, OYSS 2024

作者： Teng, Ziqiang Guo, Dong Gao, Ran Kong, Leyi Han, Wentao Chang, Huan Li, Zhipei Xin, Xiangjun School of Information and Electronics Beijing Institute of Technology 5 Zhongguancun South Street Haidian District Beijing100081 China National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing Institute of Technology 5 Zhongguancun South Street Haidian District Beijing100081 China Institute of Science and Technology Research Beijing Institute of Technology 5 Zhongguancun South Street Haidian District Beijing100081 China

ISBN: (数字)9781510688377

ISBN: (纸本)9781510688360

The advent of services such as big data and cloud computing has driven a continuous increase in the required transmission rate and capacity of optical fiber communication systems, which now support over 90% of global data traffic. Probability shaping (PS), which adjusts the probability distribution of constellation points, enhances both data transmission rates and the resilience of signals to channel nonlinearity. However, traditional PS methods, such as those using constant composition distribution matching (CCDM), cannot dynamically adjust the probability distribution of constellation points based on channel conditions. To address this limitation, we propose an end-to-end Autoencoder (AE)-based PS technique for optical communication. Simulation results show that compared to traditional 16/64/256QAM, this scheme achieves a maximum improvement of 0.356 bit/symbol in mutual information over the AWGN channel. In the optical fiber channel, under varying signal power and fiber length conditions, the mutual information is improved in different degrees and the influence of channel nonlinearity on the signal is reduced. Innovatively, residual connections are added to the decoder to enhance the model's generalization performance, enabling a deeper network structure and improving its ability to handle complex optical fiber channels. © 2025 SPIE.

关键词： Optical fiber communication

来源：评论

学校读者我要写书评

暂无评论

High-precision end-to-end adaptive optics aided orbital angular momentum wireless communication with XFTC-Net

引用

Optics Letters 2025年第10期50卷 3265-3268页

作者： Panpan Xu Huan Chang Fei Wang Ran Gao Dong Guo Lei Zhu Zhipei Li Sitong Zhou Qi Xu Jing Chen Xiangjun Xin School of Information and Electronics Beijing Institute of Technology (BIT) Beijing 100081 China National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing China School of Electronic Engineering Beijing University of Posts and Telecommunications (BUPT) Beijing 100876 China Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology 250353 China

In this Letter, we demonstrate high-precision end-to-end adaptive optics (AO) technique based on the X-Shape Fusion Transformer-convolutional neural network (XFTC-Net) without an additional probe path to compensate for distortions caused by atmospheric turbulence (AT) in orbital angular momentum (OAM) optical wireless communication links. The experimental results show that the XFTC-Net effectively extracts the intensity distribution features of distorted OAM beams, predicting AT phase screens and identifying OAM modes. After XFTC-Net-aided AO compensation, the bit error rate of the OAM optical communication system remains below 3.8 × 10 −3 , staying within $C_{n}^2=1 \times 10^{-15}$ –1 × 10 −13 m −2/3 . Moreover, the optical power with l = 3 increases from 5.08 dBm to 8.23 dBm at a transmission distance of 800 m. These experimental results indicate that the proposed XFTC-Net AO technique effectively compensates for OAM beam distortion in both single- and multiplexed-channel OAM links, which effectively balances the system complexity and transmission performance of OAM-based free space optical (FSO) communication systems, opening up new avenues for enhancing the performances of high-capacity optical communication.

关键词： Adaptive optics Bit error rate Neural networks Optical wireless communication Polarization division multiplexing Space division multiplexing

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：