检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Jiang, Kaixun Chen, Zhaoyu Fu, Jiyuan Hong, Lingyi Li, Jinglun Zhang, Wenqiang Shanghai Engineering Research Center of AI Robotics Academy for Engineering & Technology Fudan University Shanghai China Engineering Research Center of AI & Robotics Ministry of Education Academy for Engineering & Technology Fudan University Shanghai China Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China

—Recent work indicates that video recognition models are vulnerable to adversarial examples, posing a serious security risk to downstream applications. However, current research has primarily focused on adversarial attacks, with limited work exploring defense mechanisms. Furthermore, due to the spatial-temporal complexity of videos, existing video defense methods face issues of high cost, overfitting, and limited defense performance. Recently, diffusion-based adversarial purification methods have achieved robust defense performance in the image domain. However, due to the additional temporal dimension in videos, directly applying these diffusion-based adversarial purification methods to the video domain suffers performance and efficiency degradation. To achieve an efficient and effective video adversarial defense method, we propose the first diffusion-based video purification framework to improve video recognition models’ adversarial robustness: VideoPure. Given an adversarial example, we first employ temporal DDIM inversion to transform the input distribution into a temporally consistent and trajectory-defined distribution, covering adversarial noise while preserving more video structure. Then, during DDIM denoising, we leverage intermediate results at each denoising step and conduct guided spatial-temporal optimization, removing adversarial noise while maintaining temporal consistency. Finally, we input the list of optimized intermediate results into the video recognition model for multi-step voting to obtain the predicted class. We investigate the defense performance of our method against state-of-the-art black-box, gray-box, and adaptive attacks on benchmark datasets and models. Compared with other adversarial purification methods, our method overall demonstrates better defense performance against different attacks. Moreover, our method can be applied as a flexible defense plugin for video recognition models. Our code is available at https://***/deep-kaix

关键词： HTTP

来源：评论

学校读者我要写书评

暂无评论

A spectrum-enhanced attention model for semantic segmentation of remote sensing images

A spectrum-enhanced attention model for semantic segmentatio...

引用

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

作者： Xin Li Feng Xu Feifei Tao Yao Tong Xin Lyu Jianyi Zhong André Kaup College of Computer Science and Software Engineering Hohai University Nanjing China Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing China School of Computer Engineering Jiangsu Ocean University Lianyungang China School of Artificial Intelligence and Information Technology Nanjing University of Chinese Medicine Nanjing China Chair of Multimedia Communications and Signal Processing Friedrich-Alexander University Erlangen-Nuremberg Erlangen Germany

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Semantic segmentation of remote sensing images (RSIs) is essential for applications such as environmental monitoring, urban planning, and disaster management. Convolutional Neural Networks (CNNs) and their variants struggle to capture comprehensive spectral context for learning discriminative representations. In this paper, we propose a Spectrum-Enhanced Network (SPENet) that leverages the Frequency Transformer Block (FTB) to capture rich spectral context. FTB integrates Spectrum-Enhanced Attention (SEA) with Multi-Head Frequency Self-Attention (MH-FSA), incorporating more informative contextual cues. Specifically, SEA aggregates spectral statistics through covariance matrix normalization before applying channel-wise attention. By projecting feature maps onto the frequency domain, MH-FSA provides the network with a broader context, extending beyond the low-frequency focus of standard self-attention mechanisms. Extensive experiments on the ISPRS Potsdam and LoveDA datasets show that SPENet significantly outperforms state-of-the-art methods. Besides, the proposed SEA module notably rises average F1-score/overall accuracy/mean insert over union wiht more than 2.5/2.6%/2.3%, as demonstrated by ablation study.

关键词： Semantic segmentation Frequency-domain analysis Urban planning Semantics Speech enhancement Signal processing Transformers Sensors Remote sensing Standards

来源：评论

学校读者我要写书评

暂无评论

Charging Out Rectangle: Quadrangle IoU for Scene Text Detection under Balanced Supervision 25

Charging Out Rectangle: Quadrangle IoU for Scene Text Detect...

引用

Proceedings of the 4th International Conference on computer, Artificial Intelligence and Control Engineering

作者： Min Ma Xiangnan Zhang Wang Bin Qiuli Wang Kexing Che School of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing Jiangsu China Key Laboratory of Intelligent Information Processing Corporation Key Laboratory of Aperture Array and Space Application The 38th Research Institute of China Electronics Technology Group Hefei Anhui China Government and Enterprise Division China Unicom Shandong Branch Jinan Shandong China School of Electronic Engineering Xidian University Xi' an Shaanxi China

ISBN: (纸本)9798400712647

In the past few years, text detection approaches have been able to cope with more and more challenging complex scenes. In this field, the arbitrary shape and various scale of text instances are the two most frequently mentioned topics. Among the existing methods, the bounding box prediction methods based on Intersection over Union (IoU) are efficient, but can only handle multi-oriented rectangles. Although arbitrary shape text detection methods have been proposed, these methods are often aimed at curved text. Besides, the post-processing is usually cumbersome. Considering that the affine transformation phenomenon caused by out-plane rotation is more frequent than curved text in real scenario, we design a quadrangle IoU (QIoU) loss to efficiently predict arbitrary convex quadrangle text. Furthermore, we analyze the challenge of variable scale in text detection from the perspective of unbalanced supervision information, and propose a cross-scale knowledge distillation (CSKD) method to improve the detection accuracy of large-scale text. An extensive ablation study demonstrates the effectiveness and superiority of the proposed strategies. During inferring, our method does not consume extra time. Using the basic feature pyramid network for feature extraction, our method achieves state-of-the-art results on several popular datasets for scene text detection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An RTDNN-Based Hybrid Precoding and Combining Joint Optimization Algorithm for MUPC-MIMO Systems

IEEE Transactions on Green Communications and Networking

引用

IEEE Transactions on Green Communications and Networking 2025年

作者： Liu, Fulai Liu, Yubiao Yang, Xianghuan Duan, Zhuoyao Shi, Baozhu Ji, Li Du, Ruiyan Northeastern University at Qinhuangdao Lab of Key Technology of Millimeter-wave Large-scale MIMO System Hebei Key Laboratory of Marine Perception Network and Data Processing Qinhuangdao066004 China Hebei University College of Mathematics and Information Science Baoding071002 China Northeastern University School of Computer Science and Engineering Shenyang110819 China Qinhuangdao Vocational and Technical College Qinhuangdao066100 China School of Computer Science and Engineering Northeastern University Shenyang110004 China

To achieve a satisfactory balance between energy efficiency (EE) and spectral efficiency (SE) for hybrid precoding and combining (HPC), this paper presents a two-stage joint optimization HPC algorithm based on residual deep neural network (DNN) for multi-user partially connected (MUPC) structure, namely RTDNN algorithm. In the proposed algorithm, a two-stage framework is designed to optimize analog and digital coders at the transmitter and receiver simultaneously, which can effectively preserve coupling relationship of coders between the transmitter and receiver. Specially, the RTDNN architecture is mainly divided into two stage networks, which includes analog stage and digital stage networks. The analog stage network is developed to obtain the optimal analog precoder and combiner simultaneously. On this basis, the digital stage network is constructed to solve the digital precoder and combiner concurrently. To further improve the prediction accuracy of RTDNN-based HPC, residual modules are adopted into the developed two stage networks. Moreover, the proposed RTDNN is trained with unsupervised learning. Simulation results show that the EE of the proposed algorithm is at least enhanced by 0.6 bits/Hz/J with satisfactory SE than other methods. © 2017 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Unmanned aerial vehicle based multi-person detection via deep neural network models

引用

Frontiers in Neurorobotics 2025年 19卷 1582995页

作者： Alshehri, Mohammed Zahoor, Laiba AlQahtani, Yahya Alshahrani, Abdulmonem AlHammadi, Dina Abdulaziz Jalal, Ahmad Liu, Hui Department of Computer Science King Khalid University Abha Saudi Arabia Faculty of Computer Science Air University Islamabad Pakistan Department of Informatics and Computer Systems King Khalid University Abha Saudi Arabia Department of Information Systems College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University Riyadh Saudi Arabia Department of Computer Science and Engineering College of Informatics Korea University Seoul Korea Republic of Cognitive Systems Lab University of Bremen Bremen Germany Guodian Nanjing Automation Company Ltd. Nanjing China Jiangsu Key Laboratory of Intelligent Medical Image Computing School of Future Technology Nanjing University of Information Science and Technology Nanjing China

Introduction: Understanding human actions in complex environments is crucial for advancing applications in areas such as surveillance, robotics, and autonomous systems. Identifying actions from UAV-recorded videos becomes more challenging as the task presents unique challenges, including motion blur, dynamic background, lighting variations, and varying viewpoints. The presented work develops a deep learning system that recognizes multi-person behaviors from data gathered by UAVs. The proposed system provides higher recognition accuracy while maintaining robustness along with dynamic environmental adaptability through the integration of different features and neural network models. The study supports the wider development of neural network systems utilized in complicated contexts while creating intelligent UAV applications utilizing neural networks. Method: The proposed study uses deep learning and feature extraction approaches to create a novel method to recognize various actions in UAV-recorded video. The proposed model improves identification capacities and system robustness by addressing motion dynamic problems and intricate environmental constraints, encouraging advancements in UAV-based neural network systems. Results: We proposed a deep learning-based framework with feature extraction approaches that may effectively increase the accuracy and robustness of multi-person action recognition in the challenging scenarios. Compared to the existing approaches, our system achieved 91.50% on MOD20 dataset and 89.71% on Okutama-Action. These results do, in fact, show how useful neural network-based methods are for managing the limitations of UAV-based application. Discussion: Results how that the proposed framework is indeed effective at multi-person action recognition under difficult UAV conditions. Copyright © 2025 Alshehri, Zahoor, AlQahtani, Alshahrani, AlHammadi, Jalal and Liu.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

A parallel ant colonies approach to de novo prediction of protein backbone in CASP8/9

引用

Science China(information Sciences) 2013年第10期56卷 226-238页

作者： LV Qiang WU HongJie WU JinZhen HUANG Xu LUO XiaoHu QIAN PeiDe School of Computer Science and Technology Soochow University Jiangsu Provincial Key Lab for Information Processing Technologies School of Electronic and Information Engineering Suzhou University of Science and Technology

Predicting the three-dimensional structure of proteins from amino acid sequences with only a few remote homologs,or de novo prediction,remains a major challenge in computational *** modeling of the protein backbone represents the initial phase of a protein structure prediction *** a parallel ant colony optimization based on sharing one pheromone matrix,this report proposes a parallel approach to predict the structure of a protein *** parallel approach combines various sources of energy functions and generates protein backbones with the lowest energies jointly determined by the various energy *** free modeling targets in CASP8/9 are used to evaluate the performance of the *** 13 targets in CASP8,two out of the predicted model1s selected by our approach are the best of the published CASP8 results,and seven out of the model1s are ranked in the top *** 29 targets in CASP9,20 out of the best models from our predictions are ranked in the top 10,and 11 out of the model1s are ranked in the top 10.

关键词： protein backbone prediction parallel ant colony optimization

来源：评论

学校读者我要写书评

暂无评论

Blockchain-aided Mobile Edge Intelligence With Sparse Rewarded Computing Resource Allocation

引用

IEEE Transactions on Vehicular technology 2025年

作者： Niu, Wei Shi, Long Wang, Zhe Yang, Weiwei Guo, Yongan Nanjing University of Science and Technology School of Electronic and Optical Engineering Nanjing210094 China Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing210094 China Dongguan University of Technology School of Electrical Engineering and Intelligentization Dongguan523000 China Nanjing University of Posts and Telecommunications Jiangsu Key Laboratory of Intelligent Information Processing and Communication Technology Nanjing210003 China Nanjing University of Posts and Telecommunications School of Communications and Information Engineering Nanjing210003 China

In the blockchain-aided mobile edge intelligence (B-MEI) network, base stations (BSs) each with an edge server not only execute tasks offloaded from users but also serve as blockchain nodes to ensure trustworthy data management of task execution in a decentralized manner. A challenging issue of B-MEI is that, both task execution and blockchain consensus demand significant computing resources. Insufficient resource allocation inevitably leads to resource wastage and even degrades system performance, especially in scenarios where task arrivals and wireless channels are dynamically changing. Driven by this issue, we first formulate the dynamic allocation of computing resources as a Markov Decision Process (MDP) to maximize the average transaction throughput of the B-MEI system. In particular, we find that, due to the time-consuming nature of blockchain consensus, the MDP rewards stemmed from the block generation is typically delayed and sparse. To address this issue, we propose a novel reinforcement learning algorithm, named Stable Hindsight Credit Assignment (SHCA), to effectively learn the stable credit assignment for sparse rewards across intermediate actions to optimize policy decisions. Simulation results demonstrate that the proposed algorithm improves the average transaction throughput by 78% compared with the baseline algorithm. © 1967-2012 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Structural network communication differences in drug-naive depressed adolescents with non-suicidal self-injury and suicide attempts

引用

World Journal of Psychiatry 2025年第5期15卷 66-78页

作者： Shuai Wang Jiao-Long Qin Lian-Lian Yang Ying-Ying Ji Hai-Xia Huang Xiao-Shan Gao Zi-Mo Zhou Zhen-Ru Guo Ye Wu Lin Tian Huang-Jing Ni Zhen-He Zhou School of Wuxi Medicine Nanjing Medical UniversityWuxi 214000Jiangsu ProvinceChina Department of Clinical Psychology The Affiliated Mental Health Center of Jiangnan UniversityWuxi Central Rehabilitation HospitalWuxi 214000Jiangsu ProvinceChina Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education School of Computer Science and EngineeringNanjing University of Science and TechnologyNanjing 210000Jiangsu ProvinceChina School of Medicine Jiangnan UniversityWuxi 214000Jiangsu ProvinceChina Department of Rehabilitation Medicine The Affiliated Mental Health Center of Jiangnan UniversityWuxi Central Rehabilitation HospitalWuxi 214000Jiangsu ProvinceChina Department of Medical Imaging Huadong SanatoriumWuxi 214000Jiangsu ProvinceChina School of Computer Science and Engineering Nanjing University of Science and TechnologyNanjing 210000Jiangsu ProvinceChina Department of Psychiatry The Affiliated Mental Health Center of Jiangnan UniversityWuxi Central Rehabilitation HospitalWuxi 214000Jiangsu ProvinceChina School of Computer Science and Engineering Nanjing University of Posts and TelecommunicationsNanjing 210000Jiangsu ProvinceChina

BACKGROUND Depression,non-suicidal self-injury(NSSI),and suicide attempts(SA)often co-occur during adolescence and are associated with long-term adverse health ***,neural mechanisms underlying self-injury and SA are poorly understood in depressed adolescents but likely relate to the structural abnormalities in brain *** To investigate structural network communication within large-scale brain networks in adolescents with *** We constructed five distinct network communication models to evaluate structural network efficiency at the whole-brain level in adolescents with *** magnetic resonance imaging data were acquired from 32 healthy controls and 85 depressed adolescents,including 17 depressed adolescents without SA or NSSI(major depressive disorder group),27 depressed adolescents with NSSI but no SA(NSSI group),and 41 depressed adolescents with SA and NSSI(NSSI+SA group).RESULTS Significant differences in structural network communication were observed across the four groups,involving spatially widespread brain regions,particularly encompassing cortico-cortical connections(e.g.,dorsal posterior cingulate gyrus and the right ventral posterior cingulate gyrus;connections based on precentral gyrus)and cortico-subcortical circuits(e.g.,the nucleus accumbens-frontal circuit).In addition,we examined whether compromised communication efficiency was linked to clinical symptoms in the depressed *** observed significant correlations between network communication efficiencies and clinical scale scores derived from depressed adolescents with NSSI and *** This study provides evidence of structural network communication differences in depressed adolescents with NSSI and SA,highlighting impaired neuroanatomical communication efficiency as a potential contributor to their *** findings offer new insights into the pathophysiological mechanisms underlying the comorbidity of NSSI and SA in adolescen

关键词： Depression Non-suicidal self-injury Suicide attempts Adolescents Communication models Structural network efficiency

来源：评论

学校读者我要写书评

暂无评论

A Fast Calculation of Metric Scores for Learning Bayesian Network

引用

International Journal of Automation and computing 2012年第1期9卷 37-44页

作者： Qiang Lv Xiao-Yan Xia Pei-De Qian School of Computer Science and Technology Soochow University Suzhou 215006 PRC Jiangsu Provincial Key Lab for Computer Information Processing Technology Suzhou 215006 PRC

Frequent counting is a very so often required operation in machine learning algorithms. A typical machine learning task, learning the structure of Bayesian network （BN） based on metric scoring, is introduced as an example that heavily relies on frequent counting. A fast calculation method for frequent counting enhanced with two cache layers is then presented for learning BN. The main contribution of our approach is to eliminate comparison operations for frequent counting by introducing a multi-radix number system calculation. Both mathematical analysis and empirical comparison between our method and state-of-the-art solution are conducted. The results show that our method is dominantly superior to state-of-the-art solution in solving the problem of learning BN.

关键词： Frequent counting radix-based calculation ADtree learning Bayesian network metric score

来源：评论

学校读者我要写书评

暂无评论

Fusion Analysis of Resting-State Networks and Its Application to Alzheimer's Disease

引用

Tsinghua Science and technology 2019年第4期24卷 456-467页

作者： Shengbing Pei Jihong Guan Shuigeng Zhou the Department of Computer Science and Technology Tongji University Shanghai Key Lab of Intelligent Information Processing School of Computer ScienceFudan University

Functional networks are extracted from resting-state functional magnetic resonance imaging data to explore the biomarkers for distinguishing brain disorders in disease diagnosis. Previous works have primarily focused on using a single Resting-State Network(RSN) with various techniques. Here, we apply fusion analysis of RSNs to capturing biomarkers that can combine the complementary information among the RSNs. Experiments are carried out on three groups of subjects, i.e., Cognition Normal(CN), Early Mild Cognitive Impairment(EMCI), and Alzheimer's Disease(AD) groups, which correspond to the three progressing stages of AD; each group contains18 subjects. First, we apply group Independent Component Analysis(ICA) to extracting the Default Mode Network(DMN) and Dorsal Attention Network(DAN) for each subject group. Then, by obtaining the common DMN and DAN as templates for each group, we employ the individual ICA to extract the DMN and DAN for each ***, we fuse the DMNs and DANs to explore the biomarkers. The results show that(1) the templates generated by group ICA can extract the RSN for each subject by individual ICA effectively;(2) the RSNs combined with the fusion analysis can obtain more informative biomarkers than without fusion analysis;(3) the most different regions of DMN and DAN are found between CN and EMCI and between EMCI and AD, which show differences. For the DMN, the difference in the medial prefrontal cortex between the EMCI and AD is smaller than that between CN and EMCI, whereas that in the posterior cingulate between EMCI and AD is larger. As for the DAN, the difference in the intraparietal sulcus is smaller than that between CN and EMCI;(4) extracting DMN and DAN for each subject via the back reconstruction of group ICA is invalid.

关键词： Independent Component Analysis(ICA) group analysis fusion analysis Alzheimer’s Disease(AD)

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：