检索结果-内蒙古大学图书馆

Learning to Learn Transferable Generative Attack for Person Re-Identification

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

An Improved Dual Neural Network Method Based on Levy Flight for Multi-Robot Cooperative Area Coverage Search in 3D Unknown Environments

引用

IEEE Transactions on Cognitive and Developmental Systems 2025年

作者： Zhang, Fangfang Wang, Yongqi Wang, Wenhao Xin, Jianbin Peng, Jinzhu Wang, Yaonan Zhengzhou University School of Electrical and Information Engineering Zhengzhou450001 China State Key Laboratory of Intelligent Agricultural Power Equipment Luoyang471039 China National Engineering Laboratory of Robot Visual Perception and Control Technology School of Robotics Hunan University Changsha410082 China

The research on multi-robot collaborative search in unknown 3D environments, based on bio-inspired neural networks, holds significant value and ***, challenges arise in 3D environments, including excessive turning and vertical movement, as well as the potential for collisions between robots. In response, we propose an improved Glasius Bio-Inspired Neural Network(GBNN) that mitigates decision conflicts among robots and considers the impact of turning and vertical movement on robot decision-making. Furthermore, to address the issue of robots getting trapped in local deadlocks during the search process, we present a dual neural network algorithm based on Levy flights. In the method Dual Glasius Bio-Inspired Neural Network based on Levy Flight(LF-DUAL-GBNN) proposed in this paper, robots obtain random target points through Levy flights and are then guided by a dual neural network to navigate to the vicinity of the target points, thus breaking free from local deadlock states. Finally, we conducted simulation experiments to validate the algorithm's effectiveness. © 2016 IEEE.

关键词： Microrobots

来源：评论

学校读者我要写书评

暂无评论

Salient Object Detection in Traffic Scene through the TSOD10K Dataset

arXiv

引用

arXiv 2025年

作者： Qiu, Yu Sun, Yuhang Mei, Jie Xiao, Lin Xu, Jing College of Information Science and Engineering Hunan Normal University Changsha410081 China National Key Laboratory of Intelligent Tracking and Forecasting for Infectious Diseases College of Artificial Intelligence Nankai University Tianjin300350 China National Engineering Research Center of Robot Visual Perception and Control Technology School of Robotics Hunan University Changsha410082 China

Traffic Salient Object Detection (TSOD) aims to segment the objects critical to driving safety by combining semantic (e.g., collision risks) and visual saliency. Unlike SOD in natural scene images (NSI-SOD), which prioritizes visually distinctive regions, TSOD emphasizes the objects that demand immediate driver attention due to their semantic impact, even with low visual contrast. This dual criterion, i.e., bridging perception and contextual risk, re-defines saliency for autonomous and assisted driving systems. To address the lack of task-specific benchmarks, we collect the first large-scale TSOD dataset with pixel-wise saliency annotations, named TSOD10K. TSOD10K covers the diverse object categories in various real-world traffic scenes under various challenging weather/illumination variations (e.g., fog, snowstorms, low-contrast, and low-light). Methodologically, we propose a Mamba-based TSOD model, termed Tramba. Considering the challenge of distinguishing inconspicuous visual information from complex traffic backgrounds, Tramba introduces a novel Dual-Frequency visual State Space module equipped with shifted window partitioning and dilated scanning to enhance the perception of fine details and global structure by hierarchically decomposing high/low-frequency components. To emphasize critical regions in traffic scenes, we propose a traffic-oriented Helix 2D-Selective-Scan (Helix-SS2D) mechanism that injects driving attention priors while effectively capturing global multi-direction spatial dependencies. We establish a comprehensive benchmark by evaluating Tramba and 22 existing NSI-SOD models on TSOD10K, demonstrating Tramba’s superiority. Our research establishes the first foundation for safety-aware saliency analysis in intelligent transportation systems. Copyright © 2025, The Authors. All rights reserved.

关键词： Risk perception

来源：评论

学校读者我要写书评

暂无评论

Tackling Real-world Complexity: Hierarchical Modeling and Dynamic Prompting for Multimodal Long Document Classification

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Liu, Tengfei Hu, Yongli Li, Mingjie Yi, Junfei Chang, Xiaojun Gao, Junbin Yin, Baocai Beijing University of Technology Beijing Key Laboratory of Multimedia and Intelligent Software Technology Beijing Institute of Artificial Intelligence School of Information Science and Technology Beijing100124 China Stanford University Department of Radiation Oncology StanfordCA94305 United States Hunan University National Engineering Laboratory of Robot Visual Perception and Control Technology College of Electrical and Information Engineering Hunan Changsha410082 China University of Technology Sydney ReLER Laboratory Australian Artificial Intelligence Institute Faculty of Engineering and Information Technology UltimoNSW2007 Australia The University of Sydney Business School The University of Sydney Discipline of Business Analytics CamperdownNSW2006 Australia

With the rapid growth of internet content, multimodal long document data has become increasingly prominent, drawing significant attention from researchers. However, most existing methods primarily focus on scenarios where all modalities are present, often overlooking more challenging and realistic cases involving missing image modality. To address this limitation, we propose a robust multimodal long document classification (MLDC) framework that integrates hierarchical modeling and dynamic prompting to handle complex multimodal long document data. Our approach begins by leveraging hierarchical modeling combined with an Adaptive Correlation Multimodal Transformer (ACMT) to effectively capture relationships between text and images at both section and sentence levels. We also introduce a Dynamic Prompt Generation (DPG) module at both levels to enhance the model's robustness in handling missing image data. By evaluating sample uncertainty, the DPG module dynamically adjusts both the number of prompts and the prompts themselves, allowing the model to better adapt to the varying needs of different samples. Finally, a Hierarchical Heterogeneous Graph (HHG) is introduced to enhance feature interactions across levels, further improving the coherence and accuracy of the model. Extensive experiments on four multi-modal long document datasets demonstrate that our model shows superior performance compared to existing state-of-the-art MLDC classification methods in various conditions. © 1991-2012 IEEE.

关键词： dynamic prompt generation hierarchical heterogeneous graph Multimodal long document classification

来源：评论

学校读者我要写书评

暂无评论

When Shannon Meets Nonstochastic information: Communication and Estimation

引用

IEEE Transactions on Automatic Control 2025年

作者： Zhang, Wentao Zuo, Zhiqiang Zhao, Rui Wang, Yijing Hu, Guoqiang Zhang, Hui Wang, Yaonan Hunan University School of Robotics Changsha410082 China Nanyang Technological University Continental-NTU Corporate Lab Singapore639798 Singapore Tianjin University Tianjin Key Laboratory of Intelligent Unmanned Swarm Technology and System School of Electrical and Information Engineering Tianjin300072 China Nanyang Technological University School of Electrical and Electronic Engineering Singapore639798 Singapore National Engineering Research Center for Robot Visual Perception and Control Changsha410082 China Hunan University College of Electrical and Information Engineering Changsha410082 China

This notes focuses on the issue of whether or not the state of a plant can be estimated when the inputs of communication channel involve noise and disturbance simultaneously. It turns out to calculate the maximum capacity of stationary memoryless multiple quasi-access channel under nonstochastic information theory. It is shown that the maximum information rate over such a channel is determined by a convex hull spanned by the zero-error capacities which are specified on the underlying sample spaces. Moreover, the state of a plant could be estimated provided that the maximal information rate is strictly greater than the topology entropy. © 1963-2012 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

Resilient Formation Control Based on Watermarks for Networked Quadrotors under Deception Attacks

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Zhan, Weiwei Miao, Zhiqiang Zeng, Jianxin Chen, Yanjie Wu, Zheng-Guang He, Wei Wang, Yaonan Hunan University College of Electrical and Information Engineering Changsha410082 China Fuzhou University School of Mechanical Engineering and Automation Fuzhou350108 China National Engineering Research Center of Robot Visual Perception and Control Technology Changsha410082 China Zhejiang University Institute of Cyber-Systems and Control Hangzhou310027 China University of Science and Technology Beijing Key Laboratory of Intelligent Bionic Unmanned Systems Ministry of Education School of Intelligence Science and Technology Institute of Artificial Intelligence Beijing100083 China

This article addresses the problem of formation control of networked UAVs under deception attacks. A lightweight resilient formation control framework based on watermarks is proposed to achieve the desired formation configuration without extra monitoring attack status. Since deception attacks are covert, the shared information is watermarked before transmission to establish the protocol among networked UAVs. To facilitate the resilient formation controller design, a decoder is first developed to decipher the inverse transformation of deception attacks, where the watermark is the criterion for approximating the inverse transformation. The Gauss error function is introduced to eliminate some unrealistic input commands under deception attacks, obtaining the predefined input performance. Then, a resilient formation controller is developed to guarantee the global boundedness of all signals within the inner-loop and outerloop system, while the formation error converges to a small neighborhood of zero by solving the linear matrix inequality. Two challenging deception attack examples in simulations and experiments are conducted to verify the effectiveness and performance of the proposed resilient formation control framework. © 1967-2012 IEEE.

关键词： Inverse transforms

来源：评论

学校读者我要写书评

暂无评论

Diff-Reg v2: Diffusion-Based Matching Matrix Estimation for Image Matching and 3D Registration

arXiv

引用

arXiv 2025年

作者： Wu, Qianliang Jiang, Haobo Ding, Yaqing Luo, Lei Xie, Jin Yang, Jian PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education China School of Computer Science and Engineering Nanjing University of Science and Technology China Nanyang Technological University Singapore Visual Recognition Group Faculty of Electrical Engineering Czech Technical University in Prague Prague Czech Republic State Key Laboratory for Novel Software Technology Nanjing University Nanjing China School of Intelligence Science and Technology Nanjing University Suzhou China

Establishing reliable correspondences is crucial for all registration tasks, including 2D image registration, 3D point cloud registration, and 2D-3D image-to-point cloud registration. However, these tasks are often complicated by challenges such as scale inconsistencies, symmetry, and large deformations, which can lead to ambiguous matches. Previous feature-based and correspondence-based methods typically rely on geometric or semantic features to generate or polish initial potential correspondences. Some methods typically leverage specific geometric priors, such as topological preservation, to devise diverse and innovative strategies tailored to a given enhancement goal, which cannot be exhaustively enumerated. Additionally, many previous approaches rely on a single-step prediction head, which can struggle with local minima in complex matching scenarios. To address these challenges, we introduce an innovative paradigm that leverages a diffusion model in matrix space for robust matching matrix estimation. Our model treats correspondence estimation as a denoising diffusion process in the matching matrix space, gradually refining the intermediate matching matrix to the optimal one. Specifically, we apply the diffusion model in the doubly stochastic matrix space for 3D-3D and 2D-3D registration tasks. In the 2D image registration task, we deploy the diffusion model in a matrix sub-space, where dual-softmax projection regularization is applied. For all three registration tasks, we provide adaptive matching matrix embedding implementations tailored to the specific characteristics of each task while maintaining a consistent"match-to-warp" encoding pattern. Furthermore, we adopt a lightweight design for the denoising module. In inference, once points or image features are extracted and fixed, this module performs multi-step denoising predictions through reverse sampling. Evaluations on both 2D and 3D registration tasks demonstrate the effectiveness of our approach. Copyrigh

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

ECINFusion: A Novel Explicit Channel-wise Interaction Network for Unified Multi-modal Medical Image Fusion

引用

IEEE Transactions on Circuits and Systems for Video Technology 2024年第5期35卷 4011-4025页

作者： Wei, Xinjian Qiu, Yu Xu, Xiaoxuan Xu, Jing Mei, Jie Zhang, Jun Nankai University National Key Laboratory of Intelligent Tracking and Forecasting for Infectious Diseases College of Artificial Intelligence Tianjin300350 China Hunan Normal University College of Information Science and Engineering Changsha410081 China National Engineering Research Center of Robot Visual Perception and Control Technology School of Robotics Hunan University Changsha410081 China College of Artificial Intelligence Nankai University Tianjin300350 China

Multi-modal medical image fusion enhance the representation, aggregation and comprehension of functional and structural information, improving accuracy and efficiency for subsequent analysis. However, lacking explicit cross channel modeling and interaction among modalities results in the loss of details and artifacts. To this end, we propose a novel Explicit Channel-wise Interaction Network for unified multi-modal medical image Fusion, namely ECINFusion. ECINFusion encompasses two components: multi-scale adaptive feature modeling (MAFM) and explicit channel-wise interaction mechanism (ECIM). MAFM leverages adaptive parallel convolution and transformer in multi-scale manner to achieve the global context-aware feature representation. ECIM utilizes the designed multi-head channel-attention mechanism for explicit modeling in channel dimension to accomplish the cross-modal interaction. Besides, we introduce a novel adaptive L-Norm loss, preserving fine-grained details. Experiments demonstrate ECINFusion outperforms state-of-the-art approaches in various medical fusion sub-tasks on different metrics. Furthermore, extended experiments reveal the robust generalization of the proposed in different fusion tasks. In breif, the proposed explicit channel-wise interaction mechanism provides new insight for multi-modal interaction. © 2024 IEEE.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Efficient Image Super-Resolution with Feature Interaction Weighted Hybrid Network

引用

IEEE Transactions on Multimedia 2024年 27卷 2256-2267页

作者： Li, Wenjie Li, Juncheng Gao, Guangwei Deng, Weihong Yang, Jian Qi, Guo-Jun Lin, Chia-Wen Beijing University of Posts and Telecommunications Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing100080 China Shanghai University School of Communication and Information Engineering Shanghai200444 China Nanjing University of Posts and Telecommunications Intelligent Visual Information Perception Laboratory Institute of Advanced Technology Nanjing210046 China Ministry of Education Key Laboratory of Artificial Intelligence Shanghai200240 China Soochow University Provincial Key Laboratory for Computer Information Processing Technology Suzhou215006 China Nanjing University of Science and Technology School of Computer Science and Technology Nanjing210094 China Westlake University Research Center for Industries of the Future School of Engineering Hangzhou310024 China OPPO Research SeattleWA98101 United States National Tsing Hua University Department of Electrical Engineering Institute of Communications Engneering Hsinchu300044 Taiwan

Lightweight image super-resolution aims to reconstruct high-resolution images from low-resolution images using low computational costs. However, existing methods result in the loss of middle-layer features due to activation functions. To minimize the impact of intermediate feature loss on reconstruction quality, we propose a Feature Interaction Weighted Hybrid Network (FIWHN), which comprises a series of Wide-residual Distillation Interaction Block (WDIB) as the backbone. Every third WDIB forms a Feature Shuffle Weighted Group (FSWG) by applying mutual information shuffle and fusion. Moreover, to mitigate the negative effects of intermediate feature loss, we introduce Wide Residual Weighting units within WDIB. These units effectively fuse features of varying levels of detail through a Wide-residual Distillation Connection (WRDC) and a Self-Calibrating Fusion (SCF). To compensate for global feature deficiencies, we incorporate a Transformer and explore a novel architecture to combine CNN and Transformer. We show that our FIWHN achieves a favorable balance between performance and efficiency through extensive experiments on low-level and high-level tasks. Codes will be available at https://***/IVIPLab/FIWHN. © 1999-2012 IEEE.

关键词： Transformers Convolutional neural networks Computational modeling Feature extraction Training Superresolution Adaptation models Computer architecture Telecommunications Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

intelligent Gear Shifting Strategy of Mining Truck Based on Deep Learning and Real-Time Vehicle Condition

SSRN

引用

SSRN 2023年

作者： Su, Qinghua Xu, Xiaoyu Wang, Liyong Zhang, Dingge Xie, Min Zhang, Pengbo Key Laboratory of Modern Measurement and Control Technology Ministry of Education Beijing Information Science and Technology University Beijing100192 China Laboratory for Visual Perception and Intelligent Systems School of Control Science and Engineering Shandong University Shangdong Province Jinan250100 China

Mining areas are characterized by complex driving conditions, making automatic gear shift strategies specifically suited for mine trucks are critical. Nevertheless, development of automatic gear shifting strategy is under challenging, as it relies on experience and historical experiment data which is the top classified commercial secret of the manufacturers. Recently, some gear shifting strategies have been implemented based on artificial intelligent technology. However, many of them shift the gear based on vehicle current status and ignore the influences of historical data. It has potential risk by making wrong shift when receiving abnormal sensor data accidentally. Besides that, it also causes the gear continuous shifting within short time, which increases the chance of transmission damage and influences the driving experience. Consequently, a novel method based on Bi-directional Long Short-Term Memory(Bi-LSTM) network with multiple parameters from continuous time spans for gear prediction is proposed. The real-time vehicle status data is becaptured from CAN-bus, and 9 types of parameters with positive relation for gear shifting are chosen by R/S analysis. By inputting values of 9 paramters from continuous time spans to our Bi-LSTM based machine learning model, gear prediction target is achieved. The experimental records show that our network outputs the gears best suited to the current vehicle state with 96.85% accuracy. Its average prediction time consumption is around 3.86ms, which fits the real-time processing requirement in driving. Our network not only has advantages in balancing prediction correct rate and time consumption, but also maintains high accuracy when overcoming the influence of transient abnormal sensor data. Hence, it has the potential to be widely applied to the fields that prediction model is based on the data with temporal characteristic. © 2023, The Authors. All rights reserved.

关键词： Long short-term memory

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：