检索结果-内蒙古大学图书馆

Proceedings of the 38th International Conference on Neural information processing Systems

作者： Benyuan Meng Qianqian Xu Zitai Wang Zhiyong Yang Xiaochun Cao Qingming Huang Institute of Information Engineering CAS and School of Cyber Security University of Chinese Academy of Sciences Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and Peng Cheng Laboratory Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS School of Computer Science and Tech. University of Chinese Academy of Sciences School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University School of Computer Science and Tech. University of Chinese Academy of Sciences and Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and Key Laboratory of Big Data Mining and Knowledge Management CAS

ISBN: (纸本)9798331314385

Diffusion models are powerful generative models, and this capability can also be applied to discrimination. The inner activations of a pre-trained diffusion model can serve as features for discriminative tasks, namely, diffusion feature. We discover that diffusion feature has been hindered by a hidden yet universal phenomenon that we call content shift. To be specific, there are content differences between features and the input image, such as the exact shape of a certain object. We locate the cause of content shift as one inherent characteristic of diffusion models, which suggests the broad existence of this phenomenon in diffusion feature. Further empirical study also indicates that its negative impact is not negligible even when content shift is not visually perceivable. Hence, we propose to suppress content shift to enhance the overall quality of diffusion features. Specifically, content shift is related to the information drift during the process of recovering an image from the noisy input, pointing out the possibility of turning off-the-shelf generation techniques into tools for content shift suppression. We further propose a practical guideline named GATE to efficiently evaluate the potential benefit of a technique and provide an implementation of our methodology. Despite the simplicity, the proposed approach has achieved superior results on various tasks and datasets, validating its potential as a generic booster for diffusion features. Our code is available at https://***/Darkbblue/diffusion-content-shift.

关键词：

来源：评论

学校读者我要写书评

暂无评论

STGlow: A Flow-based Generative Framework with Dual Graphormer for Pedestrian Trajectory Prediction

arXiv

引用

arXiv 2022年

作者： Liang, Rongqin Li, Yuanman Zhou, Jiantao Li, Xia Guangdong Key Laboratory of Intelligent Information Processing College of Electronics and Information Engineering Shenzhen University Shenzhen China State Key Laboratory of Internet of Things for Smart City China Department of Computer and Information Science University of Macau China

The pedestrian trajectory prediction task is an essential component of intelligent systems. Its applications include but are not limited to autonomous driving, robot navigation, and anomaly detection of monitoring systems. Due to the diversity of motion behaviors and the complex social interactions among pedestrians, accurately forecasting their future trajectory is challenging. Existing approaches commonly adopt GANs or CVAEs to generate diverse trajectories. However, GAN-based methods do not directly model data in a latent space, which may make them fail to have full support over the underlying data distribution;CVAE-based methods optimize a lower bound on the log-likelihood of observations, which may cause the learned distribution to deviate from the underlying distribution. The above limitations make existing approaches often generate highly biased or inaccurate trajectories. In this paper, we propose a novel generative flow based framework with dual graphormer for pedestrian trajectory prediction (STGlow). Different from previous approaches, our method can more precisely model the underlying data distribution by optimizing the exact log-likelihood of motion behaviors. Besides, our method has clear physical meanings for simulating the evolution of human motion behaviors. The forward process of the flow gradually degrades complex motion behavior into simple behavior, while its reverse process represents the evolution of simple behavior into complex motion behavior. Further, we introduce a dual graphormer combining with the graph structure to more adequately model the temporal dependencies and the mutual spatial interactions. Experimental results on several benchmarks demonstrate that our method achieves much better performance compared to previous state-of-the-art approaches. © 2022, CC BY-NC-SA.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Optimal Tracking Control of Injection Speed in Injection Molding Machine with Gaussian Process Learning and Model Predictive Control

Optimal Tracking Control of Injection Speed in Injection Mol...

引用

第43届中国控制会议

作者： Jianpu Cai Zhigang Ren Bo Zhang Zongze Wu School of Automation Guangdong Key Laboratory of IoT Information Technology Guangdong University of Technology Guangdong-HongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangdong University of Technology Key Laboratory of Intelligent Detection and The Internet of Things in Manufacturing (GDUT) Ministry of Education College of Mechatronics and Control Engineering Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)Shenzhen University

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

Injection molding, as a common plastic processing technology, has significant importance in modern manufacturing industry. However, due to the nonlinear dynamic characteristics of injection molding machines(IMMs) and the influence of various factors such as raw materials, equipment, and environment during the injection molding process(IMP), uncertainty residuals are generated, which makes it difficult to achieve optimal tracking control of injection speed, thereby affecting product quality and production efficiency. To address this issue, we propose a learning-based model predictive control(LMPC) *** scheme uses Gaussian process regression(GPR) to predict and model uncertainty residuals in the IMP. The residual model of IMM is learned through historical injection molding data, and the model predictive control(MPC) is used to achieve optimal tracking control of injection speed based on the predicted model, thereby automatically adjusting the injection speed according to requirements. In addition, we use differential dynamic programming with control constraints to solve the optimization ***, we conduct comprehensive numerical simulation experiments to prove the effectiveness and efficiency of the proposed LMPC scheme in injection speed control of IMM.

关键词： Injection molding model predictive control optimal control gaussian process learning control

来源：评论

学校读者我要写书评

暂无评论

Improving Image Clustering through Sample Ranking and Its Application to remote-sensing images

arXiv

引用

arXiv 2022年

作者： Li, Qinglin Qiu, Guoping College of Electronic and Information Engineering Shenzhen University Shenzhen518052 China Guangdong Key Lab for Intelligent Information Processing Shenzhen University Shenzhen518052 China Shenzhen Institute of AI and Robotics for Society Shenzhen518172 China Pengcheng Laboratory Shenzhen518055 China

Image clustering is a very useful technique that is widely applied to various areas, including remote sensing. Recently, visual representations by self-supervised learning have greatly improved the performance of image clustering. To further improve the well-trained clustering models, this paper proposes a novel method by first ranking samples within each cluster based on the confidence in their belonging to the current cluster and then using the ranking to formulate a weighted cross-entropy loss to train the model. For ranking the samples, we developed a method for computing the likelihood of samples belonging to the current clusters based on whether they are situated in densely populated neighborhoods, while for training the model, we give a strategy for weighting the ranked samples. We present extensive experimental results that demonstrate that the new technique can be used to improve the State–of–the–Art image clustering models, achieving accuracy performance gains ranging from 2.1% to 15.9%. Performing our method on a variety of datasets from remote sensing, we show that our method can be effectively applied to remote–sensing images. Copyright © 2022, The Authors. All rights reserved.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Synchronization of Nonlinear Neural Networks with Hybrid Couplings and Uncertain Time-Varying Perturbations: A Novel Distributed-Delay Impulsive Comparison Principle

SSRN

引用

SSRN 2024年

作者： Fan, Hongguang Shi, Kaibo Zhao, Yi College of Computer Chengdu University Chengdu610106 China Key Laboratory of Pattern Recognition and Intelligent Information Processing Institutions of Higher Education of Sichuan Province Chengdu University Chengdu610106 China School of Electronic Information and Electrical Engineering Chengdu University Chengdu610106 China School of Mathematical Sciences Shenzhen University Shenzhen518060 China

In this paper, the synchronization of nonlinear drive-response neural networks with uncertain time-varying perturbations, non-delayed coupling, and distributed delay coupling is studied. To address the impact of distributed delay and discrete delay on the system, a novel impulsive comparison principle is established, which can be viewed as an effective continuation of the Halanay inequality. Besides, with the help of Lyapunov stability theory, sufficient conditions guaranteeing the exponential synchronization of concerned neural networks are derived by using a delayed impulsive controller with historical status information, which releases the conventional limitation that impulsive delays should be smaller than impulsive intervals, and generalize the existing synchronization results regarding distributed delay networks. Besides, numerical simulations for chaotic neural networks are presented to demonstrate the validity of theoretical results and the sensitivity of the control gain matrix. © 2024, The Authors. All rights reserved.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Asynchronous Tag-based Physical-Layer Authentication in Wireless Communications

引用

IEEE Transactions on Wireless Communications 2025年

作者： Tan, Haijun Xu, Yuntao Du, Jiewei Xie, Ning Li, Hongbin Peng Cheng Laboratory Control and Network Foundation Laboratory Frontier Research Center Shenzhen518107 China Shenzhen University State Key Laboratory of Radio Frequency Heterogeneous Integration The Guangdong Key Laboratory of Intelligent Information Processing College of Electronics and Information Engineering Shenzhen518060 China Beijing Jiaotong University School of Electronic and Information Engineering Beijing100044 China National Innovation Center of High Speed Train Qingdao266111 China Stevens Institute of Technology Department of Electrical and Computer Engineering HobokenNJ07030 United States

Tag-based physical-layer authentication (PLA) has gained significant research interest due to its high security and low complexity compared to traditional upper-layer authentication mechanisms. However, conventional tag-based PLA schemes often require strict synchronization between the tag and the source message before transmission, which may limit their practicality and effectiveness. To address this limitation, we propose an asynchronous tag-based PLA scheme, where the tag and the source message are transmitted asynchronously with an intentional time delay introduced at the transmitter. The proposed scheme enhances both compatibility and security without compromising robustness. We provide a theoretical analysis of the proposed scheme, and derive closed-form expressions to characterize its performance. Furthermore, theoretical comparisons with existing methods yield insightful conclusions regarding the advantages of the proposed approach. The scheme is implemented and extensively evaluated through simulations, where the theoretical results exhibit strong agreement with the simulation outcomes, thereby validating its effectiveness. © 2025 IEEE.

关键词： asynchronous closed form intentional timing delay Physical-layer authentication tag-based

来源：评论

学校读者我要写书评

暂无评论

Energy Efficiency of Distributed Antenna Systems with D2D Communications Under Imperfect CSI

引用

Journal of Communications and information Networks 2020年第1期5卷 62-74页

作者： Chunlong He Fangyan Zeng Chiya Zhang Cunhua Pan Daquan Feng Fu-Chun Zheng Guangdong Key Laboratory of Intelligent Information Processing Shenzhen 518060China School of Electronic and Information Engineering Harbin Institute of TechnologyShenzhen 518055China School of Electronic Engineering and Computer Science Queen Mary University of LondonLondon E14NSUK

In this paper,we investigate the distributed antenna systems(DAS)based on device to device(DASD2D)communications under the imperfect channel state information(CSI).Our aim is to maximize the energy efficiency(EE)of the D2D users equipment(DUE)under the constraints of the maximum transmission power of D2D pairs and the quality of service(QoS)requirements of the cellular user equipment(CUE).The worst-case design is considered so that the QoS of the CUE can be guaranteed for every realization of the CSI error in the ellipsoid *** EE objective function of the optimization problem is non-convex and non-linear,and thus this problem cannot be solved by the traditional optimization *** solve this problem,first we transform it to an EE maximization problem without uncertain parameters by exploiting the Markov and Cauchy-Schwartz *** using the fractional programming theory and difference of convex functions optimization method,the robust EE maximization algorithms based on the hard and soft protection method are developed to maximize the system’s EE performance,***,these two algorithms are designed at the cost of the reduced EE of the ***,in order to further improve the EE performance and make a trade-off between the EE performance and the robustness,the iterative update algorithms for the total power constraint and average interference constraint are developed to maximize the system’s EE performance,*** results demonstrate the effectiveness of the four proposed EE algorithms and illustrate the trade-off between the EE performance and robustness for the iterative update algorithms.

关键词： distributed antenna systems device-todevice communications energy efficiency robust worstcase power allocation imperfect channel state information

来源：评论

学校读者我要写书评

暂无评论

MSAmba: Exploring Multimodal Sentiment Analysis with State Space Models 39

MSAmba: Exploring Multimodal Sentiment Analysis with State S...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： He, Xilin Liang, Haijian Peng, Boyi Xie, Weicheng Khan, Muhammad Haris Song, Siyang Yu, Zitong Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing China Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates University of Exeter United Kingdom Great Bay University China

ISBN: (纸本)157735897X

Multimodal sentiment analysis, which learns a model to process multiple modalities simultaneously and predict a sentiment value, is an important area of affective computing. Modeling sequential intra-modal information and enhancing cross-modal interactions are crucial to multimodal sentiment analysis. In this paper, we propose MSAmba, a novel hybrid Mamba-based architecture for multimodal sentiment analysis, consisting of two core blocks: Intra-Modal Sequential Mamba (ISM) block and Cross-Modal Hybrid Mamba (CHM) block, to comprehensively address the above-mentioned challenges with hybrid state space models. Firstly, the ISM block models the sequential information within each modality in a bi-directional manner with the assistance of global information. Subsequently, the CHM blocks explicitly model centralized cross-modal interaction with a hybrid combination of Mamba and attention mechanism to facilitate information fusion across modalities. Finally, joint learning of the intra-modal tokens and cross-modal tokens is utilized to predict the sentiment values. This paper serves as one of the pioneering works to unravel the outstanding performances and great research potential of Mamba-based methods in the task of multimodal sentiment analysis. Experiments on CMU-MOSI, CMU-MOSEI and CH-SIMS demonstrate the superior performance of the proposed MSAmba over prior Transformer-based and CNN-based methods. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Modal analysis

来源：评论

学校读者我要写书评

暂无评论

A Local Dominance Based Single Source Points Detector for Mixing Matrix Estimation

A Local Dominance Based Single Source Points Detector for Mi...

引用

International Wireless Communications and Mobile Computing Conference, IWCMC

作者： Yu-Yang Huang Ping Chu Bin Liao Guangdong Key Laboratory of Intelligent Information Processing College of Electronics and Information Engineering Shenzhen University Shenzhen China

In this paper, a single source points (SSPs) detection method based on local dominance is devised for mixing matrix estimation in underdetermined blind source separation (UBSS). In the proposed detector, time-frequency (TF) points of mixed signals are firstly divided into different groups, and the local covariance matrix of each group is calculated. Taking advantage of the local dominance property, the groups with rank-one local covariance matrices are then identified as single source groups, i.e., the TF points of mixed signals in single source groups are regarded as SSPs. Finally, the obtained SSPs are clustered by the hierarchical clustering algorithm to achieve mixing matrix estimation. Simulations with real audio sources show that the proposed method yields competitive robustness, efficiency and effectiveness, in comparison with the traditional methods.

关键词： Wireless communication Time-frequency analysis Estimation Clustering algorithms Detectors Robustness Blind source separation

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Broadband DOA Estimation

Deep Learning Based Broadband DOA Estimation

引用

European Conference on Antennas and Propagation, EuCAP

作者： Yi Ma Jinfeng Zhang Ping Chu Bin Liao Guangdong Key Laboratory of Intelligent Information Processing College of Electronics and Information Engineering Shenzhen University Shenzhen China

This paper proposes a fast and robust learning- based method for direction-of-arrival (DOA) estimation of multiple broadband far-field sources. The processing procedure involves two steps. First, a beamspace preprocessing which has the property of frequency invariant is applied to the array outputs to perform focusing over a wide bandwidth. By converting the outputs from the element-space to beamspace in this step, the computation can be reduced through adjusting the number of beamformers. In the second step, a hierarchical deep neural network is employed to achieve classification, which can output the DOA estimates. Simulation results verify the effectiveness and robustness of the proposed method.

关键词： Estimation error Direction-of-arrival estimation Simulation Neural networks Redundancy Focusing Europe

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：