检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Li, Pengxiang Gao, Zhi Zhang, Bofei Yuan, Tao Wu, Yuwei Harandi, Mehrtash Jia, Yunde Zhu, Song-Chun Li, Qing Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology China State Key Laboratory of General Artificial Intelligence BIGAI China State Key Laboratory of General Artificial Intelligence Peking University China Department of Electrical and Computer System Engineering Monash University Australia Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University China Department of Automation Tsinghua University China

Vision language models (VLMs) have achieved impressive progress in diverse applications, becoming a prevalent research direction. In this paper, we build FIRE, a feedback-refinement dataset, consisting of 1.1M multi-turn conversations that are derived from 27 source datasets, empowering VLMs to spontaneously refine their responses based on user feedback across diverse tasks. To scale up the data collection, FIRE is collected in two components: FIRE-100K and FIRE-1M, where FIRE-100K is generated by GPT-4V, and FIRE-1M is freely generated via models trained on FIRE-100K. Then, we build FIRE-Bench, a benchmark to comprehensively evaluate the feedback-refining capability of VLMs, which contains 11K feedback-refinement conversations as the test data, two evaluation settings, and a model to provide feedback for VLMs. We develop the FIRE-LLaVA model by fine-tuning LLaVA on FIRE-100K and FIRE-1M, which shows remarkable feedback-refining capability on FIRE-Bench and outperforms untrained VLMs by 50%, making more efficient user-agent interactions and underscoring the significance of the FIRE dataset. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Variational Bayesian Kalman filter using natural gradient

引用

Chinese Journal of Aeronautics 2022年第5期35卷 1-10页

作者： Yumei HU Xuezhi WANG Quan PAN Zhentao HU Bill MORAN School of Automation Northwestern Polytechnical UniversityXi’an 710072China The Key Laboratory of Information Fusion Technology Ministry of EducationXi’an 710072China Department of Electrical and Electronic Engineering The University of MelbourneMelbourneVIC 3010Australia School of Engineering RMIT UniversityMelbourneVIC 3000Australia School of Computer and Information Engineering Henan UniversityKaifeng 475001China

We propose a technique based on the natural gradient method for variational lower bound maximization for a variational Bayesian Kalman *** natural gradient approach is applied to the Kullback-Leibler divergence between the parameterized variational distribution and the posterior density of *** a Gaussian assumption for the parametrized variational distribution,we obtain a closed-form iterative procedure for the Kullback-Leibler divergence minimization,producing estimates of the variational hyper-parameters of state estimation and the associated error *** results in both a Doppler radar tracking scenario and a bearing-only tracking scenario are presented,showing that the proposed natural gradient method outperforms existing methods which are based on other linearization techniques in terms of tracking accuracy.

关键词： Kullback-Leibler divergence Natural gradient Nonlinear Kalman filter Target tracking Variational Bayesian optimization

来源：评论

学校读者我要写书评

暂无评论

Skeleton-based Action Recognition Using Two-stream Graph Convolutional Network with Pose Refinement 41

Skeleton-based Action Recognition Using Two-stream Graph Con...

引用

第41届中国控制会议

作者： Biao Zheng Luefeng Chen Min Wu Witold Pedrycz Kaoru Hirota School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Department of Electrical and Computer Engineering University of Alberta Tokyo Institute of Technology

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

With the development of science and technology,graph convolutional network has made great progress in improving the accuracy of action ***,there still exists some deficiencies in current ***,the human skeleton point coordinates entering into the network are barely refined,which may cause large ***,the second-order information(the length and direction of bones),which can reflect action characteristics discriminatively,is rarely *** solve the above issues,a two stream graph convolutional network with pose refinement for skeleton based action recognition is ***,we use an adaptive block to to help improve the *** test our method on Kinetics dataset and the experiment show it can get better results than some recent methods,which plays a positive role in future research.

关键词： Graph convolutional network Pose refinement Skeleton based action recognition Adaptive block

来源：评论

学校读者我要写书评

暂无评论

Vehicle Identification Model of Expressway Service Area Based on ETC Transaction Data 15th

Vehicle Identification Model of Expressway Service Area Base...

引用

15th International Conference on Genetic and Evolutionary Computing, ICGEC 2023

作者： You, Yi Zou, Fumin Cai, Qiqin Guo, Feng Fujian Provincial Key Laboratory of Automotive Electronics and Electric Drive Technology Fuzhou350118 China School of Mechanical Engineering and Automation Huaqiao University Xiamen361021 China College of Computer and Data Science Fuzhou University Fuzhou350108 China

ISBN: (纸本)9789819700677

This paper mainly focuses on vehicle identification model of expressway service area based on ETC transaction data, First Steps, Define the time when the service area entrance RSU identifies the vehicle as the vehicle order entry time;the second step, The identification time of the RSU at the service area is the export time of the vehicle order;the third step, Determine whether the vehicle order exit time minus the vehicle order entry time is greater than or equal to the threshold time T;In Step 4, If order exit time minus order entry time is greater than or equal to threshold time T, The order vehicle is considered as the vehicle entering the service area;If order exit time minus order entry time is less than threshold time T, Think that the order vehicle did not enter the service area, For the arterial road vehicles, Based on the method and system of identifying whether the vehicle enters the service area on the expressway, ETC effectively solves the expressway service area scenario, The difficult problem of the vehicle information collection in the service area being misread by the ETC equipment in the service area. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Multi-objective Optimal Operation of Centralized Battery Swap Charging System with Photovoltaic

引用

Journal of Modern Power Systems and Clean Energy 2022年第1期10卷 149-162页

作者： Yuanzheng Li Yihan Cai Tianyang Zhao Yun Liu Jian Wang Lei Wu Yong Zhao School of Artificial Intelligence and Automation Ministry of Education Key Laboratory of Image Processing and Intelligence ControlHuazhong University of Science and TechnologyWuhanChina School of Electrical and Electronic Engineering Nanyang Technological UniversitySingaporeSingapore College of Mechatronics and Control Engineering Shenzhen UniversityShenzhenChina Department of Electrical&Computer Engineering Stevens Institute of TechnologyHobokenUSA

Electric vehicles(EVs)are widely deployed throughout the world,and photovoltaic(PV)charging stations have emerged for satisfying the charging demands of EV *** paper proposes a multi-objective optimal operation method for the centralized battery swap charging system(CBSCS),in order to enhance the economic efficiency while reducing its adverse effects on power *** proposed method involves a multi-objective optimization scheduling model,which minimizes the total operation cost and smoothes load fluctuations,***,we modify a recently proposed multi-objective optimization algorithm of non-sorting genetic algorithm III(NSGA-III)for solving this scheduling ***,simulation studies verify the effectiveness of the proposed multi-objective operation method.

关键词： Multi-objective optimization electric vehicle battery swap charging system scheduling photovoltaic

来源：评论

学校读者我要写书评

暂无评论

Convolution-Transformer for Image Feature Extraction

引用

computer Modeling in engineering & Sciences 2024年第10期141卷 87-106页

作者： Lirong Yin Lei Wang Siyu Lu Ruiyang Wang Youshuai Yang Bo Yang Shan Liu Ahmed AlSanad Salman A.AlQahtani Zhengtong Yin Xiaolu Li Xiaobing Chen Wenfeng Zheng Department of Geography and Anthropology Louisiana State UniversityBaton RougeLA70803USA School of Automation University of Electronic Science and Technology of ChinaChengdu610054China College of Computer and Information Sciences King Saud UniversityRiyadh11574Saudi Arabia College of Resources and Environmental Engineering Key Laboratory of Karst Georesources and Environment(Guizhou University)Ministry of EducationGuiyang550025China School of Geographical Sciences Southwest UniversityChongqing400715China School of Electrical and Computer Engineering Louisiana State UniversityBaton RougeLA70803USA

This study addresses the limitations of Transformer models in image feature extraction,particularly their lack of inductive bias for visual *** to Convolutional Neural Networks(CNNs),the Transformers are more sensitive to different hyperparameters of optimizers,which leads to a lack of stability and slow *** tackle these challenges,we propose the Convolution-based Efficient Transformer Image Feature Extraction Network(CEFormer)as an enhancement of the Transformer *** model incorporates E-Attention,depthwise separable convolution,and dilated convolution to introduce crucial inductive biases,such as translation invariance,locality,and scale invariance,into the Transformer ***,we implement a lightweight convolution module to process the input images,resulting in faster convergence and improved *** results in an efficient convolution combined Transformer image feature extraction *** results on the ImageNet1k Top-1 dataset demonstrate that the proposed network achieves better accuracy while maintaining high computational *** achieves up to 85.0%accuracy across various model sizes on image classification,outperforming various baseline *** integrated into the Mask Region-ConvolutionalNeuralNetwork(R-CNN)framework as a backbone network,CEFormer outperforms other models and achieves the highest mean Average Precision(mAP)*** research presents a significant advancement in Transformer-based image feature extraction,balancing performance and computational efficiency.

关键词： Transformer E-Attention depth convolution dilated convolution CEFormer

来源：评论

学校读者我要写书评

暂无评论

FedDGL: Federated Dynamic Graph Learning for Temporal Evolution and Data Heterogeneity 16

FedDGL: Federated Dynamic Graph Learning for Temporal Evolut...

引用

16th Asian Conference on Machine Learning, ACML 2024

作者： Xie, Zaipeng Li, Likun Chen, Xiangbin Yu, Hao Huang, Qian Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing China College of Computer Science and Software Engineering Hohai University Nanjing China College of Artificial Intelligence and Automation Hohai University Nanjing China

Federated graph learning enhances federated learning by enabling privacy-preserving collaborative training on distributed graph data. While traditional methods are effective in managing data heterogeneity, they typically assume static graph structures, overlooking the dynamic nature of real-world graphs. Integrating federated graph learning with dynamic graph neural networks addresses this issue but often fails to retain previously acquired knowledge, limiting generalization for both global and personalized models. This paper proposes FedDGL, a novel framework designed to address temporal evolution, and data heterogeneity in federated dynamic graph learning. Unlike conventional approaches, FedDGL captures temporal dynamics through a global knowledge distillation technique and manages client heterogeneity using a global prototype-based regularization method. The framework employs contrastive learning to generate global prototypes, enhancing feature representation while utilizing a prototype similarity-based personalized aggregation strategy for effective adaptation to local and global data distributions. Experiments on multiple benchmark datasets show that FedDGL achieves significant performance improvements over state-of-the-art methods, with up to 9.02% and 8.77% gains in local and global testing, respectively, compared to FedAvg. These results highlight FedDGL’s effectiveness in improving personalized and global model performance in dynamic, heterogeneous federated graph learning scenarios. © 2024 Z. Xie, L. Li, X. Chen, H. Yu & Q. Huang.

关键词： Dynamic Graph Learning Federated Graph Learning Knowledge Distillation Personalized Aggregation Prototype Learning Temporal Evolution

来源：评论

学校读者我要写书评

暂无评论

Discounted Iterative Adaptive Critic Designs With Novel Stability Analysis for Tracking Control

引用

IEEE/CAA Journal of Automatica Sinica 2022年第7期9卷 1262-1272页

作者： Mingming Ha Ding Wang Derong Liu School of Automation and Electrical Engineering University of Science and Technology BeijingBeijing 100083China Faculty of Information Technology the Beijing Key Laboratory of Computational Intelligence and Intelligent Systemthe Beijing Laboratory of Smart Environmental Protectionand the Beijing Institute of Artificial IntelligenceBeijing University of TechnologyBeijing 100124China Department of Electrical and Computer Engineering University of Illinois at ChicagoChicago IL 60607 USA IEEE

The core task of tracking control is to make the controlled plant track a desired *** traditional performance index used in previous studies cannot eliminate completely the tracking error as the number of time steps *** this paper,a new cost function is introduced to develop the value-iteration-based adaptive critic framework to solve the tracking control *** the regulator problem,the iterative value function of tracking control problem cannot be regarded as a Lyapunov function.A novel stability analysis method is developed to guarantee that the tracking error converges to *** discounted iterative scheme under the new cost function for the special case of linear systems is ***,the tracking performance of the present scheme is demonstrated by numerical results and compared with those of the traditional approaches.

关键词： Adaptive critic design adaptive dynamic programming(ADP) approximate dynamic programming discrete-time nonlinear systems reinforcement learning stability analysis tracking control value iteration(VI)

来源：评论

学校读者我要写书评

暂无评论

ADD 2023: the Second Audio Deepfake Detection Challenge

ADD 2023: the Second Audio Deepfake Detection Challenge

引用

2023 Workshop on Deepfake Audio Detection and Analysis, DADA 2023

作者： Yi, Jiangyan Tao, Jianhua Fu, Ruibo Yan, Xinrui Wang, Chenglong Wang, Tao Zhang, Chu Yuan Zhang, Xiaohui Zhao, Yan Ren, Yong Xu, Le Zhou, Junzuo Gu, Hao Wen, Zhengqi Liang, Shan Lian, Zheng Nie, Shuai Li, Haizhou State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China Department of Automation Tsinghua University Beijing China Department of Electrical and Computer Engineering National University of Singapore Singapore The Chinese University of Hong Kong Hong Kong

Audio deepfake detection is an emerging topic in the artificial intelligence community. The second Audio Deepfake Detection Challenge (ADD 2023) aims to spur researchers around the world to build new innovative technologies that can further accelerate and foster research on detecting and analyzing deepfake speech utterances. Different from previous challenges (e.g. ADD 2022), ADD 2023 focuses on surpassing the constraints of binary real/fake classification, and actually localizing the manipulated intervals in a partially fake speech as well as pinpointing the source responsible for generating any fake audio. Furthermore, ADD 2023 includes more rounds of evaluation for the fake audio game sub-challenge. The ADD 2023 challenge includes three subchallenges: audio fake game (FG), manipulation region location (RL) and deepfake algorithm recognition (AR). This paper describes the datasets, evaluation metrics, and protocols. Some findings are also reported in audio deepfake detection tasks. © 2023 CEUR-WS. All rights reserved.

关键词： Fake detection

来源：评论

学校读者我要写书评

暂无评论

Entropy-Guided Reinforced Open World Active 3D Object Detection Learning

Entropy-Guided Reinforced Open World Active 3D Object Detect...

引用

2024 China automation Congress, CAC 2024

作者： Zhang, Haozhe Ma, Liyan Ying, Shihui Institute of Artificial Intelligence Shanghai University Shanghai200444 China School of Computer Engineering and Science School of Mechatronic Engineering and Automation Shanghai Key Laboratory of Intelligent Manufacturing and Robotics Shanghai University Shanghai200444 China Department of Mathematics School of Science Shanghai University Shanghai200444 China

ISBN: (纸本)9798350368604

Traditional fully annotated closed set 3D object detection methods improve model performance but are impractical in real-world settings due to the emergence of new categories and the complexity of 3D annotations. Open-World Object Detection (OWOD) addresses these issues but relies heavily on manual labeling, which is costly. This paper focuses on open world active learning and proposes an entropy-guided reinforced open world active 3D object detection (EROA). EROA regards active learning as a reinforcement learning problem tailored for open driving scenarios. We use entropy as a reward metric for efficient reinforcement learning. We also leverage knowledge from the 2D domain using object-level large-scale vision-language models to enhance sample selection. Extensive experiments evidence that the proposed EROA meets the dynamic and cost-sensitive requirements of autonomous driving, enabling real-time detection of both known and unknown objects. © 2024 IEEE.

关键词： Active learning

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：