检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Li, Jiaqi Li, Haoran Chen, Yaran Ding, Zixiang Li, Nannan Ma, Mingjun Duan, Zicheng Zhao, Dongbing The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China The School of Mechanical Engineering Beijing Institute of Technology Beijing100081 China The University of Chinese Academy of Sciences Beijing China The College of Engineering and Computer Science Australian National University ACT2601 Australia

Currently, an increasing number of model pruning methods are proposed to resolve the contradictions between the computer powers required by the deep learning models and the resource-constrained devices. However, most of the traditional rule-based network pruning methods can not reach a sufficient compression ratio with low accuracy loss and are time-consuming as well as laborious. In this paper, we propose Automatic Block-wise and Channel-wise Network Pruning (ABCP1) to jointly search the block-wise and channel-wise pruning action with deep reinforcement learning. A joint sample algorithm is proposed to simultaneously generate the pruning choice of each residual block and the channel pruning ratio of each convolutional layer from the discrete and continuous search space respectively. The best pruning action taking both the accuracy and the complexity of the model into account is obtained finally. Compared with the traditional rule-based pruning method, this pipeline saves human labor and achieves a higher compression ratio with lower accuracy loss. Tested on the mobile robot detection dataset, the pruned YOLOv3 model saves 99.5% FLOPs, reduces 99.5% parameters, and achieves 37.3× speed up with only 2.8% mAP loss. The results of the transfer task on the sim2real detection dataset also show that our pruned model has much better robustness performance. Copyright © 2021, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

MVM3Det: A novel method for multi-view monocular 3D detection

arXiv

引用

arXiv 2021年

作者： Li, Haoran Duan, Zicheng Ma, Mingjun Chen, Yaran Li, Jiaqi Zhao, Dongbin The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China The University of Chinese Academy of Sciences Beijing China The College of Engineering and Computer Science Australian National University ACT2601 Australia The School of Mechanical Engineering Beijing Institute of Technology Beijing100081 China

Monocular 3D object detection encounters occlusion problems in many application scenarios, such as traffic monitoring, pedestrian monitoring, etc., which leads to serious false negatives. Multi-view object detection effectively solves this problem by combining data from different perspectives. However, due to label confusion and feature confusion, the orientation estimation of multi-view 3D object detection is intractable, which is important for object tracking and intention prediction. In this paper, we propose a novel multi-view 3D object detection method named MVM3Det which simultaneously estimates the 3D position and orientation of the object according to the multi-view monocular information. The method consists of two parts: 1) Position proposal network, which integrates the features from different perspectives into consistent global features through feature orthogonal transformation to estimate the position. 2) Multi-branch orientation estimation network, which introduces feature perspective pooling to overcome the two confusion problems during the orientation estimation. In addition, we present the first dataset for multi-view 3D object detection named MVM3D. Comparing with State-Of-The-Art (SOTA) methods on our dataset and public dataset WildTrack, our method achieves very competitive results. © 2021, CC BY.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Plug-and-Play Based Optimization Algorithm for New Crime Density Estimation

引用

Journal of computer science & Technology 2019年第2期34卷 476-493页

作者： Xiang-Chu Feng Chen-Ping Zhao Si-Long Peng Xi-Yuan Hu Zhao-Wei Ouyang School of Mathematics and Statistics Xidian University Xi’an 710126 China School of Mathematical Science Henan Institute of Science and Technology Xinxiang 453003 China Institute of Automation Chinese Academy of Sciences Beijing 100190 China School of Computer and Control Engineering University of Chinese Academy of Sciences Beijing 100190 China Research Center of Beijing Visystem Co. Ltd. Beijing 100190 China

Different from a general density estimation,the crime density estimation usually has one important factor:the geographical *** this paper,a new crime density estimation model is formulated,in which the regions where crime is impossible to happen,such as mountains and lakes,are *** further optimize the estimation method,a learning-based algorithm,named Plug-and-Play,is implanted into the augmented Lagrangian scheme,which involves an off-the-shelf filtering *** selections of the filtering operator make the algorithm correspond to several classical estimation ***,the proposed Plug-and-Play optimization based estimation algorithm can be regarded as the extended version and general form of several classical *** the experiment part,synthetic examples with different invalid regions and samples of various distributions are first *** under complex geographic constraints,we apply the proposed method with a real crime dataset to recover the density *** state-of-the-art results show the feasibility of the proposed model.

关键词： crime density estimation augmented Lagrangian strategy Plug-and-Play filtering operator

来源：评论

学校读者我要写书评

暂无评论

Exact Differentiator with Lipschitz Continuous Output and Optimal Worst-Case Accuracy Under Bounded Noise

Exact Differentiator with Lipschitz Continuous Output and Op...

引用

IEEE Conference on Decision and control

作者： Rodrigo Aldana-López Richard Seeber Hernan Haimovich David Gómez-Gutiérrez Department of Computer Science and Systems Engineering University of Zaragoza Zaragoza Spain Christian Doppler Laboratory for Model Based Control of Complex Test Bed Systems Institute of Automation and Control Graz University of Technology Graz Austria Centro Internacional Franco-Argentino de Ciencias de la Información y de Sistemas (CIFASIS) CONICET-UNR Rosario Argentina Intel Tecnología de México Intel Labs Intelligent Systems Research Lab Jalisco Mexico Tecnológico Nacional de México Instituto Tecnológico José Mario Molina Pasquel y Henríquez Unidad Académica Zapopan Jalisco Mexico

The online differentiation of a signal contaminated with bounded noise is addressed. A differentiator is developed that generates a Lipschitz continuous output, is exact in the absence of noise, and provides the optimal worst-case accuracy among all possible exact differentiators when noise is present. This combination of features is not shared by any previously existing differentiator. Tuning of the developed differentiator is very simple, requiring only the knowledge of a bound for the second-order derivative of the signal. The approach consists in regularizing the possibly highly noisy output of a recently introduced linear adaptive robust exact differentiator and feeding it to a first-order sliding-mode filter designed to maintain optimal accuracy. The proposed regularization and filtering of this output allows trading the speed with which exactness is obtained for the feature of a Lipschitz continuous, hence less noisy, output. An illustrative example is provided to highlight the features of the developed differentiator.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Spatial-temporal Transformer For Skeleton-based Action Recognition

Spatial-temporal Transformer For Skeleton-based Action Recog...

引用

Chinese automation Congress (CAC)

作者： Qipeng Zhang Tian Wang Mengyi Zhang Kexin Liu Peng Shi Hichem Snoussi School of Automation Science and Electrical Engineering Beihang University Beijing China Jiangsu Key Laboratory of Image and Video Understanding for Social Safety Nanjing University of Science and Technology Nanjing China Institute of Artificial Intelligence Beihang University Beijing China College of Electrical Engineering and Control Science Nanjing Tech University Nanjing China School of Mathematics and Computer Science Fujian Normal University Fujian China

ISBN: (纸本)9781665426480

In the area of skeleton-based human action recognition, GCN has achieved good results in previous research due to its excellent modeling ability on graph data. Recently, transformers have achieved extraordinary results in many computer vision fields. Comparing transformer and GCN, from a certain point of view, we can regard transformer as a kind of dynamic GCN, and the weight of each node is dynamically determined by data. In this work, a three-dimensional position encoding was proposed by us to solve the representation of node spatial information, in order to apply the transformer to the graph data. In addition, similar to Spatial-Temporal Graph Convolutional Networks (ST-GCN), we proposed a Space-Time Transformer (ST-TR), which applies transformers in space and time to extract spatiotemporal feature of skeleton data to complete action recognition.

关键词： computer vision Image recognition Computational modeling Transformers Feature extraction Skeleton Encoding

来源：评论

学校读者我要写书评

暂无评论

Solving non-cyclic dynamic multi-objective optimization problems via GRU prediction and multi-information hybrid exploration

引用

Journal of Supercomputing 2025年第8期81卷 1-34页

作者： Sun, Hao Bai, Xiaochuang Wang, Cong Yang, He Hu, Ziyu School of Electrical and Engineering Yanshan University Hebei Qinhuangdao066004 China Key Laboratory of Industrial Computer Control Engineering of Hebei Province Yanshan University Hebei Qinhuangdao066004 China Electrical automation department Tianjin Research Institute of Electric Science Co. Ltd. Tianjin China

In non-cyclic dynamic multi-objective optimization problems, the non-cyclic nature of environmental changes may cause the Pareto optimal front (PF) to be different from historical times. In addition, changes may also occur on the Pareto optimal solutions set (PS). However, predictions based solely on a single space show lower accuracy due to insufficient information. Therefore, solving non-cyclic dynamic multi-objective optimization problems via gate recurrent unit (GRU) prediction and multi-information hybrid exploration (GPMHE) is designed to overcome the above challenges. In the objective space, the GRU-based prediction strategy (GP) captures patterns of population change, predicts its distribution in new environments, and subsequently maps the results to the decision space;The multi-information hybrid exploration strategy (MHE) takes the feature individual as the representative individual, adaptively guides the population evolution direction in the decision space, thereby enhancing the algorithm’s adaptability. Compared with five advanced algorithms on the non-cyclic dynamic benchmark test set (NCD), the proposed algorithm GPMHE has shown robust adaptation to dynamic environmental changes. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Optimal CPU scheduling in data centers via a finite-time distributed quantized coordination mechanism

arXiv

引用

arXiv 2021年

作者： Rikos, Apostolos I. Grammenos, Andreas Kalyvianaki, Evangelia Hadjicostis, Christoforos N. Charalambous, Themistoklis Johansson, Karl H. Division of Decision and Control Systems KTH Royal Institute of Technology StockholmSE-100 44 Sweden Department of Computer Science and Technology University of Cambridge Cambridge United Kingdom Alan Turing Institute London United Kingdom Department of Electrical and Computer Engineering University of Cyprus Nicosia1678 Cyprus Department of Electrical Engineering and Automation School of Electrical Engineering Aalto University Espoo02150 Finland

In this paper we analyze the problem of optimal task scheduling for data centers. Given the available resources and tasks, we propose a fast distributed iterative algorithm which operates over a large scale network of nodes and allows each of the interconnected nodes to reach agreement to an optimal solution in a finite number of time steps. More specifically, the algorithm (i) is guaranteed to converge to the exact optimal scheduling plan in a finite number of time steps and, (ii) once the goal of task scheduling is achieved, it exhibits distributed stopping capabilities (i.e., it allows the nodes to distributely determine whether they can terminate the operation of the algorithm). Furthermore, the proposed algorithm operates exclusively with quantized values (i.e., the information stored, processed and exchanged between neighboring agents is subject to deterministic uniform quantization) and relies on event-driven updates (e.g., to reduce energy consumption, communication bandwidth, network congestion, and/or processor usage). We also provide examples to illustrate the operation, performance, and potential advantages of the proposed algorithm. Finally, by using extensive empirical evaluations through simulations we show that the proposed algorithm exhibits state-of-the-art performance. Copyright © 2021, The Authors. All rights reserved.

关键词： Multitasking

来源：评论

学校读者我要写书评

暂无评论

A Simplified Variant for Graph Convolutional Network Based Knowledge Graph Completion Model

A Simplified Variant for Graph Convolutional Network Based K...

引用

IEEE International Conference on Data science in Cyberspace (DSC)

作者： Yashen Wang Qiang Li Yi Zhang Xuecheng Zhang Zhuoya Ju Jian Sun National Engineering Laboratory for Risk Perception and Prevention (RPP) Key Laboratory of Cognition and Intelligence Technology (CIT) China Academy of Electronics and Information Technology Artificial Intelligence Institute of CETC Beijing China The State Key Laboratory for Management and Control of Complex Systems Scientific and Technological Innovation Center of ARI Institute of Automation Chinese Academy of Sciences Beijing China CETC Academy of Electronics and Information Technology Group Co. Ltd. Beijing China Khoury College of Computer Science Northeastern University U.S.A Scientific and Technological Innovation Center of ARI Beijing China Qi An Xin Technology Group Inc. Beijing China

Knowledge graphs (KGs) serve as useful resources for various applications including machine learning, data mining, and artificial intelligence. Knowledge Graph Completion (KGC) aims at reasoning over known (observed) facts and infer the missing (unobserved) relationships, to improve KG's coverage. Many recent works have laid stress on leveraging Graph Convolutional Networks (GCNs) for KGC task, which obtain good representation learning ability for graph-structured data, and have achieved satisfactory results. However, GCN-based researches continue to improve these lines of models by introducing an increasingly complex feature space. Especially, the hyper-parameter space of conventional GCN-based KGC model is too huge, resulting in low computational efficiency and excessive storage pressure. To overcome this problem, this paper investigates a simplified and generic variant for GCN-based KGC model, and shows that simple changes in the architecture of the underlying architecture (with a Subtraction Operator and an Addition Operator), can compte with state-of-the-art GCN-based models. Therefore, this paper proposes a easy-to-accomplish plug-in unit, which could be loaded into any current GCN-based KGC architectures, and help them maximize the maintenance of native model's original performance while significantly reducing parameter scale.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Intelligent production of the future - first results of a survey 17

Intelligent production of the future - first results of a su...

引用

17th IMEKO TC 10 and EUROLAB Virtual Conference: Global Trends in Testing, Diagnostics and Inspection for 2030

作者： Nick, Gábor Szaller, Ádám Zsolt János, Viharos Várgedő, Tamás Bányai, Dóra Fries, Christian Fechter, Manuel EPIC InnoLabs Nonprofit Ltd Budapest Hungary Institute for Computer Science and Control Budapest Hungary Budapest University of Technology and Economics Budapest Hungary Széchenyi University Research Center of Vehicle Industry Győr Hungary Fraunhofer-Institute for Manufacturing Engineering and Automation IPA Stuttgart Germany John von Neumann University Kecskemét Hungary University of Stuttgart Institute of Industrial Manufacturing and Management IFF Germany

Witnessing the unprecedented scale and speed of industry transformation due to digitization in general and the emergence of smart solutions in all aspects of manufacturing in particular, it is well justified to deal with the question of what production of the future will look like. How intelligent will it be when the hard challenges and disruptive effects of the changes will be overcome, and what are the chances to meet the critical requirements of collaboration and cooperation, flexibility and competitiveness? What are the technological and management tools to avoid being stuck in the so-called pilot purgatory? These issues are addressed in an international survey based on a questionnaire specifically tailored to conclude to viable options and recommendations for industrial companies. The results that are mostly in conformity with those published in the literature show that there is yet a lot to do to facilitate a definite turn in the mindset of the actors and to make them realize the relevance of simultaneous and continuous cultural and technological development. © Global Trends in Testing, Diagnostics and Inspection for *** rights reserved.

关键词： Manufacture

来源：评论

学校读者我要写书评

暂无评论

Robust Iterative Learning control for Spatially Interconnected Systems using 2D control Theory

Robust Iterative Learning Control for Spatially Interconnect...

引用

European control Conference (ECC)

作者： Bartłomiej Sulikowski Krzysztof Gałkowski Daniel Trzciński Eric Rogers Anton Kummert Institute of Control and Computation Engineering University of Zielona Góra Zielona Góra Poland Institute of Automation Electronic and Electrical Engineering University of Zielona Góra Zielona Góra Poland Department of Electronics and Computer Science University of Southampton Southampton UK Faculty of Electrical Information and Media Engineering University of Wuppertal Wuppertal Germany

This paper develops a class of iterative learning control (ILC) laws for a subclass of uncertain spatially interconnected systems. Model uncertainties appear both in the state and the output equation of the dynamics modeled in the 2D systems setting to which existing results are not applicable. The first stage is to write the dynamics in 2D model form. Then the stability theory for a distinct class of 2D systems known as repetitive processes is used to develop the ILC law in the case of differential dynamics. This analysis results in a design algorithm that can be applied using linear matrix inequalities.

关键词：

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：