检索结果-内蒙古大学图书馆

IEEE International Conference on Robotics and Biomimetics

作者： Yijie Li Hewei Wang Zhenqi Li Shaofan Wang Soumyabrata Dev Guoyu Zuo Beijing-Dublin International College Beijing University of Technology Beijing China Faculty of Information Technology Beijing University of Technology Beijing China School of Computer Science University College Dublin Dublin Ireland Faculty of Information Technology Beijing University of Technology Beijing Key Laboratory of Computing Intelligence and Intelligent Systems Beijing China

When the Convolutional neural network (CNN) has been introduced for computer vision, many researches use CNN-based model to perform salient object detection (SOD). In recent years, The feature pyramid network (FPN) based structure is more popular for salient object detection tasks. In this paper, to improve the overall performance of salient object detection tasks, we propose a dual attention aggregating network (DAANet), which is an FPN-based deep convolutional neural network with a dual attention aggregation module (DAAM) and dilated refinement block (DRB). The DRB module uses convolutions with different dilation rates to expand the receptive field. The DAAM considers the salient map prediction from the low-level output as pseudo-attention which can efficiently aggregate multi-scale information. The convolution block attention module (CBAM) in DAAM can refine the aggregation of pseudo-attention which enables better performance. We evaluate DAANet on six benchmark datasets that prove the effectiveness of DAANet and its components. Our implementation can be found at: https://***/Att100/DAANet.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Convolutional Correlation Filter Learning Toward Robust Visual Object Tracking

Deep Convolutional Correlation Filter Learning Toward Robust...

引用

Chinese Control and Decision Conference, CCDC

作者： Tayssir Bouraffa Zihang Feng Yuxuan Wang Liping Yan Yuanqing Xia Bo Xiao School of Automation Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology Beijing P. R. China School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing P. R. China

ISBN: (纸本)9781665478977

Recently, convolutional neural network has been pervasively adopted in visual object tracking for its potential in discriminating the target from the surrounding background. Most of the visual object trackers extract deep features from a specific layer, generally from the last convolutional layer. However, these trackers are less effective, especially when the target undergoes drastic appearance variations caused by the presence of different challenging situations, such as occlusion, illumination change, background clutter and so on. In this research paper, a novel tracking algorithm is developed by introducing an elastic net constraint and a contextual information into the convolutional network to successfully track the desired target throughout a video sequence. Hierarchical features are extracted from the shallow and the deep convolutional layers to further improve the tracking accuracy and robustness. As the deep convolutional layers capture important semantic information, they are more robust to the target appearance variations. As for the shallow convolutional layers, they encode significant spatial details, which are more accurate to precisely localize the desired target. Moreover, Peak–Strength Context–Aware correlation filters are embedded to each convolutional layer output that produce multi–level convolutional response maps to collaboratively identify the estimated position of the target in a coarse–to–fine manner. Quantitative and qualitative experiments are performed on the widely used benchmark, the OTB–2015 dataset that shows impressive results compared to the state–of–the–art trackers.

关键词： Visualization Target tracking Correlation Semantics Video sequences Feature extraction Information filters

来源：评论

学校读者我要写书评

暂无评论

Resolution Switchable Networks for Runtime Efficient Image Recognition 16th

Resolution Switchable Networks for Runtime Efficient Image R...

引用

16th European Conference on Computer Vision, ECCV 2020

作者： Wang, Yikai Sun, Fuchun Li, Duo Yao, Anbang State Key Lab on Intelligent Technology and Systems Department of Computer Science and Technology Tsinghua University Beijing China Cognitive Computing Laboratory Intel Labs China Beijing China

ISBN: (纸本)9783030585549

We propose a general method to train a single convolutional neural network which is capable of switching image resolutions at inference. Thus the running speed can be selected to meet various computational resource limits. Networks trained with the proposed method are named Resolution Switchable Networks (RS-Nets). The basic training framework shares network parameters for handling images which differ in resolution, yet keeps separate batch normalization layers. Though it is parameter-efficient in design, it leads to inconsistent accuracy variations at different resolutions, for which we provide a detailed analysis from the aspect of the train-test recognition discrepancy. A multi-resolution ensemble distillation is further designed, where a teacher is learnt on the fly as a weighted ensemble over resolutions. Thanks to the ensemble and knowledge distillation, RS-Nets enjoy accuracy improvements at a wide range of resolutions compared with individually trained models. Extensive experiments on the ImageNet dataset are provided, and we additionally consider quantization problems. Code and models are available at https://***/yikaiw/RS-Nets. © 2020, Springer Nature Switzerland AG.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Learning Network-Invariant and Label-Discriminative Representations for Cross-Network Node Classification

Learning Network-Invariant and Label-Discriminative Represen...

引用

2021 China Automation Congress, CAC 2021

作者： Yang, Linyao Xu, Yancai Hou, Jiachen Dai, Yuxin Lv, Chen The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China Qingdao Academy of Intelligent Industries Qingdao China Institute of Systems Engineering Macau University of Science and Technology China School of Electrical Engineering and Automation Wuhan University Wuhan China China Electric Power Research Institute Beijing China

ISBN: (纸本)9781665426473

Networks are ubiquitous data structures in the real world. The accurate and efficient analysis of networks is critical to realizing many intelligent network-based services. However, most existing network analysis methods are developed for single networks and require a lot of labeled data, which is costly and time-consuming to acquire. Transfer learning has been widely accepted as an effective paradigm for tackling this problem by reusing the model trained on a supervised task. However, transfer learning on the non-euclidean network data has been investigated by no more than a few studies. To realize accurate node classification based on the knowledge learned from the labeled source network, this paper proposes to learn network-invariant and label-discriminative representations based on graph embedding and linear discriminant analysis. Specifically, we embed the source and target networks into adjacent vector spaces based on the graph attention network by minimizing the Sinkhorn distributional distances between their embeddings. To obtain label-discriminative features for learning better classification models, we then utilize a transferable linear discriminative analysis method to project the embeddings into label-discriminative subspaces. In the end, a support vector machine model trained on the labeled source network is utilized to classify the target nodes. Experiments on two pairs of networks illustrate that our method achieves the best performance and evaluates the effectiveness of the proposed modules. © 2021 IEEE

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Nonlinear Cooperative Output Regulation with Input Delay Compensation

arXiv

引用

arXiv 2024年

作者： Zheng, Shiqi Ahn, Choon Ki Jiang, Xiaowei Yan, Huaicheng Shi, Peng The School of Automation China University of Geosciences Wuhan430079 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China The Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China The Shaoyang Institute of Advanced Manufacturing Technology Shaoyang422000 China The School of Electrical Engineering Korea University Seoul136-701 Korea Republic of The Key Laboratory of Smart Manufacturing in Energy Chemical Process of Ministry of Education East China University of Science and Technology Shanghai200237 China The School of Electrical and Mechanical Engineering The University of Adelaide AdelaideSA5005 Australia

This paper investigates the cooperative output regulation (COR) of nonlinear multi-agent systems (MASs) with long input delay based on periodic event-triggered mechanism. Compared with other mechanisms, periodic event-triggered control can automatically guarantee a Zeno-free behavior and avoid the continuous monitoring of triggered conditions. First, a new periodic event-triggered distributed observer, which is based on the fully asynchronous communication data, is proposed to estimate the leader information. Second, a new distributed predictor feedback control method is proposed for the considered nonlinear MASs with input delay. By coordinate transformation, the MASs are mapped into new coupled ODE-PDE target systems with some disturbance-like terms. Then, we show that the COR problem is solvable. At last, to further save the communication resource, a periodic event-triggered mechanism is considered in the sensor-to-controller transmission in every agent. A new periodic event-triggered filter is proposed to deal with the periodic event-triggered feedback data. The MASs with input delay are mapped into coupled ODE-PDE target systems with sampled data information. Then, Lyapunov-Krasovskii functions are constructed to demonstrate the exponential stability of the MASs. Simulations verify the validity of the proposed results. © 2024, CC BY-NC-ND.

关键词： Feedback control

来源：评论

学校读者我要写书评

暂无评论

AI Graphical Programming Learning Platform for Children

AI Graphical Programming Learning Platform for Children

引用

2021 China Automation Congress, CAC 2021

作者： Zhao, Hongxia Liu, Xiwei Gong, Xiaoyan Li, Qiang Jing, Sifeng Xue, Yaofeng The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Institute of Smart Education Systems Qingdao Academy of Intelligent Industries Qingdao China University of Chinese Academy of Sciences Beijing China Shanghai Engineering Research Center of Digital Education Equipment Department of Education Information Technology East China Normal University Shanghai China

ISBN: (纸本)9781665426473

In this era of rapid development of artificial intelligence, the truth of competition in the future is the talent. Countries all over the world attach great importance to the programming and artificial intelligence education of children. In the future, the theoretical development and practical application of this emerging field will usher in a period of rapid development. This paper presents an artificial intelligence graphical programming learning platform based on Jetson Nano, which combines artificial intelligence education with modular software programming, provides students with a more open, intelligent, and interesting programming environment through the cross-platform development mode of "cloud service + intelligent hardware", and adopts visual programming to reduce the difficulty of artificial intelligence programming. The platform can fully tap learning resources, reduce education costs, and make artificial intelligence education more intuitive and humanized. © 2021 IEEE

关键词： Computer graphics

来源：评论

学校读者我要写书评

暂无评论

Soft-Landing Dynamics of a Type of Four-Legged Space Lander

SSRN

引用

SSRN 2024年

作者： Shi, Tengfei Shi, Tengfei Yang, Yinping Zhang, Zhijuan Liu, Cuicui Liu, Caishan Ma, Daolin Applied Mechanics and Structure Safety Key Laboratory of Sichuan Province School of Mechanics and Aerospace Engineering Southwest Jiaotong University Chengdu610031 China State Key Laboratory for Turbulence and Complex Systems College of Engineering Peking University Beijing100871 China Institute of Dynamics and Control College of Mechanical Engineering and Applied Electronics Technology Beijing University of Technology Beijing100871 China China Academy of Space Technology Beijing100094 China School of Naval Architecture Ocean and Civil Engineering Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of Marine Intelligent Equipment and System Ministry of Education Shanghai200240 China

Analyzing the landing dynamics response is essential for enhancing the success rate of surface explorations on Mars, the moon, or asteroids. This paper develops a comprehensive dynamics model for a space lander equipped with four sets of buffer legs, each consisting of a primary strut, two secondary struts, and a footpad, during its soft landing process. The degrees of freedom of the main body and the footpads are defined as generalized coordinates to describe the motion of the space lander. The compression force of the buffer struts is obtained by interpolating real experimental data, and the contact force between the footpad and the ground is calculated using Archimedes law for granular media. Then, the dynamical model for the lander in terms of minimal degrees of freedom can be constructed by applying the Lagrange equations of the second kind. The proposed dynamics model is validated by the experiments of a single-legged lander vertical touchdown and a four-legged lander free touchdown. Moreover, histories of buffer force, acceleration of the main body, and other key physical quantities are computed to investigate the landing process. This highly efficient and accurate dynamics model provides a method to perform extensive simulations to design and optimize a soft landing process. © 2024, The Authors. All rights reserved.

关键词： Landing

来源：评论

学校读者我要写书评

暂无评论

Emotion Recognition Empowered Human-Computer Interaction with Domain Adaptation Network

引用

IEEE Transactions on Consumer Electronics 2024年

作者： Xu, Xu Fu, Chong Chen, Junxin Northeastern University School of Computer Science and Engineering Shenyang110004 China Dalian University of Technology China The School of Software Dalian116621 China Northeastern University School of Computer Science and Engineering Shenyang110004 China Northeastern University Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Shenyang110819 China Ministry of Education Engineering Research Center of Security Technology of Complex Network System Shenyang110004 China Dalian University of Technology School of Software Dalian116621 China

Multi-modal emotion recognition plays a vital role in the human-computer interaction (HCI) for consumer electronics. Nowadays, many studies have developed multi-modal fusion algorithms for this ***, two challenging issues remain unsolved, i.e., inefficient multi-modal feature fusion and unclear distance in feature *** this end, we develop a novel framework, namely LAFDA-Net, for cross-subject emotion recognition using EEG and eye movement *** is based on low-rank fusion and domain adaptation *** specifically, the multi-modal signals are input into the feature extraction branch in parallel to generate ***, these features are fused by the low-rank fusion branch, reducing complexity and avoiding ***, the fused features are flattened and sent to the classification branch to determine the emotion *** training, these features are input into the domain adaptive branch to bridge the gap between the source domain and target *** benchmark datasets, i.e., SEED, SEED-IV, and SEED-V, are employed for performance *** results demonstrate that the proposed LAFDA-Net is robust, effective, and has advantages over peer methods. © 1975-2011 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Multi-objective Evolutionary Algorithm Based Graph Neural Network Architecture Search 11th

Multi-objective Evolutionary Algorithm Based Graph Neural Ne...

引用

11th International Symposium on Computational Intelligence and Industrial Applications, ISCIIA 2024

作者： He, Lianyi Liu, Xiaobo Xiang, Hongbo Wang, Guangjun School of Automation China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China Key Laboratory of Geological Survey and Evaluation of Ministry of Education China University of Geosciences Wuhan430074 China

ISBN: (纸本)9789819647521

Graph Neural Networks (GNN) has become a powerful graph data processing method, which has been widely used in node classification, link prediction, and other graph analysis tasks. Due to the diversity and complexity of graph structures and information propagation, as well as the handling of heterogeneous graphs, etc., the design of GNNs presents many challenges. The existing methods have high classification accuracy, but their structures are very complex. In this paper, a graph neural network architecture search framework named MO-GNN, which is based on multi-objective evolutionary algorithm is proposed. Furthermore, a weight sharing strategy MO-GNN-WS is proposed to reduce the resource consumption caused by weight training of different architectures. To verify the performance of the proposed algorithm, experiments on four popular graph datasets are used for transduction and induction tasks. The experimental results show that the MO-GNN-WS algorithm outperforms the most advanced neural network architecture search methods in terms of classification accuracy and resource consumption. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Data Sharing

来源：评论

学校读者我要写书评

暂无评论

Noise Reduction Method of Transient Electromagnetic Signal Based on VMD-ICA

Noise Reduction Method of Transient Electromagnetic Signal B...

引用

第40届中国控制会议

作者： Guangjun Wang Zhaohui Wang Hui Jiang Lan Cui Chengxiang Ding Xinzhao Qi Yutao Cheng School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems School of Law Zhongnan University of Economics and Law

Aiming at the problems of traditional transient electromagnetic signal noise reduction methods that have poor noise reduction effects and excessive noise reduction to varying degrees,a transient electromagnetic signal noise reduction algorithm based on VMD and ICA is *** use VMD decomposition to adaptively decompose the original signal into multiple intrinsic mode functions（IMF）,select the noise component according to the autocorrelation criterion,and then use the independent component analysis algorithm based on kurtosis maximization to achieve transient electromagnetic signal best *** with the traditional EMD noise reduction method,we found that the method proposed in this paper not only has a good noise reduction effect,but also retains more signal *** algorithm proposed in this paper is an effective method for noise reduction of transient electromagnetic signals,and it has important value for transient electromagnetic detection to improve detection accuracy.

关键词： TEM noise reduction VMD ICA autocorrelation

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：