检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Zhao, Chen Yang, Jiaqi Xiong, Xin Zhu, Angfan Cao, Zhiguo Li, Xin National Key Laboratory of Science and Technology on Multi-spectral Information Processing School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China School of Computer Science Northwestern Polytechnical University Xi’an710072 China Lane Department of Computer Science and Electrical Engineering West Virginia University Morgantown26506 United States

Point cloud analysis is a fundamental task in 3D computer vision. Most previous works have conducted experiments on synthetic datasets with well-aligned data;while real-world point clouds are often not pre-aligned. How to achieve rotation invariance remains an open problem in point cloud analysis. To meet this challenge, we propose an approach toward achieving rotation-invariant (RI) representations by combining local geometry with global topology. In our local-global-representation (LGR)-Net, we have designed a two-branch network where one stream encodes local geometric RI features and the other encodes global topology-preserving RI features. Motivated by the observation that local geometry and global topology have different yet complementary RI responses in varying regions, two-branch RI features are fused by an innovative multi-layer perceptron (MLP) based attention module. To the best of our knowledge, this work is the first principled approach toward adaptively combining global and local information under the context of RI point cloud analysis. Extensive experiments have demonstrated that our LGR-Net achieves the state-of-the-art performance on various rotation-augmented versions of ModelNet40, ShapeNet, ScanObjectNN, and S3DIS. Copyright © 2019, The Authors. All rights reserved.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

Multi-view multi-instance multi-label learning based on collaborative matrix factorization

arXiv

引用

arXiv 2019年

作者： Xing, Yuying Yu, Guoxian Domeniconi, Carlotta Wang, Jun Zhang, Zili Guo, Maozu College of Computer and Information Science Southwest University Chongqing China Hubei Key Laboratory of Intelligent Geo-Information Processing China University of Geosciences Wuhan China Department of Computer Science George Mason University FairfaxVA United States School of Information Technology Deakin University GeelongVIC Australia School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture Beijing China

Multi-view Multi-instance Multi-label Learning(M3L) deals with complex objects encompassing diverse instances, represented with different feature views, and annotated with multiple labels. Existing M3L solutions only partially explore the inter or intra relations between objects (or bags), instances, and labels, which can convey important contextual information for M3L. As such, they may have a compromised performance. In this paper, we propose a collaborative matrix factorization based solution called M3Lcmf. M3Lcmf first uses a heterogeneous network composed of nodes of bags, instances, and labels, to encode different types of relations via multiple relational data matrices. To preserve the intrinsic structure of the data matrices, M3Lcmf collaboratively factorizes them into low-rank matrices, explores the latent relationships between bags, instances, and labels, and selectively merges the data matrices. An aggregation scheme is further introduced to aggregate the instance-level labels into bag-level and to guide the factorization. An empirical study on benchmark datasets show that M3Lcmf outperforms other related competitive solutions both in the instance-level and bag-level prediction. Copyright © 2019, The Authors. All rights reserved.

关键词： Matrix factorization

来源：评论

学校读者我要写书评

暂无评论

STUDY OF DENSE NETWORK APPROACHES FOR SPEECH EMOTION RECOGNITION

STUDY OF DENSE NETWORK APPROACHES FOR SPEECH EMOTION RECOGNI...

引用

IEEE International Conference on Acoustics, Speech and Signal processing

作者： Mohammed Abdelwahab Carlos Busso Multimodal Signal Processing (MSP) Laboratory Department of Electrical Computer Engineering The University of Texas at Dallas Richardson TX 75080 USA

ISBN: (纸本)9781538646595

Deep neural networks have been proven to be very effective in various classification problems and show great promise for emotion recognition from speech. Studies have proposed various architectures that further improve the performance of emotion recognition systems. However, there are still various open questions regarding the best approach to building a speech emotion recognition system. Would the system's performance improve if we have more labeled data? How much do we benefit from data augmentation? What activation and regularization schemes are more beneficial? How does the depth of the network affect the performance? We are collecting the MSP-Podcast corpus, a large dataset with over 30 hours of data, which provides an ideal resource to address these questions. This study explores various dense architectures to predict arousal, valence and dominance scores. We investigate varying the training set size, width, and depth of the network, as well as the activation functions used during training. We also study the effect of data augmentation on the network's performance. We find that bigger training set improves the performance. Batch normalization is crucial to achieving a good performance for deeper networks. We do not observe significant differences in the performance in residual networks compared to dense networks.

关键词： Speech emotion recognition Deep Neural Networks emotion recognition System performance Speech Network Activating function

来源：评论

学校读者我要写书评

暂无评论

NOVEL REALIZATIONS OF SPEECH-DRIVEN HEAD MOVEMENTS WITH GENERATIVE ADVERSARIAL NETWORKS

NOVEL REALIZATIONS OF SPEECH-DRIVEN HEAD MOVEMENTS WITH GENE...

引用

IEEE International Conference on Acoustics, Speech and Signal processing

作者： Najmeh Sadoughi Carlos Busso Multimodal Signal Processing (MSP) Laboratory Department of Electrical and Computer Engineering The University of Texas at Dallas Richardson TX 75080 USA

ISBN: (纸本)9781538646595

Head movement is an integral part of face-to-face communications. It is important to investigate methodologies to generate naturalistic movements for conversational agents (CAs). The predominant method for head movement generation is using rules based on the meaning of the message. However, the variations of head movements by these methods are bounded by the predefined dictionary of gestures. Speech-driven methods offer an alternative approach, learning the relationship between speech and head movements from real recordings. However, previous studies do not generate novel realizations for a repeated speech signal. Conditional generative adversarial network (GAN) provides a framework to generate multiple realizations of head movements for each speech segment by sampling from a conditioned distribution. We build a conditional GAN with bidirectional long-short term memory (BLSTM), which is suitable for capturing the long-short term dependencies of time-continuous signals. This model learns the distribution of head movements conditioned on speech prosodic features. We compare this model with a dynamic Bayesian network (DBN) and BLSTM models optimized to reduce mean squared error (MSE) or to increase concordance correlation. The objective evaluations and subjective evaluations of the results showed better performance for the conditional GAN model compared with these baseline systems.

关键词： Head movements synthesis speech-driven animation conditional generative adversarial networks Head Movements Speech Head Conditional Voice Signal Mean square error

来源：评论

学校读者我要写书评

暂无评论

Learning Robust Facial Landmark Detection via Hierarchical Structured Ensemble

Learning Robust Facial Landmark Detection via Hierarchical S...

引用

International Conference on computer Vision (ICCV)

作者： Xu Zou Sheng Zhong Luxin Yan Xiangyun Zhao Jiahuan Zhou Ying Wu College of Life Science and Technology Huazhong University of Science & Technology (HUST) Wuhan China National Key Laboratory of Science & Technology on Multi-Spectral Information Processing HUST Wuhan China School of Aritificial Intelligence and Automation HUST Wuhan China Department of Electrical and Computer Engineering Northwestern University IL USA

ISBN: (数字)9781728148038

ISBN: (纸本)9781728148045

Heatmap regression-based models have significantly advanced the progress of facial landmark detection. However, the lack of structural constraints always generates inaccurate heatmaps resulting in poor landmark detection performance. While hierarchical structure modeling methods have been proposed to tackle this issue, they all heavily rely on manually designed tree structures. The designed hierarchical structure is likely to be completely corrupted due to the missing or inaccurate prediction of landmarks. To the best of our knowledge, in the context of deep learning, no work before has investigated how to automatically model proper structures for facial landmarks, by discovering their inherent relations. In this paper, we propose a novel Hierarchical Structured Landmark Ensemble (HSLE) model for learning robust facial landmark detection, by using it as the structural constraints. Different from existing approaches of manually designing structures, our proposed HSLE model is constructed automatically via discovering the most robust patterns so HSLE has the ability to robustly depict both local and holistic landmark structures simultaneously. Our proposed HSLE can be readily plugged into any existing facial landmark detection baselines for further performance improvement. Extensive experimental results demonstrate our approach significantly outperforms the baseline by a large margin to achieve a state-of-the-art performance.

关键词： Robustness Heating systems Detectors Face Shape Mathematical model

来源：评论

学校读者我要写书评

暂无评论

A chaotic artificial bee colony algorithm based on lévy search

A chaotic artificial bee colony algorithm based on lévy sea...

引用

作者： Lin, Shijie Dong, Chen Wang, Zhiqiang Guo, Wenzhong Chen, Zhenyi Ye, Yin College of Mathematics and Computer Science Fuzhou University Fuzhou350116 China Key Laboratory of Information Security of Network Systems Fuzhou350116 China Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou350116 China Department of Electrical Engineering University of South Florida TampaFL33620 United States

A Lévy search strategy based chaotic artificial bee colony algorithm (LABC) is proposed in this paper. The chaotic sequence, global optimal mechanism and Lévy flight mechanism were introduced respectively into the initialization, the employed bee search and the onlooker bee search. The experiments show that the proposed algorithm performed better in convergence speed, global search ability and optimization accuracy than other improved ABC. Copyright © 2018 The Institute of Electronics, Information and Communication Engineers.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Neural signatures of motor skill in the resting brain

arXiv

引用

arXiv 2019年

作者： Özdenizci, Ozan Meyer, Timm Wichmann, Felix Peters, Jan Schölkopf, Bernhard Çetin, Müjdat Grosse-Wentrup, Moritz Department of Electrical and Computer Engineering Northeastern University BostonMA United States Signal Processing and Information Systems Laboratory Faculty of Engineering and Natural Sciences Sabancı University Istanbul Turkey Max Planck Institute for Intelligent Systems Tübingen Germany Faculty of Science University of Tübingen Bernstein Center for Computational Neuroscience Tübingen Tübingen Germany FG Intelligente Autonome Systeme Technische Universität Darmstadt Darmstadt Germany Department of Electrical and Computer Engineering University of Rochester RochesterNY United States Research Group Neuroinformatics Faculty of Computer Science University of Vienna Vienna Austria

Stroke-induced disturbances of large-scale cortical networks are known to be associated with the extent of motor deficits. We argue that identifying brain networks representative of motor behavior in the resting brain would provide significant insights for current neurorehabilitation approaches. Particularly, we aim to investigate the global configuration of brain rhythms and their relation to motor skill, instead of learning performance as broadly studied. We empirically approach this problem by conducting a three-dimensional physical space visuomotor learning experiment during electroencephalographic (EEG) data recordings with thirty-seven healthy participants. We demonstrate that across-subjects variations in average movement smoothness as the quantified measure of subjects' motor skills can be predicted from the global configuration of resting-state EEG alpha-rhythms (8-14 Hz) recorded prior to the experiment. Importantly, this neural signature of motor skill was found to be orthogonal to (independent of) task- as well as to learning-related changes in alpha-rhythms, which we interpret as an organizing principle of the brain. We argue that disturbances of such configurations in the brain may contribute to motor deficits in stroke, and that reconfiguring stroke patients' brain rhythms by neurofeedback may enhance post-stroke neurorehabilitation. Copyright © 2019, The Authors. All rights reserved.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Social Energy:Mining Energy From the Society

引用

IEEE/CAA Journal of Automatica Sinica 2017年第3期4卷 466-482页

作者： Jun Jason Zhang David Wenzhong Gao Yingchen Zhang Xiao Wang Xiangyang Zhao Dongliang Duan Xiaoxiao Dai Jun Hao Fei-Yue Wang Department of Electrical and Computer Engineering Ritchie School of Engineering and Computer ScienceUniversity of Denver IEEE National Renewable Energy Laboratory Qingdao Academy of Intelligent Industries(QAII) QingdaoShandongChinaand SKL-MCCSCASIA School of Automation Science and Electrical Engineering Beihang University Department of Electrical and Computer Engineering College of Engineering and Applied ScienceUniversity of Wyoming State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences(SKL-MCCSCASIA) Research Center of Computational Experiments and Parallel Systems National University of Defense Technology

The inherent nature of energy,i.e.,physicality,sociality and informatization,implies the inevitable and intensive interaction between energy systems and social *** this perspective,we define "social energy" as a complex sociotechnical system of energy systems,social systems and the derived artificial virtual systems which characterize the intense intersystem and intra-system *** recent advancement in intelligent technology,including artificial intelligence and machine learning technologies,sensing and communication in Internet of Things technologies,and massive high performance computing and extreme-scale data analytics technologies,enables the possibility of substantial advancement in socio-technical system optimization,scheduling,control and *** this paper,we provide a discussion on the nature of energy,and then propose the concept and intention of social energy systems for electrical power.A general methodology of establishing and investigating social energy is proposed,which is based on the ACP approach,i.e., "artificial systems"(A), "computational experiments"(C) and "parallel execution"(P),and parallel system methodology.A case study on the University of Denver(DU) campus grid is provided and studied to demonstrate the social energy *** the concluding remarks,we discuss the technical pathway,in both social and nature sciences,to social energy,and our vision on its future.

关键词： ACP distribution locational marginal pricing intelligent operation in power systems parallel control parallel intelligence parallel management social energy socio-technical energy systems

来源：评论

学校读者我要写书评

暂无评论

FLEXIBLE NETWORK BINARIZATION WITH LAYER-WISE PRIORITY

FLEXIBLE NETWORK BINARIZATION WITH LAYER-WISE PRIORITY

引用

IEEE International Conference on Image processing

作者： He Wang Yi Xu Bingbing Ni Lixue Zhuang Hongteng Xu Shanghai Key Laboratory of Digital Media Processing and Transmissions Shanghai Jiao Tong University Department of Electrical and Computer Engineering Duke University

How to effectively approximate real-valued parameters with binary codes plays a central role in neural network binarization. In this work, we reveal an important fact that binarizing different layers has a widely varied effect on the compression ratio of network and the loss of performance. Based on this fact, we propose a novel and flexible neural network binarization method by introducing the concept of layer-wise priority which binarizes parameters in inverse order of their layer depth. In each training step, our method selects a specific network layer, minimizes the discrepancy between the original real-valued weights and its binary approximations following block coordinate descent scheme. During the iteration of the above process, it is significant that we can flexibly decide whether to binarize the remaining floating layers or not and explore a trade-off between the loss of performance and the compression ratio of model. The resulting binary network is applied for efficient pedestrian detection. Experimental results on several benchmarks show that under the same compression ratio, the model compressed by our method achieves much lower miss rate and faster detection speed than those obtained by the state-of-the-art neural network binarization method.

关键词： Neural networks Training Task analysis Convolution Optimization Computational modeling Image coding

来源：评论

学校读者我要写书评

暂无评论

A Novel modeling approach for all-dielectric metasurfaces using deep neural networks

arXiv

引用

arXiv 2019年

作者： An, Sensong Fowler, Clayton Zheng, Bowen Shalaginov, Mikhail Y. Tang, Hong Li, Hang Zhou, Li Ding, Jun Agarwal, Anuradha Murthy Rivero-Baleine, Clara Richardson, Kathleen A. Gu, Tian Hu, Juejun Zhang, Hualiang Department of Electrical & Computer Engineering University of Massachusetts Lowell LowellMA United States Department of Materials Science & Engineering Massachusetts Institute of Technology CambridgeMA United States Shanghai Key Laboratory of Multidimensional Information Processing East China Normal University Shanghai China Lockheed Martin Corporation OrlandoFL United States CREOL University of Central Florida OrlandoFL United States

Metasurfaces have become a promising means for manipulating optical wavefronts in flat and high-performance optical devices. Conventional metasurface device design relies on trial-and-error methods to obtain target electromagnetic (EM) response, an approach that demands significant efforts to investigate the enormous number of possible meta-atom structures. In this paper, a deep neural network approach is introduced that significantly improves on both speed and accuracy compared to techniques currently used to assemble metasurface-based devices. Our neural network approach overcomes three key challenges that have limited previous neural-network-based design schemes: input/output vector dimensional mismatch, accurate EM-wave phase prediction, as well as adaptation to 3-D dielectric structures, and can be generically applied to a wide variety of metasurface device designs across the entire electromagnetic spectrum. Using this new methodology, examples of neural networks capable of producing on-demand designs for meta-atoms, metasurface filters, and phase-change reconfigurable metasurfaces are demonstrated. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep neural networks

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：