检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Xu, Jiamiao Wang, Fangzhao Peng, Qinmu You, Xinge Wang, Shuo Jing, Xiao-Yuan Philip Chen, C.L. School of Electronic Information and Communications Huazhong University of Science and Technology Wuhan430074 China Shenzhen Huazhong University of Science and Technology Research Institute China State Key Laboratory of Software Engineering School of Computer Wuhan University China Department of Computer and Information Science Faculty of Science and Technology University of Macau 99999 China Dalian Maritime University Dalian116026 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100080 China

Low-rank Multi-view Subspace Learning (LMvSL) has shown great potential in cross-view classification in recent years. Despite their empirical success, existing LMvSL based methods are incapable of well handling view discrepancy and discriminancy simultaneously, which thus leads to the performance degradation when there is a large discrepancy among multi-view data. To circumvent this drawback, motivated by the block-diagonal representation learning, we propose Structured Low-rank Matrix Recovery (SLMR), a unique method of effectively removing view discrepancy and improving discriminancy through the recovery of structured low-rank matrix. Furthermore, recent low-rank modeling provides a satisfactory solution to address data contaminated by predefined assumptions of noise distribution, such as Gaussian or Laplacian distribution. However, these models are not practical since complicated noise in practice may violate those assumptions and the distribution is generally unknown in advance. To alleviate such limitation, modal regression is elegantly incorporated into the framework of SLMR (term it MR-SLMR). Different from previous LMvSL based methods, our MR-SLMR can handle any zero-mode noise variable that contains a wide range of noise, such as Gaussian noise, random noise and outliers. The alternating direction method of multipliers (ADMM) framework and half-quadratic theory are used to efficiently optimize MR-SLMR. Experimental results on four public databases demonstrate the superiority of MR-SLMR and its robustness to complicated noise. Copyright © 2020, The Authors. All rights reserved.

关键词： Gaussian noise (electronic)

来源：评论

学校读者我要写书评

暂无评论

Anchor-based spatio-temporal attention 3D convolutional networks for dynamic 3D point cloud sequences

arXiv

引用

arXiv 2020年

作者： Wang, Guangming Chen, Muyao Liu, Hanwen Yang, Yehui Liu, Zhe Wang, Hesheng The Department of Automation Institute of Medical Robotics Key Laboratory of System Control and Information Processing Ministry of Education Key Laboratory of Marine Intelligent Equipment System of Ministry of Education Shanghai Jiao Tong University Shanghai200240 China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology China The Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China The Department of Computer Science and Technology University of Cambridge

With the rapid development of measurwement technology, LiDAR and depth cameras are widely used in the perception of the 3D environment. Recent learning based methods for robot perception most focus on the image or video, but deep learning methods for dynamic 3D point cloud sequences are underexplored. Therefore, developing efficient and accurate perception method compatible with these advanced instruments is pivotal to autonomous driving and service robots. An Anchor-based Spatio-Temporal Attention 3D Convolution operation (ASTA3DConv) is proposed in this paper to process dynamic 3D point cloud sequences. The proposed convolution operation builds a regular receptive field around each point by setting several virtual anchors around each point. The features of neighborhood points are firstly aggregated to each anchor based on the spatio-temporal attention mechanism. Then, anchor-based 3D convolution is adopted to aggregate these anchors' features to the core points. The proposed method makes better use of the structured information within the local region and learns spatio-temporal embedding features from dynamic 3D point cloud sequences. Anchor-based Spatio-Temporal Attention 3D Convolutional Neural Networks (ASTA3DCNNs) are built for classification and segmentation tasks based on the proposed ASTA3DConv and evaluated on action recognition and semantic segmentation tasks. The experiments and ablation studies on MSRAction3D and Synthia datasets demonstrate the superior performance and effectiveness of our method for dynamic 3D point cloud sequences. Our method achieves the state-of-the-art performance among the methods with dynamic 3D point cloud sequences as input on MSRAction3D and Synthia datasets. Copyright © 2020, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Geometric Filterless Photodetectors for Mid-infrared Spin Light

arXiv

引用

arXiv 2022年

作者： Wei, Jingxuan Chen, Yang Li, Ying Li, Wei Xie, Junsheng Lee, Chengkuo Novoselov, Kostya S. Qiu, Cheng-Wei Department of Electrical and Computer Engineering National University of Singapore Singapore117583 Singapore CAS Key Laboratory of Mechanical Behaviour and Design of Materials Department of Precision Machinery and Precision Instrumentation University of Science and Technology of China Hefei230026 China Interdisciplinary Center for Quantum Information State Key Laboratory of Modern Optical Instrumentation ZJU-Hangzhou Global Scientific and Technological Innovation Center Zhejiang University Hangzhou310027 China International Joint Innovation Center Key Lab of Advanced Micro/Nano Electronic Devices & Smart Systems of Zhejiang Zhejiang University Haining314400 China GPL Photonics Lab State Key Laboratory of Applied Optics Changchun Institute of Optics Fine Mechanics and Physics Chinese Academy of Sciences Changchun130033 China Center for Intelligent Sensors and MEMS National University of Singapore Singapore117608 Singapore Institute for Functional Intelligent Materials National University of Singapore Singapore117544 Singapore

Free-space circularly polarized light (CPL) detection, requiring polarizers and waveplates, has been well established, while such spatial degree of freedom is unfortunately absent in integrated on-chip optoelectronics. So far, those reported filterless CPL photodetectors suffer from the intrinsic small discrimination ratio, vulnerability to the non-CPL field components, and low responsivity. Here, we report a distinct paradigm of geometric photodetectors in mid-infrared exhibiting colossal discrimination ratio, close-to-perfect CPL-specific response, a zero-bias responsivity of 392 V/W at room temperature, and a detectivity of ellipticity down to 0.03o Hz−1/2. Our approach employs plasmonic nanostructures array with judiciously designed symmetry, assisted by graphene ribbons to electrically read their near-field optical information. This geometry-empowered recipe for infrared photodetectors provides a robust, direct, strict, and high-quality solution to on-chip filterless CPL detection and unlocks new opportunities for integrated functional optoelectronic devices. Copyright © 2022, The Authors. All rights reserved.

关键词： Photodetectors

来源：评论

学校读者我要写书评

暂无评论

Learning data-adaptive non-parametric kernels

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2020年第1期21卷 8590-8628页

作者： Fanghui Liu Xiaolin Huang Chen Gong Jie Yang Li Li Department of Electrical Engineering ESAT-STADIUS KU Leuven Belgium Institute of Image Processing and Pattern Recognition Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China PCA Lab Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology China and Department of Computing Hong Kong Polytechnic University Hong Kong SAR China Department of Automation BNRist Tsinghua University China

In this paper, we propose a data-adaptive non-parametric kernel learning framework in margin based kernel methods. In model formulation, given an initial kernel matrix, a data-adaptive matrix with two constraints is imposed in an entry-wise scheme. Learning this data-adaptive matrix in a formulation-free strategy enlarges the margin between classes and thus improves the model flexibility. The introduced two constraints are imposed either exactly (on small data sets) or approximately (on large data sets) in our model, which provides a controllable trade-off between model flexibility and complexity with theoretical demonstration. In algorithm optimization, the objective function of our learning framework is proven to be gradient-Lipschitz continuous. Thereby, kernel and classifier/regressor learning can be efficiently optimized in a unified framework via Nesterov's acceleration. For the scalability issue, we study a decomposition-based approach to our model in the large sample case. The effectiveness of this approximation is illustrated by both empirical studies and theoretical guarantees. Experimental results on various classification and regression benchmark data sets demonstrate that our non-parametric kernel learning framework achieves good performance when compared with other representative kernel learning based algorithms.

关键词： support vector machines non-parametric kernel learning gradient-Lipschitz continuous

来源：评论

学校读者我要写书评

暂无评论

Spherical interpolated convolutional network with distance-feature density for 3D semantic segmentation of point clouds

arXiv

引用

arXiv 2020年

作者： Wang, Guangming Yang, Yehui Zhang, Huixin Liu, Zhe Wang, Hesheng Department of Automation Insititue of Medical Robotics Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Jiao Tong University Shanghai200240 China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology China Department of Computer Science and Technology University of Cambridge United Kingdom

The semantic segmentation of point clouds is an important part of the environment perception for robots. However, it is difficult to directly adopt the traditional 3D convolution kernel to extract features from raw 3D point clouds because of the unstructured property of point clouds. In this paper, a spherical interpolated convolution operator is proposed to replace the traditional grid-shaped 3D convolution operator. This newly proposed feature extraction operator improves the accuracy of the network and reduces the parameters of the network. In addition, this paper analyzes the defect of point cloud interpolation methods based on the distance as the interpolation weight and proposes the self-learned distance-feature density by combining the distance and the feature correlation. The proposed method makes the feature extraction of spherical interpolated convolution network more rational and effective. The effectiveness of the proposed network is demonstrated on the 3D semantic segmentation task of point clouds. Experiments show that the proposed method achieves good performance on the ScanNet dataset and Paris-Lille-3D dataset. Copyright © 2020, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

A registration-aided domain adaptation network for 3D Point cloud based place recognition

arXiv

引用

arXiv 2020年

作者： Qiao, Zhijian Hu, Hanjiang Shi, Weiang Chen, Siyuan Liu, Zhe Wang, Hesheng Department of Automation Insititue of Medical Robotics Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Jiao Tong University Shanghai200240 China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology China Department of Mechanical Engineering Carnegie Mellon University United States Department of Computer Science and Technology University of Cambridge United Kingdom

In the field of large-scale SLAM for autonomous driving and mobile robotics, 3D point cloud based place recognition has aroused significant research interest due to its robustness to changing environments with drastic daytime and weather variance. However, it is time-consuming and effort-costly to obtain high-quality point cloud data for place recognition model training and ground truth for registration in the real world. To this end, a novel registration-aided 3D domain adaptation network for point cloud based place recognition is proposed. A structure-aware registration network is introduced to help to learn features with geometric information and a 6-DoFs pose between two point clouds with partial overlap can be estimated. The model is trained through a synthetic virtual LiDAR dataset through GTA-V with diverse weather and daytime conditions and domain adaptation is implemented to the real-world domain by aligning the global features. Our results outperform state-of-the-art 3D place recognition baselines or achieve comparable on the real-world Oxford RobotCar dataset with the visualization of registration on the virtual dataset. Copyright © 2020, The Authors. All rights reserved.

关键词： Three dimensional computer graphics

来源：评论

学校读者我要写书评

暂无评论

A review of uncertainty quantification in deep learning: Techniques, applications and challenges

arXiv

引用

arXiv 2020年

作者： Abdar, Moloud Pourpanah, Farhad Hussain, Sadiq Rezazadegan, Dana Liu, Li Ghavamzadeh, Mohammad Fieguth, Paul Cao, Xiaochun Khosravi, Abbas Rajendra Acharya, U. Makarenkov, Vladimir Nahavandi, Saeid Deakin University Australia College of Mathematics and Statistics Guangdong Key Lab. of Intelligent Information Processing Shenzhen University Shenzhen518060 China Dibrugarh University Dibrugarh India Department of Computer Science and Software Engineering Swinburne University of Technology Melbourne Australia Center for Machine Vision and Signal Analysis University of Oulu Oulu Finland Google research United States Department of Systems Design Engineering University of Waterloo Waterloo Canada State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing China Department of Electronics and Computer Engineering Ngee Ann Polytechnic Clementi Singapore Department of Computer Science University of Quebec in Montreal MontrealQC Canada

—Uncertainty quantification (UQ) plays a pivotal role in the reduction of uncertainties during both optimization and decision making, applied to solve a variety of real-world applications in science and engineering. Bayesian approximation and ensemble learning techniques are two of the most widely-used UQ methods in the literature. In this regard, researchers have proposed different UQ methods and examined their performance in a variety of applications such as computer vision (e.g., self-driving cars and object detection), image processing (e.g., image restoration), medical image analysis (e.g., medical image classification and segmentation), natural language processing (e.g., text classification, social media texts and recidivism risk-scoring), bioinformatics, etc. This study reviews recent advances in UQ methods used in deep learning, investigates the application of these methods in reinforcement learning, and highlight the fundamental research challenges and directions associated with the UQ field. Copyright © 2020, The Authors. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

The Algonauts Project: A Platform for Communication between the sciences of Biological and Artificial Intelligence

arXiv

引用

arXiv 2019年

作者： Cichy, Radoslaw Martin Roig, Gemma Andonian, Alex Dwivedi, Kshitij Lahner, Benjamin Lascelles, Alex Mohsenzadeh, Yalda Ramakrishnan, Kandan Oliva, Aude Department of Education and Psychology Freie Universität Berlin Berlin Germany Singapore University Technology and Design Information Systems Technology and Design Singapore Computer Science and Artificial Intelligence Laboratory Mit Cambridge United States

In the last decade, artificial intelligence (AI) models inspired by the brain have made unprecedented progress in performing real-world perceptual tasks like object classification and speech recognition. Recently, researchers of natural intelligence have begun using those AI models to explore how the brain performs such tasks. These developments suggest that future progress will benefit from increased interaction between disciplines. Here we introduce the Algonauts Project as a structured and quantitative communication channel for interdisciplinary interaction between natural and artificial intelligence researchers. The project's core is an open challenge with a quantitative benchmark whose goal is to account for brain data through computational models. This project has the potential to provide better models of natural intelligence and to gather findings that advance AI. The 2019 Algonauts Project focuses on benchmarking computational models predicting human brain activity when people look at pictures of objects. The 2019 edition of the Algonauts Project is available online: Http://***/. Copyright © 2019, The Authors. All rights reserved.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Foundation models and intelligent decision-making: Progress, challenges, and perspectives

引用

The Innovation 2025年第6期6卷

作者： Jincai Huang Yongjun Xu Qi Wang Qi (Cheems) Wang Xingxing Liang Fei Wang Zhao Zhang Wei Wei Boxuan Zhang Libo Huang Jingru Chang Liantao Ma Ting Ma Yuxuan Liang Jie Zhang Jian Guo Xuhui Jiang Xinxin Fan Zhulin An Tingting Li Aiguo Fei Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China National Engineering Research Center for Software Engineering Peking University Beijing 100871 China College of Systems Engineering National University of Defense Technology Changsha 410073 China Department of Oral Implantology Peking University School and Hospital of Stomatology Beijing 100081 China Laboratory for Big Data and Decision National University of Defense Technology Changsha 410073 China School of Automation Beijing Institute of Technology Beijing 100081 China Huazhong University of Science and Technology Wuhan 430074 China University of Chinese Academy of Sciences Beijing 100049 China State Key Laboratory of AI Safety Beijing 100190 China Department of Automation Tsinghua University Beijing 100084 China School of Information Science and Engineering Dalian Polytechnic University Dalian 116034 China The Hong Kong University of Science and Technology (Guangzhou) Guangzhou 511453 China College of Information and Electrical Engineering China Agricultural University Beijing 100083 China State Key Laboratory of Efficient Utilization of Agricultural Water Resources Beijing 100083 China IDEA Research International Digital Economy Academy Shenzhen 518057 China School of Computer Science National Pilot Software Engineering School Beijing University of Posts and Telecommunications Beijing 100876 China

Intelligent decision-making (IDM) is a cornerstone of artificial intelligence (AI) designed to automate or augment decision processes. Modern IDM paradigms integrate advanced frameworks to enable intelligent agents to make effective and adaptive choices and decompose complex tasks into manageable steps, such as AI agents and high-level reinforcement learning. Recent advances in multimodal foundation-based approaches unify diverse input modalities—such as vision, language, and sensory data—into a cohesive decision-making process. Foundation models (FMs) have become pivotal in science and industry, transforming decision-making and research capabilities. Their large-scale, multimodal data-processing abilities foster adaptability and interdisciplinary breakthroughs across fields such as healthcare, life sciences, and education. This survey examines IDM’s evolution, advanced paradigms with FMs and their transformative impact on decision-making across diverse scientific and industrial domains, highlighting the challenges and opportunities in building efficient, adaptive, and ethical decision systems.

关键词： artificial intelligence intelligent decision-making foundation models agent large language model

来源：评论

学校读者我要写书评

暂无评论

Systematic Resource Allocation in Cloud RAN with Caching as a Service under Two Timescales

Systematic Resource Allocation in Cloud RAN with Caching as ...

引用

作者： Tang, Jianhua Quek, Tony Q. S. Chang, Tsung-Hui Shim, Byonghyo Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing College of Information Science and Engineering Hunan Normal University Changsha410081 China Institute of New Media and Communications Department of Electrical and Computer Engineering Seoul National University Seoul08826 Korea Republic of Information Systems Technology and Design Pillar Singapore University of Technology and Design Singapore487372 Singapore Department of Electronic Engineering Kyung Hee University Yongin17104 Korea Republic of School of Science and Engineering Chinese University of Hong Kong Shenzhen518172 China Shenzhen Research Institute of Big Data Shenzhen518172 China Department of Electrical and Computer Engineering Institute of New Media and Communications Seoul National University Seoul08826 Korea Republic of

Recently, cloud radio access network (C-RAN) with caching as a service (CaaS) was proposed to merge the functionalities of communication, computing, and caching (CCC) together. In this paper, we dissect the interactions of CCC in C-RAN with CaaS from two dimensions: physical resource dimension and time dimension. In the physical resource dimension, we identify how to segment the baseband unit (BBU) pool resources (i.e., computation and storage) into different types of virtual machines (VMs). In the time dimension, we address how the long-term resource segmentation in the BBU pool impacts on the short-term transmit beamforming at the remote radio heads. We formulate the problem as a stochastic mixed-integer nonlinear programming (SMINLP) to minimize the system cost, including the server cost, VM cost and wireless transmission cost. After a series of approximation, including sample average approximation, successive convex approximation, and semidefinite relaxation, the SMINLP is approximated as a global consensus problem. The alternating direction method of multipliers (ADMM) is utilized to obtain the solution in a parallel fashion. Simulation results verify the convergence of our proposed algorithm, and also confirm that the proposed scheme is more cost-saving than that without considering the integration of CCC. © 1972-2012 IEEE.

关键词： Integer programming

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：