检索结果-内蒙古大学图书馆

International Conference on Computer Vision (ICCV)

作者： Zhiwu Qing Shiwei Zhang Ziyuan Huang Yingya Zhang Changxin Gao Deli Zhao Nong Sang Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Alibaba Group ARC National University of Singapore

Recently, large-scale pre-trained language-image models like CLIP have shown extraordinary capabilities for understanding spatial contents, but naively transferring such models to video recognition still suffers from unsatisfactory temporal modeling capabilities. Existing methods insert tunable structures into or in parallel with the pre-trained model, which either requires back-propagation through the whole pre-trained model and is thus resource-demanding, or is limited by the temporal reasoning capability of the pre-trained structure. In this work, we present DiST, which disentangles the learning of spatial and temporal aspects of videos. Specifically, DiST uses a dual-encoder structure, where a pre-trained foundation model acts as the spatial encoder, and a lightweight network is introduced as the temporal encoder. An integration branch is inserted between the encoders to fuse spatio-temporal information. The disentangled spatial and temporal learning in DiST is highly efficient because it avoids the back-propagation of massive pre-trained parameters. Meanwhile, we empirically show that disentangled learning with an extra network for integration benefits both spatial and temporal understanding. Extensive experiments on five benchmarks show that DiST delivers better performance than existing state-of-the-art methods by convincing gaps. When pre-training on the large-scale Kinetics-710, we achieve 89.7% on Kinetics-400 with a frozen ViT-L model, which verifies the scalability of DiST. Codes and models can be found in https://***/alibaba-mmai-research/DiST.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Generalized Subspace Distribution Adaptation Framework for Cross-Corpus Speech Emotion Recognition 48

A Generalized Subspace Distribution Adaptation Framework for...

引用

48th IEEE International Conference on Acoustics, Speech and Signal processing, ICASSP 2023

作者： Li, Shaokai Song, Peng Ji, Liang Jin, Yun Zheng, Wenming Yantai University School of Computer and Control Engineering China Jiangsu Normal University School of Physics and Electronic Engineering China Research Center for Learning Science Southeast University Key Laboratory of Child Development and Learning Science Southeast University Ministry of Education China Tibetan Information Processing and Machine Translation Key Laboratory of Qinghai Province The State Key Laboratory of Tibetan Intelligent Information Processing and Application China

ISBN: (纸本)9781728163277

In this paper, we propose a novel transfer learning framework, named generalized subspace distribution adaptation (GSDA), to tackle the challenging cross-corpus speech emotion recognition problem. First, we learn a common low-dimensional feature subspace by utilizing a generalized subspace learning method. Second, we develop a novel distance metric to reduce the divergence between the source and target corpora, which can efficiently explore the similarity and dissimilarity information in the process of knowledge transfer. Third, to demonstrate the effectiveness of our framework, we apply GSDA to the traditional subspace learning algorithms. Finally, we conduct extensive experiments by using the low-level features and deep features on three popular emotional databases, i.e., Berlin, IEMOCAP, and CVE. The results demonstrate that the proposed framework can achieve better performance than several state-of-the-art transfer learning approaches. © 2023 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Research on a Microwave Band-pass Filter 2

Research on a Microwave Band-pass Filter

引用

2nd International Conference on Electronic Materials and Information Engineering, EMIE 2022

作者： Qian, Jun Hou, Yifeng School of Electronic and Information Engineering Wuzhou University Guangxi Wuzhou China Guangxi Key Laboratory of Image Processing and Intelligent Information System Wuzhou University Guangxi Wuzhou China

ISBN: (纸本)9781713865629

This paper introduces a broadband microwave bandpass filter. The structure of the filter is a filter cavity formed by two balanced dielectric sheets. On the two dielectric sheets, the relative face of the microwave input end and the microwave output end is symmetrically provided with a guided wave surface, the middle face is symmetrically provided with a filter groove surface for filtering, and the surface of an exponential curve structure is arranged along the microwave transmission direction, A plurality of arc-shaped filter grooves are arranged on the opposite surface of the dielectric sheet perpendicular to the microwave transmission direction. This special structure is analyzed and calculated by the finite difference time domain method. The results show that the filter can fully improve the subwavelength binding effect in microwave band and make the anti electromagnetic interference ability of the filter better. © VDE VERLAG GMBH ∙ Berlin ∙ Offenbach.

关键词： Finite difference time domain method

来源：评论

学校读者我要写书评

暂无评论

Research on Multi-dimensional Bilingual Teaching Model of Computer Courses Supported by Artificial Intelligence 17th

Research on Multi-dimensional Bilingual Teaching Model of Co...

引用

17th International Conference on Computer Science and Education, ICCSE 2022

作者： Zhao, Changhua Mi, Chunqiao Tangbo School of Computer Science and Engineering Huaihua University Hunan Huaihua418000 China Key Laboratory of Wuling-Mountain Health Big Data Intelligent Processing and Application in Hunan Province Universities Hunan Huaihua418000 China Key Laboratory of Intelligent Control Technology for Wuling-Mountain Ecological Agriculture in Hunan Province Hunan Huaihua418000 China

ISBN: (纸本)9789819924486

Aiming at the problems of the integration of computer course teaching with international teaching and engineering certification, this study designs a multi-dimensional teaching mode of computer courses through the support of Artificial Intelligence. It analyzes the teaching resources, learning services, teaching process and teaching means involved in computer course teaching. Taking the course of "Computer Introduction" as an example, this study explores the multi-dimensional bilingual teaching mode supported by Artificial Intelligence, trains computer talents who meet the ability requirements of the era of Artificial Intelligence, and provides ideas for the teaching innovation of other courses. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Point-Query Quadtree for Crowd Counting, Localization, and More

arXiv

引用

arXiv 2023年

作者： Liu, Chengxin Lu, Hao Cao, Zhiguo Liu, Tongliang Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology China The University of Sydney Australia

We show that crowd counting can be viewed as a decomposable point querying process. This formulation enables arbitrary points as input and jointly reasons whether the points are crowd and where they locate. The querying processing, however, raises an underlying problem on the number of necessary querying points. Too few imply underestimation;too many increase computational overhead. To address this dilemma, we introduce a decomposable structure, i.e., the point-query quadtree, and propose a new counting model, termed Point quEry Transformer (PET). PET implements decomposable point querying via data-dependent quadtree splitting, where each querying point could split into four new points when necessary, thus enabling dynamic processing of sparse and dense regions. Such a querying process yields an intuitive, universal modeling of crowd as both the input and output are interpretable and steerable. We demonstrate the applications of PET on a number of crowd-related tasks, including fully-supervised crowd counting and localization, partial annotation learning, and point annotation refinement, and also report state-of-the-art performance. For the first time, we show that a single counting model can address multiple crowd-related tasks across different learning paradigms. Code is available at https://***/cxliu0/PET. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Reform of Blended-Teaching Mode for Discipline English Based on Mobile Terminal 17th

Reform of Blended-Teaching Mode for Discipline English Based...

引用

17th International Conference on Computer Science and Education, ICCSE 2022

作者： Yu, Niefang Peng, Xiaoning Li, Xiaomei Lu, Youmin School of Computer and Artificial Intelligence Huaihua University Hunan Huaihua418000 China Key Laboratory of Wuling-Mountain Health Big Data Intelligent Processing and Application in Hunan Province Universities Hunan Huaihua418000 China Key Laboratory of Intelligent Control Technology for Wuling-Mountain Ecological Agriculture in Hunan Province Hunan Huaihua418000 China

ISBN: (纸本)9789819924455

In the context of the era of big data, the rise of using mobile terminal is also putting forward new requirements for the teaching of Discipline English. Based on some general problems in the teaching practice of this course, we discuss whether adopting the blended-teaching mode can expand the learning space and time, enrich the learning interaction, and improve the learning efficiency in the context of big data based on mobile terminals. And then improve the quality of teaching and enhance application ability for the Discipline English. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Research on a Microwave Filter with Pentagram Grooves 3

Research on a Microwave Filter with Pentagram Grooves

引用

2022 3rd International Conference on Electrical, Electronic Information and Communication Engineering, EEICE 2022

作者： Hou, Y.F. Qian, J. School of Electronic and Information Engineering Wuzhou University Guangxi Wuzhou China Guangxi Key Laboratory of Image Processing and Intelligent Information System Wuzhou University Guangxi Wuzhou China

This paper introduces a microwave filter with pentagram grooves, which belongs to an artificial surface plasmon (SSPPs) type microwave bandpass *** filter adopts a two-stage structure. The first section is a slot-line waveguide section, and one side of this section adopts an exponential curve structure to prevent sudden changes in electromagnetic impedance and achieve a good connection with the second *** second segment is the SSPPs segment, which adopts a novel mirror-symmetric pentagram-shaped groove air gap structure. By adjusting the geometric size of the pentagram-shaped groove, the microwave subwavelength confinement effect can be further improved,making the SSPPs filter more excellent in pass-band characteristics and anti-space electromagnetic *** filter can be applied to the civil microwave communication system of L~1/4S band. © Published under licence by IOP Publishing Ltd.

关键词： Microwave filters

来源：评论

学校读者我要写书评

暂无评论

A Robust Recognition and Segmentation Algorithm for Retaining Walls in Mining Scenes

A Robust Recognition and Segmentation Algorithm for Retainin...

引用

Chinese Automation Congress (CAC)

作者： Tian Zeng Li Xiao Gang Peng Aoze Wang Zhuo Wang Zhigang Sun Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Intelligence and Automation Huazhong University of Science and Technology Wuhan China

The key for bulldozers to realize automatic operation in mine scenes is whether they can accurately identify and accurately segment the retaining walls, however, because the point cloud dataset of the mine site is too few, resulting in the deep learning-based identification and segmentation algorithm cannot be applied in this scene. At the same time, because of the rugged road surface of the mine scene, the existence of a lot of dust, numerous disturbances, retaining wall features are not obvious and other problems, the algorithms proposed by previous scholars are not perfect enough to solve the problem. We propose a point cloud recognition and segmentation algorithm based on clustering and evaluation function of integrated features. Ours firstly compensates the skew of the point cloud map with RANSAC and down samples the data by gridding the point cloud. Then reduces the influence of dust and truck materials in the scene by normal vector and variance information. Finally, screens out the candidate target class by density clustering, and identifies and segments the retaining wall by integrated feature. Our proposed algorithm is validated in several different real mine scenarios and the results show that ours has high accuracy and strong robustness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Course Homework Reform in Universities Based on Extended Reality 17th

Course Homework Reform in Universities Based on Extended Rea...

引用

17th International Conference on Computer Science and Education, ICCSE 2022

作者： Fu, Jinrong Liu, Yiwen Mi, Chunqiao Peng, Xiaoning Xiao, Jianhua School of Computer and Artificial Intelligence Huaihua University Hunan Huaihua418000 China Key Laboratory of Wuling-Mountain Health Big Data Intelligent Processing and Application in Hunan Province Universities Hunan Huaihua418000 China Key Laboratory of Intelligent Control Technology for Wuling-Mountain Ecological Agriculture in Hunan Province Hunan Huaihua418000 China

ISBN: (纸本)9789819924486

In view of the serious issues commonly existing with coursework in Chinese universities at present, such as its original function weakening or being suppressed, its form being too abstract and lack of elaborate design. In order to resolve these problems observed in usual homework, this paper proposes a reform scheme for cloud coursework based on Extended Reality and Bloom model. It mainly includes five key parts, such as interaction, scene, comprehensive evaluation, digital twin and data analysis. In addition, the reform’s effectiveness is illustrated through amassing and comparing the feedback of college students for teaching. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Deployment of Heterogeneous Multi-Agent Systems via a PDE Approach

Deployment of Heterogeneous Multi-Agent Systems via a PDE Ap...

引用

Chinese Automation Congress (CAC)

作者： Jingtao Man Zhigang Zeng Qiang Xiao Key Laboratory of Image Information Processing and Intelligent Control Ministry of Education of China School of Artificial Intelligence and Automation (of Huazhong University of Science and Technology) Wuhan China

Spatial deployment of large-scale heterogeneous multi-agent systems (HMASs) over desired 2D or 3D curves is investigated in this paper. With assumption that HMASs consist of numerous first-order agents (FOAs) and second-order agents (SOAs) that could obtain local information of desired curves and their positions relative to their closest neighbors, the collective dynamics of large-scale HMASs are modeled as heterogeneous partial differential equations (PDEs). In particular, this paper introduces series-dependent topological weights between neighboring agents, which are more versatile and practical than constant topological weights commonly used in previous studies. A novel single-point control scheme is proposed, where an informed agent is situated between the last FOA and first SOA. This operation could not only ensure successful implementation of spatial deployment, but also guarantee well-posedness of the constructed heterogeneous error PDEs. By utilizing inequality techniques, sufficient conditions for exponential convergence of error system are derived. A numerical example is presented to demonstrate effectiveness of the proposed approaches.

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：