检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Yang, Hualin Li, Xiying Chen, Calvin Yu-Chian Artificial Intelligence Medical Research Center School of Intelligent Systems Engineering Shenzhen Campus of Sun Yat-sen University Guangdong Shenzhen518107 China - Preferred Program Peking University Shenzhen Graduate School Guangdong Shenzhen518055 China School of Electronic and Computer Engineering Peking University Shenzhen Graduate School Guangdong Shenzhen518055 China Department of Medical Research China Medical University Hospital Taichung40447 Taiwan Department of Bioinformatics and Medical Engineering Asia University Taichung41354 Taiwan Guangdong Provincial Key Laboratory of Intelligent Transportation System Sun Yat-sen University Guangzhou China School of Intelligent Systems Engineering Sun Yat-sen University Guangdong Shenzhen518107 China

Human skeleton-based action recognition represents a pivotal field of study, capturing the intricate interplay between physical dynamics and intentional actions. Current research primarily focuses on extracting structural and temporal information from static skeleton-based graphs, but they grapple with a myriad of challenges. These include 1) an absence of hierarchical structure in encoding the skeleton-based graphs;2) A requirement for substantial prior knowledge to interpret the diverse spatial dynamics within singular action labels;3) An intricate task of representing the multifaceted temporal dynamics of individual actions. To counter this issue, we propose DHS-Net, an innovative dynamic hierarchical skeleton-based network in video content. The proposed DHS-Net incorporates the DHS Block as a central element, effectively facilitating information exchange through node concentration and diffusion across both structural and temporal dimensions. Through this architectural design, DHS-Net extracts hierarchical representations, enhancing the comprehensive understanding of spatio-temporal dynamics and marking a significant advancement in human action recognition. Our rigorous experimental evaluations further substantiate DHS-Net's supremacy, outperforming several state-of-the-art benchmarks in skeleton-based action recognition and achieving remarkable prediction accuracy. © 2024, The Authors. All rights reserved.

关键词： Dynamics

来源：评论

学校读者我要写书评

暂无评论

Mrf-Former: A Multi-Scale Resolution Fusion Approach for Addressing Scale Discrepancies in Remote Sensing Image Change Detection

SSRN

引用

SSRN 2024年

作者： Yang, Hualin Ouyang, Jiarui Cheng, Junhao Zhang, Wen Li, Hui Li, Xiying Chen, Calvin Yu-Chian Artificial Intelligence Medical Research Center School of Intelligent Systems Engineering Shenzhen Campus of Sun Yat-sen University Guangdong Shenzhen518107 China - Preferred Program Peking University Shenzhen Graduate School Guangdong Shenzhen518055 China School of Electronic and Computer Engineering Peking University Shenzhen Graduate School Guangdong Shenzhen518055 China Department of Medical Research China Medical University Hospital Taichung40447 Taiwan Department of Bioinformatics and Medical Engineering Asia University Taichung41354 Taiwan Guangdong Provincial Key Laboratory of Intelligent Transportation System Sun Yat-sen University Guangzhou China School of Intelligent Systems Engineering Sun Yat-sen University Guangdong Shenzhen518107 China Institute of Artificial Intelligence Guangzhou University Guangzhou China

Dealing with resolution variations in dual-temporal remote sensing images is challenging due to differences in sensor capabilities, altitudes, footprints, resampling, and data fusion. Conventional methods for different-resolution change detection struggle to effectively address these challenges, primarily due to insufficient consideration of global and local feature interactions. In this paper, we propose a novel change detection model that leverages the power of multi-scale resolution fusion(MRF). By incorporating the MRF-Block, our approach extracts hierarchical multi-scale features from the input data, enabling effective capture of contextual information at various granularities. This facilitates improved handling of resolution disparities and promotes interactions between global and local features. Experimental evaluations conducted on diverse datasets, demonstrate the effectiveness of our proposed model in achieving accurate change detection in dual-temporal remote sensing imagery, even in scenarios characterized by varying resolutions. Code is available on-line at https://***/yanghl1914/MRF-Former. © 2024, The Authors. All rights reserved.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Some solution strategies for automated highway exit bottleneck problems

引用

transportation RESEARCH PART C-EMERGING TECHNOLOGIES 1996年第3期4卷 167-179页

作者： Ran, B Huang, WJ Leight, S Intelligent Transportation System Program Department of Civil Environmental Engineering University of Wisconsin at Madison 2256 Engineering Hall 1415 Engineering Drive Madison WI 53706 U.S.A.

transportation planners are exploring methods to ease congestion on urban freeways. The Automated Highway system(AHS) is a potential solution that could triple current freeway capacity. A three-fold increase in freeway capacity would translate into a significant increase in peak freeway traffic how. The corresponding increase of flow on urban roads due to exiting AHS vehicles could quickly overwhelm the capacity of urban streets and lead to critical bottlenecking of AHS flow. If exiting AHS vehicles cannot sufficiently clear AHS exits because the local streets are jammed, traffic will spill onto the AHS mainline and reduce AHS capacity. The loss of AHS capacity due to congestion in urban destinations and the resulting back spill of traffic onto the AHS wilt greatly detract from the AHS system. The following Non-Intermodal Interface (NII) and Intermodal Interface (II) strategies are proposed as solutions to this critical problem: (1) the dispersion of flow through AHS networks;(2) the dispersion of flow at commuter destinations;and (3) the consolidation of flow at central locations. Specifically, smart street signals and prioritized street design, intermodal terminals, and automated garages are identified as potential solutions. This paper qualitatively discusses the advantages and disadvantages of each of the three general strategies, and quantitatively discusses the advantages and disadvantages of each of the four specific solutions through Simulated scenarios which account for varying ramp volumes, trip attraction patterns, and urban structures. Our investigation shows that creative combinations of these methods can be useful to integrate future AHS with local road networks. Without such integration, the AHS cannot succeed. Copyright (C) 1996 Elsevier Science Ltd

关键词： Highway systems

来源：评论

学校读者我要写书评

暂无评论

Solving the bottleneck problem at automated highway exits

Solving the bottleneck problem at automated highway exits

引用

1996 Vehicular Navigation and Information systems Conference, VNIS 1996

作者： Ran, Bin Huang, Wenjing Leight, Shawn Intelligent Transportation System Program Department of Civil and Environmental Engineering University of Wisconsin at Madison 2256 Engineering Hall 1415 Engineering Drive MadisonWI53706 United States

Automated Highway systems (AHS) offer a potential solution that could triple current freeway capacity. A three-fold increase in freeway capacity would translate into a significant increase in peak freeway traffic flow. The corresponding increase of flow on urban roads due to exiting AHS vehicles could quickly overwhelm the capacity of urban streets and lead to critical bottlenecking of AHS flow. If exiting AHS vehicles can not sufficiently clear AHS exits because the local streets are jammed, traffic will spill onto the AHS mainline and reduce AHS capacity. The loss of AHS capacity due to congestion in urban destinations and the resulting back spill of traffic onto the AHS will greatly detract from the AHS system. The following Non-Intermodal Interface (NII) and Intermodal Interface (II) strategies are proposed as solutions to this critical bottleneck problem: 1) the dispersion of flow through AHS networks;2) the dispersion of flow at commuter destinations;and 3) the consolidation of flow at central locations. Specifically, smart street signals and prioritized street design;intermodal terminals;and automated garages are identified as potential solutions. This paper discusses the advantages and disadvantages of each of the three general strategies. Specifically, it discusses the advantages and disadvantages of each of the four specific solutions through simulated scenarios which account for varying ramp volumes, trip attraction patterns, and urban structures. Our investigation shows that creative combinations of these methods can be useful to integrate future AHS with local road networks. © 1996 IEEE.

关键词： Hazardous materials spills

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：