检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Maher, Kevin Huang, Zeyuan Song, Jiancheng Deng, Xiaoming Lai, Yu-Kun Ma, Cuixia Wang, Hao Liu, Yong-Jin Wang, Hongan Institute of Software Chinese Academy of Sciences Tsinghua University China State Key Laboratory of Computer Science Beijing Key Lab of Human-Computer Interaction Institute of Software Chinese Academy of Sciences University of Chinese Academy of Sciences China Cardiff University United Kingdom Alibaba Group China Tsinghua University China

What makes speeches effective has long been a subject for debate, and until today there is broad controversy among public speaking experts about what factors make a speech effective as well as the roles of these factors in speeches. Moreover, there is a lack of quantitative analysis methods to help understand effective speaking strategies. In this paper, we propose E-ffective, a visual analytic system allowing speaking experts and novices to analyze both the role of speech factors and their contribution in effective speeches. From interviews with domain experts and investigating existing literature, we identified important factors to consider in inspirational speeches. We obtained the generated factors from multi-modal data that were then related to effectiveness data. Our system supports rapid understanding of critical factors in inspirational speeches, including the influence of emotions by means of novel visualization methods and interaction. Two novel visualizations include E-spiral (that shows the emotional shifts in speeches in a visually compact way) and E-script (that connects speech content with key speech delivery information). In our evaluation we studied the influence of our system on experts' domain knowledge about speech factors. We further studied the usability of the system by speaking novices and experts on assisting analysis of inspirational speech effectiveness. Copyright © 2021, The Authors. All rights reserved.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

FlexiFed: Personalized Federated Learning for Edge Clients with Heterogeneous Model Architectures 23

FlexiFed: Personalized Federated Learning for Edge Clients w...

引用

2023 World Wide Web Conference, WWW 2023

作者： Wang, Kaibin He, Qiang Chen, Feifei Chen, Chunyang Huang, Faliang Jin, Hai Yang, Yun School of Computer Science and Technology Huazhong University of Science and Technology China Department of Computing Technologies Swinburne University of Technology Australia School of Information Technology Deakin University Australia Faculty of Information Technology Monash University Australia Guangxi Key Lab of Human-machine Interaction and Intelligent Decision Nanning Normal University China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9781450394161

Mobile and Web-of-Things (WoT) devices at the network edge account for more than half of the world's web traffic, making a great data source for various machine learning (ML) applications, particularly federated learning (FL) which offers a promising solution to privacy-preserving ML feeding on these data. FL allows edge mobile and WoT devices to train a shared global ML model under the orchestration of a central parameter server. In the real world, due to resource heterogeneity, these edge devices often train different versions of models (e.g., VGG-16 and VGG-19) or different ML models (e.g., VGG and ResNet) for the same ML task (e.g., computer vision and speech recognition). Existing FL schemes have assumed that participating edge devices share a common model architecture, and thus cannot facilitate FL across edge devices with heterogeneous ML model architectures. We explored this architecture heterogeneity challenge and found that FL can and should accommodate these edge devices to improve model accuracy and accelerate model training. This paper presents our findings and FlexiFed, a novel scheme for FL across edge devices with heterogeneous model architectures, and three model aggregation strategies for accommodating architecture heterogeneity under FlexiFed. Experiments with four widely-used ML models on four public datasets demonstrate 1) the usefulness of FlexiFed;and 2) that compared with the state-of-the-art FL scheme, FlexiFed improves model accuracy by 2.6%-9.7% and accelerates model convergence by 1.24 × -4.04 ×. © 2023 ACM.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Tangible user interfaces for children

Tangible user interfaces for children

引用

Conference on human Factors in Computing Systems, CHI EA 2005

作者： Revelle, Glenda Zuckerman, Oren Druin, Allison Bolas, Mark Sesame Workshop One Lincoln Plaza New York NY 10023 United States MIT Media Lab 20 Ames Street E15-120b Cambridge MA 02139 United States University of Maryland Human-Computer Interaction Lab College Park MD 20742 United States USC School of Cinema-Television Interactive Media Division 850 W. 34th Street Lucas 310 Los Angeles CA 90089-2211 United States

ISBN: (纸本)1595930027

Tangible user interfaces, which provide interactivity using real physical objects, hold enormous promise for children. Exploring and manipulating physical objects is a key component of young children's learning. The educational power of digital technology for children has typically been limited by the fact that users explore and manipulate abstract two-dimensional screen-based representations, and not real physical objects. Embedding interactivity into physical objects, therefore, allows the "best of both worlds"- supporting traditional exploratory play with physical objects that can be extended and enhanced by the interactive power of digital technology. Participants in this SIG are invited to share ideas regarding the design and development of tangible interfaces, and to bring demos or slides/videos showing work in this area. Participants will review as many examples as time allows, and discuss the issues surrounding design and development of such interfaces. A primary goal of this SIG is to foster the development of a community of researchers and practitioners who are focused on designing and developing tangible interfaces for children.

关键词： Toys

来源：评论

学校读者我要写书评

暂无评论

MSA-GCN:Multiscale Adaptive Graph Convolution Network for Gait Emotion Recognition

arXiv

引用

arXiv 2022年

作者： Yin, Yunfei Jing, Li Huang, Faliang Yang, Guangchao Wang, Zhuowei The School of of Computer Science and Technology Chongqing University Chongqing China Guangxi Key Lab of Human-Machine Interaction and Intelligent Decision Nanning Normal University Nanning530001 China Faculty of Engineering and Information Technology University of Technology Sydney Australia

Gait emotion recognition plays a crucial role in the intelligent system. Most of the existing methods recognize emotions by focusing on local actions over time. However, they ignore that the effective distances of different emotions in the time domain are different, and the local actions during walking are quite similar. Thus, emotions should be represented by global states instead of indirect local actions. To address these issues, a novel MultiScale Adaptive Graph Convolution Network (MSA-GCN) is presented in this work through constructing dynamic temporal receptive fields and designing multiscale information aggregation to recognize emotions. In our model, a adaptive selective spatial-temporal graph convolution is designed to select the convolution kernel dynamically to obtain the soft spatiotemporal features of different emotions. Moreover, a Cross-Scale mapping Fusion Mechanism (CSFM) is designed to construct an adaptive adjacency matrix to enhance information interaction and reduce redundancy. Compared with previous state-of-the-art methods, the proposed method achieves the best performance on two public datasets, improving the mAP by 2%. We also conduct extensive ablations studies to show the effectiveness of different components in our methods. Copyright © 2022, The Authors. All rights reserved.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Virtual Reality Pōwhiri—Practicing an indigenous welcoming ceremony 23

Virtual Reality Pōwhiri—Practicing an indigenous welcoming...

引用

Proceedings of the 35th Australian computer-human interaction Conference

作者： Laurence Lloyd-Jones Claudia Ott Holger Regenbrecht Hēmi Whaanga Human Computer Interaction (HCI) Lab University of Otago New Zealand Information Science University of Otago New Zealand Department of Information Science University of Otago New Zealand Te P?tahi-a-Toi Massey University New Zealand

ISBN: (纸本)9798400717079

Pōwhiri is a traditional welcoming ceremony in Māori culture in Aotearoa New Zealand. Certain protocols (tikanga) have to be followed and must be learned. There is a general lack of understanding regarding this due to the scarcity of pōwhiri. The immersive and experiential nature of Virtual Reality (VR) can be used as a tool to increase understanding and confidence. We have implemented a VR learning tool in the reconstructed context of Te Rau Aroha marae in Bluff which allows for safe practice of pōwhiri before applying it in a real welcoming ceremony. A cultural evaluation study was conducted first followed by a user study to determine understanding and confidence gains, highlighting the complexity of the topic. The user study clearly showed that the system was useful to increase participants’ understanding in regards to pōwhiri as well as their confidence surrounding pōwhiri. We are confident that our experiences and key findings from the studies can be used to drive further development of VR tools in the context of visualising cultural ceremonies.

关键词： 3D Reconstruction Indigenous User Interfaces VR Learning Volumetric Video

来源：评论

学校读者我要写书评

暂无评论

StoryBank: Mobile digital storytelling in a development context 09

StoryBank: Mobile digital storytelling in a development cont...

引用

27th International Conference Extended Abstracts on human Factors in Computing Systems, CHI 2009

作者： Frohlich, David M. Rachovides, Dorothy Riga, Kiriaki Edirisinghe, Eran Wickramanayaka, Dhammike Bhat, Ramnath Frank, Maxine Jones, Matt Harwood, Will Digital World Research Centre Faculty of Arts and Human Sciences University of Surrey Guildford GU2 7XH United Kingdom Department of Computer Science Loughborough University Holywell Park Loughborough LEI 1 3TU United Kingdom VOICES 9th Cross Indiranagar Bangalore India Future Interaction Technology Lab Swansea University Swansea SA2 8PP United Kingdom

ISBN: (纸本)9781605582474

Mobile imaging and digital storytelling currently support a growing practice of multimedia communication in the West. In this paper we describe a project which explores their benefit in the East, to support non-textual information sharing in an Indian village. Local audiovisual story creation and sharing activities were carried out in a one month trial, using 10 customized cameraphones and a digital library of stories represented on a village display. The findings show that the system was usable by a cross- section of the community and valued for its ability to express a mixture of development and community information in an accessible form. Lessons for the role of HC1 in this context are also discussed. Copyright 2009 ACM.

关键词： Digital libraries

来源：评论

学校读者我要写书评

暂无评论

FROM THE EDITORS OF THE SPECIAL ISSUE

引用

Applied Artificial Intelligence 2010年第6期24卷 489-493页

作者： Ruttkay, Zsófia Kipp, Michael Nijholt, Anton Vilhjálmsson, Hannes Högni Creative Technology Lab Moholy-Nagy University of Art and Design Budapest Hungary. DFKI Embodied Agents Research Group Saarbruecken Germany. Human-Media Interaction University of Twente Enschede The Netherlands. School of Computer Science Reykjavík University Reykjavík Iceland

The article discusses various reports published within the issue, including one on EMBR, a state-of-the-art character animation engine, another on the second dimension, identity and individuality and another on the ge... 详细信息

关键词： ENGINES MACHINERY

来源：评论

学校读者我要写书评

暂无评论

Revisiting metric learning for few-shot image classification

arXiv

引用

arXiv 2019年

作者： Li, Xiaomeng Yu, Lequan Fu, Chi-Wing Fang, Meng Heng, Pheng-Ann Department of Computer Science and Engineering Chinese University of Hong Kong Hong Kong Shenzhen Key Laboratory of Virtual Reality and Human Interaction Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Tencent AI Lab United States

The goal of few-shot learning is to recognize new visual concepts with just a few amount of labeled samples in each class. Recent effective metric-based few-shot approaches employ neural networks to learn a feature similarity comparison between query and support examples. However, the importance of feature embedding, i.e., exploring the relationship among training samples, is neglected. In this work, we present a simple yet powerful baseline for few-shot classification by emphasizing the importance of feature embedding. Specifically, we revisit the classical triplet network from deep metric learning, and extend it into a deep K-tuplet network for few-shot learning, utilizing the relationship among the input samples to learn a general representation learning via episode-training. Once trained, our network is able to extract discriminative features for unseen novel categories and can be seamlessly incorporated with a non-linear distance metric function to facilitate the few-shot classification. Our result on the miniImageNet benchmark outperforms other metric-based few-shot classification methods. More importantly, when evaluated on completely different datasets (Caltech-101, CUB-200, Stanford Dogs and Cars) using the model trained with miniImageNet, our method significantly outperforms prior methods, demonstrating its superior capability to generalize to unseen classes. Copyright © 2019, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

On the use of LSF intermodel interlacing property for spectral quantization 6

On the use of LSF intermodel interlacing property for spectr...

引用

6th IEEE Workshop on Speech Coding

作者： Lee, Mi Suk Kim, Hong Kook Choi, Seung Ho Lee, Hwang Soo Dept. of Electrical Eng. Korea Advanced Institute of Science and Technology Taejon305-701 Korea Republic of ATandT Labs Research 180 Park Avenue Florham ParkNJ07932 United States Human and Computer Interaction Lab. Samsung Advanced Institute of Technology Kyungki-Do449-712 Korea Republic of Central RandD Center SK Telecom 58-4 Hwaam-Dong Yusong-Gu Taejon305-348 Korea Republic of

ISBN: (纸本)0780356519

The line spectral frequencies (LSFs) extracted from successive analysis orders are interlaced with each other. This intermodel interlacing property gives a new relationship between the closeness of LSFs and their spectral sensitivities, which enables us to propose a weighting function for LSF distortion measurement. By applying the proposed weighting function to an LSF quantizer, we can achieve better performance than when using the conventional heuristic functions. Moreover, the complexity of the proposed weighting function is much lower than that of the optimal weighting function, while their performances are almost the same. © 1999 IEEE.

关键词： Spectroscopy

来源：评论

学校读者我要写书评

暂无评论

A Pattern Methodology to Specify Usable Security in Websites

A Pattern Methodology to Specify Usable Security in Websites

引用

International Workshop on Database and Expert Systems Applications

作者： Ricardo Mendoza Gonzalez Jaime Munoz-Arteaga Miguel Vargas Martin Francisco Alvarez-Rodriguez Juan Gonzalez Calleros Universidad Autónoma de Aguascalientes Centro de Ciencias Básicas Aguascalientes Mexico University of Ontario Institute of Technology Oshawa Canada Universite Catholique de Louvain Belgian Lab. of Computer-Human Interaction (BCHI) Louvain-la-Neuve Belgium

This paper presents an overview of a new pattern methodology which is oriented to achieve basic usability and security design requirements in websites. We emphasize the need of adequate and uniform guidelines useful to incorporate essential security and usability aspects in websites. In order to diminish this problem a methodology is provided to developers with guidance in designing a trustworthy environment through an effective feedback in case of a security issue are explicitly incorporated in the development life cycle. Our proposal integrates several collections of design patterns (based on HCI-S design criteria), complemented with measurement models (based on Goal Question Metrics, GQM, approach) to evaluate the obtained results.

关键词： Usability Feedback computer security human computer interaction Information security Web page design User interfaces Application software Databases Expert systems

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：