检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Huang, Enbo Zhang, Yuan Huang, Faliang Zhang, Guangyu Liu, Yang Guangxi Key Lab of Human-machine Interaction and Intelligent Decision Nanning Normal University Nanning China Zhidayuan AI Lab. Nanning China College of Mathematics and Informatics South China Agricultural University Guangzhou China School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China

Person image synthesis with controllable body poses and appearances is an essential task owing to the practical needs in the context of virtual try-on, image editing and video production. However, existing methods face significant challenges with details missing, limbs distortion and the garment style deviation. To address these issues, we propose a Disentangled Representations Diffusion Model (DRDM) to generate photo-realistic images from source portraits in specific desired poses and appearances. First, a pose encoder is responsible for encoding pose features into a high-dimensional space to guide the generation of person images. Second, a body-part subspace decoupling block (BSDB) disentangles features from the different body parts of a source figure and feeds them to the various layers of the noise prediction block, thereby supplying the network with rich disentangled features for generating a realistic target image. Moreover, during inference, we develop a parsing map-based disentangled classifier-free guided sampling method, which amplifies the conditional signals of texture and pose. Extensive experimental results on the Deepfashion dataset demonstrate the effectiveness of our approach in achieving pose transfer and appearance control. Copyright © 2024, The Authors. All rights reserved.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

FoamFactor: Hydrogel-foam composite with tunable stiffness and compressibility

arXiv

引用

arXiv 2021年

作者： Yang, Humphrey Yan, Zeyu Luo, Danli Yao, Lining Human-Computer Interaction Carnegie Mellon University PittsburghPA United States Computer Science University of Maryland College Park MD United States

This paper presents FoamFactor, a novel material with tunable stiffness and compressibility between hydration states, and a tailored pipeline to design and fabricate artifacts consisting of it. This technique compounds hydrogel with open-cell foams via additive manufacturing to produce a water-responsive composite material. Enabled by the large volumetric changes of hydrogel dispersions, the material is soft and compressible when dehydrated and becomes stiffer and rather incompressible when hydrated. Leveraging this material property transition, we explore its design space in various aspects pertaining the transition of hydration states, including multi-functional shoes, amphibious cars, mechanical transmission systems, and self-deploying robotic grippers. © 2021, CC BY.

关键词： Hydrogels

来源：评论

学校读者我要写书评

暂无评论

Dynamic Localisation of Spatial-Temporal Graph Neural Network 25

Dynamic Localisation of Spatial-Temporal Graph Neural Networ...

引用

Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1

作者： Wenying Duan Shujun Guo Zimu Zhou Wei Huang Hong Rao Xiaoxi He Jiangxi Provincial Key Laboratory of Intelligent Systems and Human-Machine Interaction Nanchang University Nanchang China School of Mathematics and Computer Sciences Nanchang University Nanchang China School of Data Science City University of Hong Kong Hong Kong Hong Kong School of Software Nanchang University Nanchang China Faculty of Science and Technology University of Macau Macao Macao Macao

ISBN: (纸本)9798400712456

Spatial-temporal data, fundamental to many intelligent applications, reveals dependencies indicating causal links between present measurements at specific locations and historical data at the same or other locations. Within this context, adaptive spatial-temporal graph neural networks (ASTGNNs) have emerged as valuable tools for modelling these dependencies, especially through a data-driven approach rather than pre-defined spatial graphs. While this approach offers higher accuracy, it presents increased computational demands. Addressing this challenge, this paper delves into the concept of localisation within ASTGNNs, introducing an innovative perspective that spatial dependencies should be dynamically evolving over time. We introduce DynAGS, a localised ASTGNN framework aimed at maximising efficiency and accuracy in distributed deployment. This framework integrates dynamic localisation, time-evolving spatial graphs, and personalised localisation, all orchestrated around the Dynamic Graph Generator, a light-weighted central module leveraging cross attention. The central module can integrate historical information in a node-independent manner to enhance the feature representation of nodes at the current moment. This improved feature representation is then used to generate a dynamic sparse graph without the need for costly data exchanges, and it supports personalised localisation. Performance assessments across two core ASTGNN architectures and nine real-world datasets from various applications reveal that DynAGS outshines current benchmarks, underscoring that the dynamic modelling of spatial dependencies can drastically improve model expressibility, flexibility, and system efficiency, especially in distributed settings.

关键词： graph sparsification

来源：评论

学校读者我要写书评

暂无评论

Saliency Region Detection in Complex Scenes Based on Multi-scale Cascaded Attention

Saliency Region Detection in Complex Scenes Based on Multi-s...

引用

IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS)

作者： Yifeng Wang Zhenfeng Huo Aoli Liu Lin Zhao Di Wang The Key Laboratory of Smart Human-Computer Interaction and Wearable Technology of Shanxi Province Xidian University China School of Computer Science and Engineering Nanjing University of Science and Technology China

ISBN: (纸本)9781665441506

This paper proposes a saliency detection method based on multi-scale cascade attention mechanism. It utilizes both channel and spatial weight attention mechanism to effectively learn the salient regions. By generating multi-scale intermediate feature maps, the shallow features are divided into categories of foreground and background. Then, the channel weights are calculated by using the foreground and background feature distribution, and the spatial weights are computed by using the predicted feature map, so that the network is more focused on salient regions and suppresses the interference of background regions. Experimental results show that the model can reliably and accurately detect salient targets and delivers better performance.

关键词： Training Cloud computing Conferences Computational modeling Interference Reliability Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Communicative Grounding of Analogical Explanations in Dialogue: A Corpus Study of Conversational Management Acts and Statistical Sequence Models for Tutoring through Analogy

Communicative Grounding of Analogical Explanations in Dialog...

引用

2021 Conference on Reasoning and interaction, ReInAct 2021

作者： Del-Bosque-Trevino, Jorge Hough, Julian Purver, Matthew Education Lab. Computational Linguistics Lab. Cognitive Science Research Group School of Electronic Engineering and Computer Science Queen Mary University of London United Kingdom Human Interaction Lab. Computational Linguistics Lab. Cognitive Science Research Group School of Electronic Engineering and Computer Science Queen Mary University of London United Kingdom Jožef Stefan Institute Computational Linguistics Lab. Cognitive Science Research Group School of Electronic Engineering and Computer Science Queen Mary University of London United Kingdom

ISBN: (纸本)9781955917070

We present a conversational management act (CMA) annotation schema for one-to-one tutorial dialogue sessions where a tutor uses an analogy to teach a student a concept. CMAs are more fine-grained sub-utterance acts compared to traditional dialogue act markup. The schema achieves an inter-annotator agreement (IAA) Cohen Kappa score of at least 0.66 across all 10 classes. We annotate a corpus of analogical episodes with the schema and develop statistical sequence models from the corpus which predict tutor content related decisions, in terms of the selection of the analogical component (AC) and tutor conversational management act (TCMA) to deploy at the current utterance, given the student’s behaviour. CRF sequence classifiers perform well on AC selection and robustly on TCMA selection, achieving respective accuracies of 61.9% and 56.3% on a cross-validation experiment over the corpus. © 2021 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Semantic Visual Simultaneous Localization and Mapping: A Survey

arXiv

引用

arXiv 2022年

作者： Chen, Kaiqi Xiao, Junhao Liu, Jialing Tong, Qiyi Zhang, Heng Liu, Ruyu Zhang, Jianhua Ajoudani, Arash Chen, Shengyong Institute of Computer Vision College of Computer Science and Technology Zhejiang University of Technology Hangzhou310023 China Human-Robot Interfaces and Interaction Lab Istituto Italiano di Tecnologia Genoa Italy National University of Defense Technology China Università di Genova Genoa Italy School of Information Science and Technology Hangzhou Normal University Hangzhou311121 China Institute of Computer Vision School of Computer Science and Engineering Tianjin University of Technology Tianjin300384 China

Visual Simultaneous Localization and Mapping (vSLAM) has achieved great progress in the computer vision and robotics communities, and has been successfully used in many fields such as autonomous robot navigation and AR/VR. However, vSLAM cannot achieve good localization in dynamic and complex environments. Numerous publications have reported that, by combining with the semantic information with vSLAM, the semantic vSLAM systems have the capability of solving the above problems in recent years. Nevertheless, there is no comprehensive survey about semantic vSLAM. To fill the gap, this paper first reviews the development of semantic vSLAM, explicitly focusing on its strengths and differences. Secondly, we explore three main issues of semantic vSLAM: the extraction and association of semantic information, the application of semantic information, and the advantages of semantic vSLAM. Then, we collect and analyze the current state-of-the-art SLAM datasets which have been widely used in semantic vSLAM systems. Finally, we discuss future directions that will provide a blueprint for the future development of semantic vSLAM. Copyright © 2022, The Authors. All rights reserved.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

A User-Centered Extended Reality Authoring Tool Development Framework for General Aviation Weather Training

A User-Centered Extended Reality Authoring Tool Development ...

引用

Conference on Digital Avionics Systems (DASC)

作者： Jiwon Kim Kexin Wang Jack Miller Michael Dorneich Eliot Winer Lori Brown Industrial and Manufacturing Systems Engineering Iowa State University Ames IA USA Human Computer Interaction Iowa State University Ames IA USA Mechanical Engineering Iowa State University Ames IA USA Aviation Flight Science Western Michigan University Kalamazoo MI USA

This paper describes a comprehensive framework for the development of an extended reality (XR) authoring toolkit for general aviation weather training. Conventional weather training methods often rely on static, text-based materials, which might result in limited engagement and failure to provide an immersive experience tailored to the unique learning needs of students. Conversely, XR-enhanced lessons offer promising alternatives to enhance weather-related knowledge and decision-making. However, existing XR toolkits typically require advanced programming skills, posing challenges for non-technologist instructors. To address this gap, a content-centered approach that shifts the focus from the technicalities of developing augmented reality visualizations to enabling non-technologist instructors to readily interact with weather objects and scenario elements is proposed. The development framework, rooted in the user-centered design approach, encompasses understanding the user's context, specifying requirements, and developing a prototype. This study provides a description of the framework, accompanied by a case study specifically tailored to developing an XR authoring toolkit for general aviation weather training. Emphasis is placed on the significance of conducting comprehensive user studies and adhering to evidence-based software design guidance throughout the development process. The proposed framework is expected to contribute to the development of user-friendly 3D authoring environments, empowering instructors to create engaging and interactive aviation weather lessons. By enabling non-technologist instructors to create XR-enhanced lessons without requiring extensive computer skills, the framework aims to broaden access to XR-based training, catering to a wider audience.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Congenital hydrocephalus:a review of recent advances in genetic etiology and molecular mechanisms

引用

Military Medical Research 2024年第6期11卷 942-958页

作者： Xiu-Yun Liu Xin Song Marek Czosnyka Chiara Robba Zofia Czosnyka Jennifer Lee Summers Hui-Jie Yu Guo-Yi Gao Peter Smielewski Fang Guo Mei-Jun Pang Dong Ming Medical School Tianjin UniversityTianjin 300072China State Key Laboratory of Advanced Medical Materials and Devices Tianjin UniversityTianjin 300072China Haihe Laboratory of Brain-Computer Interaction and Human-Machine Integration Tianjin 300380China School of Pharmaceutical Science and Technology Tianjin University300072 TianjinChina Department of Clinical Neurosciences Addenbrooke’s HospitalUniversity of CambridgeCambridge CB20QQUK San Martino Policlinico Hospital IRCCS for Oncology and Neuroscience16132 GenoaItaly Department of Anesthesiology and Critical Care Medicine Johns Hopkins UniversityBaltimoreMD 21287USA Department of Neurosurgery Tianjin Medical University General HospitalTianjin 300052China Department of Neurosurgery Beijing Tiantan HospitalCapital Medical UniversityBeijing 100070China Department of Neurosurgery Tianjin Huanhu HospitalTianjin 300350China

The global prevalence rate for congenital hydrocephalus(CH)is approximately one out of every five hundred births with multifaceted predisposing factors at *** influences stand as a major contributor to CH pathogenesis,and epidemiological evidence suggests their involvement in up to 40%of all cases observed *** about an individual’s genetic susceptibility can significantly improve prognostic precision while aiding clinical decision-making ***,the precise genetic etiology has only been pinpointed in fewer than 5%of human *** occurrences of CH cases are required for comprehensive gene sequencing aimed at uncovering additional potential genetic loci.A deeper comprehension of its underlying genetics may offer invaluable insights into the molecular and cellular basis of this brain *** review provides a summary of pertinent genes identified through gene sequencing technologies in humans,in addition to the 4 genes currently associated with CH(2 X-linked genes L1CAM and AP1S2,2 autosomal recessive MPDZ and CCDC88C).Others predominantly participate in aqueduct abnormalities,ciliary movement,and nervous system *** prospective CH-related genes revealed through animal model gene-editing techniques are further outlined,focusing mainly on 4 pathways,namely cilia synthesis and movement,ion channels and transportation,Reissner’s fiber(RF)synthesis,cell apoptosis,and ***,the proper functioning of motile cilia provides significant impulsion for cerebrospinal fluid(CSF)circulation within the brain ventricles while mutations in cilia-related genes constitute a primary cause underlying this *** far,only a limited number of CH-associated genes have been identified in *** integration of genotype and phenotype for disease diagnosis represents a new trend in the medical *** models provide insights into the pathogenesis of CH and contribute to our understanding of its association w

关键词： Congenital hydrocephalus Genetic disease Central system Cilia Ventricle

来源：评论

学校读者我要写书评

暂无评论

Pushing the Boundaries of Computational Empowerment of Children 25

Pushing the Boundaries of Computational Empowerment of Child...

引用

Proceedings of the 24th interaction Design and Children

作者： Netta Iivari Ole Sejer Iversen Yasmin Kafai Alissa N. Antle Marianne Graves Petersen Marianne Kinnula Christian Dindler Fares Kayali Elizabeth Bonsignore Charu Monga, Ms. Marie-Monique Schaper Sumita Sharma INTERACT Research Unit University of Oulu Oulu Finland Center for Computational Thinking and Design Aarhus University Aarhus Denmark Graduate School of Education University of Pennsylvania Philadelphia Pennsylvania USA School of Interactive Arts and Technology Simon Fraser University Vancouver British Columbia Canada Computer Science Aarhus University Aarhus Århus Denmark University of Vienna Vienna Austria Human-Computer Interaction Lab University of Maryland College Park Maryland USA Department of Design Indian Institute of Technology Delhi Delhi India Department for Computer Engineering and Digital Design University of Lleida Lleida Spain

ISBN: (纸本)9798400714733

Emerging technologies such as artificial intelligence (AI) and mixed reality (MR) increasingly pervade the world of children, from their schoolwork to leisure activities and social relationships. This has led to Child computer interaction (CCI) research supporting children's critical understanding of digital technologies and their ability to influence the design of future digital technologies. Despite these efforts, there are several limitations and challenges in terms of Computational Empowerment (CE) of children. This workshop unites such research 1) to create a shared manifesto for CE of children and 2) to jointly develop a research ‘roadmap’ to push the boundaries of CE of children.

关键词： Child computer interaction Computational Empowerment Participatory Design Critical Computing Emerging Technologies

来源：评论

学校读者我要写书评

暂无评论

Hydrocephalus: An update on latest progress in pathophysiological and therapeutic research

引用

Biomedicine and Pharmacotherapy 2024年 181卷 117702-117702页

作者： Anwar, Faheem Zhang, Kuo Sun, Changcheng Pang, Meijun Zhou, Wanqi Li, Haodong He, Runnan Liu, Xiuyun Ming, Dong Medical School Tianjin University Tianjin 300072 China School of Pharmaceutical Science and Technology Tianjin University 300072 China Haihe Laboratory of Brain-Computer Interaction and Human-Machine Integration Tianjin 300380 China State Key Laboratory of Advanced Medical Materials and Devices Tianjin 300072 China

Hydrocephalus is a severe and life-threatening disease associated with the imbalance of CSF dynamics and affects millions globally at any age, including infants. One cause of pathology that is wide-ranging is genetic mutations to post-traumatic injury. The most effective current pharmacological treatments provide only symptomatic relief and do not address the underlying pathology. At the same time, surgical procedures such as VP shunts performed in lower-income countries are often poorly tolerated due to insufficient diagnostic resources and suboptimal outcomes partially attributable to inferior materials. These problems are compounded by an overall lack of funding that keeps high-quality medical devices out of reach for all but the most developed countries and even among those states. There is a massive variance in treatment effectiveness. This review indicates the necessity for innovative and low-cost, accessible treatment strategies to close these gaps, focusing on current advances in novel therapies, including Pharmacological, gene therapy, and nano-based technologies, which are currently at different stages of clinical trial phases. This review provides an overview of pathophysiology, current treatments, and promising new therapeutic strategies for hydrocephalus. © 2024 The Authors

关键词： Clinical trials Hydrocephalus Non-surgical treatment Pathophysiology Pharmacological treatment Surgical interventions

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：