检索结果-内蒙古大学图书馆

Toward Integrated Automation Status and Alerting Display Management Systems for Vehicles

INCOSE International Symposium 2022年第S1期32卷 213-222页

作者： Moertl, Peter Shi, Elisabeth Sodnik, Jaka Ebinger, Nikolai Bavendiek, Jan Mirnig, Alexander Pretto, Paolo Sarabia, Joseba Trösterer, Sandra Virtual Vehicle Research GmbH Inffeldgasse 21a Graz8010 Austria Bruederstr. 53 Bergisch GladbachD-51427 Germany Nervtech Kidričeva ulica 118 Trzin1236 Slovenia RWTH Aachen University Steinbachstr. 7 Aachen52074 Germany Center for Human-Computer interaction University of Salzburg Jakob-Haringer-Straße 8 Salzburg5020 Austria Derio48160 Spain

With increasing levels of automation on modern vehicles, drivers need more knowledge about their vehicle than ever before. Thereby, the display of vehicle status and alerts are important means for safe and effective use. Nevertheless, there are currently no common and consistent ways of providing such status in-formation to drivers. This is different from other domains where standardized alert management structure are common such as in modern aviation. In current vehicles, initiation, use, and termination of automated driving assistance differs considerably between vehicle models and brands and require special learning ex-periences by the driver and alerts are not prioritized and harmonized across the various onboard systems. With higher levels of automation such complexity is expected to increase enormously. To address this problem, we propose a common taxonomy of vehicle display status and alerting terminology that is based on flight deck regulations in aviation and propose simple principles for their use in a man-aged display status and alerting system. Copyright © 2021 by Peter Moertl. Permission granted to INCOSE to publish and use.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

A Multi-Task Mean Teacher for Semi-Supervised Shadow Detection

A Multi-Task Mean Teacher for Semi-Supervised Shadow Detecti...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Zhihao Chen Lei Zhu Liang Wan Song Wang Wei Feng Pheng-Ann Heng College of Intelligence and Computing Tianjin University Department of Computer Science and Engineering The Chinese University of Hong Kong Department of Computer Science and Engineering University of South Carolina Shenzhen Key Laboratory of Virtual Reality and Human Interaction Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

Existing shadow detection methods suffer from an intrinsic limitation in relying on limited labeled datasets, and they may produce poor results in some complicated situations. To boost the shadow detection performance, this paper presents a multi-task mean teacher model for semi-supervised shadow detection by leveraging unlabeled data and exploring the learning of multiple information of shadows simultaneously. To be specific, we first build a multi-task baseline model to simultaneously detect shadow regions, shadow edges, and shadow count by leveraging their complementary information and assign this baseline model to the student and teacher network. After that, we encourage the predictions of the three tasks from the student and teacher networks to be consistent for computing a consistency loss on unlabeled data, which is then added to the supervised loss on the labeled data from the predictions of the multi-task baseline model. Experimental results on three widely-used benchmark datasets show that our method consistently outperforms all the compared state-of- the-art methods, which verifies that the proposed network can effectively leverage additional unlabeled data to boost the shadow detection performance.

关键词： Task analysis Image edge detection Feature extraction Training Radio frequency Fuses Solid modeling

来源：评论

学校读者我要写书评

暂无评论

Attention Based Hierarchical Aggregation Network for 3D Left Atrial Segmentation 9th

Attention Based Hierarchical Aggregation Network for 3D Left...

引用

9th International Workshop on Statistical Atlases and Computational Models of the Heart: Atrial Segmentation and LV Quantification Challenges, STACOM 2018, held in conjunction with Medical Image Computing and computer-Assisted Intervention, MICCAI 2018

作者： Li, Caizi Tong, Qianqian Liao, Xiangyun Si, Weixin Sun, Yinzi Wang, Qiong Heng, Pheng-Ann School of Computer Science Wuhan University Wuhan430072 China Shenzhen Key Laboratory of Virtual Reality and Human Interaction Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518000 China Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong China

ISBN: (纸本)9783030120283

Atrial fibrillation (AF) is the most common type of cardiac arrhythmia. The atrial segmentation is essential for the understanding of the human atria structure which is vital to the AF treatment. In this paper, we propose a novel three-dimensional (3D) segmentation network combining hierarchical aggregation and attention mechanism for 3D left atrial segmentation, named attention based hierarchical aggregation network (HAANet). In our network, the shallow and deep feature fusion capability of encoder-decoder convolutional neural networks is enhanced through hierarchical aggregation. Besides, attention mechanism is adopted to promote the ability of extracting efficient features. Experimental results demonstrate the HAANet can produce good results for 3D left atrial segmentation and the dice score of our HAANet reaches 92.30. © 2019, Springer Nature Switzerland AG.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

The research experience for undergraduates (REU) principal investigators (PI) guide: Development of a best practices website 125

The research experience for undergraduates (REU) principal i...

引用

125th ASEE Annual Conference and Exposition

作者： Pena, Mariangely Iglesias Gilbert, Stephen B. Payton, Jamie Human Computer Interaction Iowa State University Virtual Reality Applications Center United States Department of Computer and Information Sciences Temple University United States

With the help of the National Science Foundation (NSF), many Principal Investigators (Pls) have been able to mentor undergraduates through Research Experience for Undergraduates (REU) site awards. These REU sites are critical to the development of future graduate students, but can be challenging to run due to several required skills outside the scope of most faculty members' expertise, e.g., recruiting applicants, navigating the logistics of housing visiting undergraduate students, and tracking student outcomes after their REU experiences. In recent years, REU Pls in NSF's computer & Information Science & Engineering (CISE) Directorate have come together through PI meetings to share best practices for running a successful REU site. While PIs inevitably take different approaches to running their sites based on their research projects, there is still a need to provide new Pls with guidance on the different aspects of an REU site such as identifying resources that can assist in recruiting women and underrepresented minority applicants, providing training for graduate students acting as mentors, and strategies for keeping a mentoring connection to undergraduate researchers after they return to their home institutions. Currently, REU site preparation and orientation for new PIs is a face-to-face process that requires careful planning and significant travel costs. The REU PI Guide, a set of web-based resources at https://***/cise-reu-pi-resourcesA was developed to share best practices of experienced PIs and build capacity within the REU PI community in a more scalable and cost-effective way. The REU PI Guide allows PIs to look up advice and guidance when needed and share their own best practices. This paper describes our approach to designing the REU PI Guide. The Guide is a database of documents, examples, and overviews of the different aspects of running an REU site. The Guide was developed by assessing new PIs' needs at an NSF workshop for new PIs, gat

关键词：

来源：评论

学校读者我要写书评

暂无评论

MS-net: Multi-site network for improving prostate segmentation with heterogeneous MRI data

arXiv

引用

arXiv 2020年

作者： Liu, Quande Dou, Qi Yu, Lequan Heng, Pheng Ann Department of Computer Science and Engineering Chinese University of Hong Kong Hong Kong Department of Radiation Oncology Stanford University StanfordCA94305 United States Shenzhen Key Laboratory of Virtual Reality and Human Interaction Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China

Automated prostate segmentation in MRI is highly demanded for computer-assisted diagnosis. Recently, a variety of deep learning methods have achieved remarkable progress in this task, usually relying on large amounts of training data. Due to the nature of scarcity for medical images, it is important to effectively aggregate data from multiple sites for robust model training, to alleviate the insufficiency of single-site samples. However, the prostate MRIs from different sites present heterogeneity due to the differences in scanners and imaging protocols, raising challenges for effective ways of aggregating multi-site data for network training. In this paper, we propose a novel multi-site network (MS-Net) for improving prostate segmentation by learning robust representations, leveraging multiple sources of data. To compensate for the inter-site heterogeneity of different MRI datasets, we develop Domain-Specific Batch Normalization layers in the network backbone, enabling the network to estimate statistics and perform feature normalization for each site separately. Considering the difficulty of capturing the shared knowledge from multiple datasets, a novel learning paradigm, i.e., Multi-site-guided Knowledge Transfer, is proposed to enhance the kernels to extract more generic representations from multi-site data. Extensive experiments on three heterogeneous prostate MRI datasets demonstrate that our MS-Net improves the performance across all datasets consistently, and outperforms state-of-the-art methods for multi-site learning. Copyright © 2020, The Authors. All rights reserved.

关键词： Urology

来源：评论

学校读者我要写书评

暂无评论

Global guidance network for breast lesion segmentation in ultrasound images

arXiv

引用

arXiv 2021年

作者： Xue, Cheng Zhu, Lei Fu, Huazhu Hu, Xiaowei Li, Xiaomeng Zhang, Hai Heng, Pheng-Ann Department of Computer Science and Engineering Chinese University of Hong Kong Hong Kong Department of Applied Mathematics and Theoretical Physics University of Cambridge Inception Institute of Artificial Intelligence Abu Dhabi United Arab Emirates Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong Shenzhen People's Hospital Second Clinical College of Jinan University First Affiliated Hospital of Southern University of Science and Technology Shenzhen Key Laboratory of Virtual Reality and Human Interaction Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China

Automatic breast lesion segmentation in ultrasound helps to diagnose breast cancer, which is one of the dreadful diseases that affect women globally. Segmenting breast regions accurately from ultrasound image is a challenging task due to the inherent speckle artifacts, blurry breast lesion boundaries, and inhomogeneous intensity distributions inside the breast lesion regions. Recently, convolutional neural networks (CNNs) have demonstrated remarkable results in medical image segmentation tasks. However, the convolutional operations in a CNN often focus on local regions, which suffer from limited capabilities in capturing long-range dependencies of the input ultrasound image, resulting in degraded breast lesion segmentation accuracy. In this paper, we develop a deep convolutional neural network equipped with a global guidance block (GGB) and breast lesion boundary detection (BD) modules for boosting the breast ultrasound lesion segmentation. The GGB utilizes the multi-layer integrated feature map as a guidance information to learn the long-range non-local dependencies from both spatial and channel domains. The BD modules learn additional breast lesion boundary map to enhance the boundary quality of a segmentation result refinement. Experimental results on a public dataset and a collected dataset show that our network outperforms other medical image segmentation methods and the recent semantic segmentation methods on breast ultrasound lesion segmentation. Moreover, we also show the application of our network on the ultrasound prostate segmentation, in which our method better identifies prostate regions than state-of-the-art networks. © 2021, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Grimes's Music Video "Shinigami Eyes"

引用

JOURNAL OF POPULAR MUSIC STUDIES 2023年第3期35卷 32-60页

作者： Vernallis, Carol Paris, Cesare Gardner, Justin Woodiwiss, Aubrey Carol Vernallis’s monograph Experiencing Music Video: Aesthetics and Cultural Context (CUP 2004) is the first to articulate a theory of how music lyrics and image can be placed in relation as well as provide detailed analyses of individual videos. Her second Unruly Media: YouTube Music Video and the New Digital Cinema (OUP 2013) takes account of a new mediascape that is driven by intensified audiovisual relations. Her third The Media Swirl (Duke 4/14/23) further considers the contemporary landscape. She is co-editor of Cybermedia: Explorations in Science Sound and Vision and Transmedia Directors (Bloomsbury) and two Oxford Handbooks on audiovisuality. She’s adjunct professor in the department of Cultural Studies and Comparative Literature at the University of Minnesota. Justin Gardner is an Associate Professor in Psychology at Stanford where he heads the Gardner lab. He and his team use a combination of functional magnetic resonance imaging computational modeling and analysis and psychophysical measurements to study how neural activity in the human cortex creates our sense of visual perception. Of particular interest is the ways our brain mechanisms give rise to our remarkable cognitive feats such as selective attention and sensory inference. Gardner is also a member of BioX an affiliate of Institute for Human-Centered Artificial Intelligence (HAI) and a member of Wu Tsai Neurosciences Institute. Cesare Parise is a Senior Lecturer in Psychology at the University of Liverpool where he heads a lab devoted to multisensory perception. His current projects include the development of a model for fly vision that can be adapted to other creatures. Parise’s background is in experimental psychology. After earning his DPhil at Oxon he worked as a research scientist for the Max Planck Institute for Biological Cybernetics and the Center for Excellence in Cognitive Interaction Technologies. In 2016 he joined Facebook Reality Labs (now Meta Reality Labs) as a Primary Investigator in perception science wh

This article draws on recent findings in neuroscience to provide a close reading of Grimes's music video "Shinigami Eyes." It includes interviews with a neuroscientist who specializes in multisensory integration, a vision scientist, a color grader, and a media scholar. While multisensory integration is a burgeoning field, accessible texts and reviews are lacking. There haven't been analyses that apply the findings from the field of multisensory integration to real media objects. Drawing on neuroscience studies, this article explores the concept of Bayesian predictions (a viewer's experience of a present event weighted against previous experiences);the ways neuroscience explains color, size and placement, and emotion work;and processes such as the inverse effectiveness (when neurons boost both lower-res and higher-res signals, with the most perceptible often for sound), super-additive multisensory effects, the attentional blink, the ventriloquist effect, congruence and incongruity, memory, distractors, sound before image and vice versa, and other features. A conversation with the color grader for "Shinigami Eyes" helps fill things in. This article emerges from a belief that modules on neuroscience and industry studies can be incorporated as components of media study courses, and that neuroscience-informed analyses can facilitate interest and engagement with close readings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Inception classification and object detection based joint-CNN for indoor scene classification

Inception classification and object detection based joint-CN...

引用

2018 International MultiConference of Engineers and computer Scientists, IMECS 2018

作者： Tian, Yarding Zhang, Weitong Zhang, Qieshi Lu, Gang School of Computer Science Shaanxi Normal University Xi'an China Shenzhen Key Laboratory of Virtual Reality and Human Interaction Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China

ISBN: (纸本)9789881404886

While convolutional neural network (CNN) has been successfully used in many fields including single-label scene classification, it is vital to note that real world scenes generally contain multiple semantics and multi-label, especially in the indoor scene classification due to its content complexity. At the same time, most approaches try to make the network much deeper to make sure that they can extract more detail information. However, the deeper network will cause a lot of problems such as the increase of computational costs and network costs and so on. In order to solve these problems, this paper presents a novel framework which called Joint-CNN based on the proposed special label extraction and network structure. Extensive experiments on various data sets show that our method has enhanced the performance on MIT indoor67 and SUN397 data sets. © 2018 Newswood Limited. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Walking Imagery Evaluation Based on Multi-view Features and Stacked Denoising Auto-encoder Network

Walking Imagery Evaluation Based on Multi-view Features and ...

引用

IEEE International Symposium on Biomedical Imaging

作者： Enmin Liang Ahmed Elazab Shuang Liang Qiong Wang Tianfu Wang Baiying Lei National-Regional Key Technology Engineering Laboratory for Medical Ultrasound Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging School of Biomedical Engineering Health Science Center Shenzhen University Shenzhen China School of Geographic and Biologic Information Nanjing University of Posts and Telecommunications Nanjing China Shenzhen Key Laboratory of Virtual Reality and Human Interaction Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China

ISBN: (数字)9781538693308

ISBN: (纸本)9781538693315

Brain-computer interfaces (BCIs) based on motor imagery (MI) have played an important role and obtained impressive achievement in exercise rehabilitation. However, most of the previous researches focused on the upper limb, while many disabled patients need the same technology to assist their rehabilitation training. It is more difficult to detect lower limb MI than upper limb because of the deeper and smaller corresponding sensorimotor cortex. To solve this problem, a new paradigm is proposed to perform waking imagery (WI) for subjects in a virtual environment (VE) to further enhance their brain activities. Furthermore, to decode WI efficiently when facing the low reliable and limited data, we propose a stacked denoising auto-encoder (SDAE) network, which is trained on multi-view feature obtained from VE. First, the spatial and frequency based features are extracted and fused from the raw data. Second, we use SDAE network to extract the hidden features from the above features. Third, we fuse the previous features and hidden features to train the Softmax classifier. Experimental results on our self-collected data demonstrate that, SDAE network outperforms other deep learning methods in classifying WI in VE.

关键词： Feature extraction Training Electroencephalography Noise reduction Legged locomotion Machine learning Brain modeling

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

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：