检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Li, Jianning Zhou, Zongwei Yang, Jiancheng Pepe, Antonio Gsaxner, Christina Luijten, Gijs Qu, Chongyu Zhang, Tiezheng Chen, Xiaoxi Li, Wenxuan Wodzinski, Marek Friedrich, Paul Xie, Kangxian Jin, Yuan Ambigapathy, Narmada Nasca, Enrico Solak, Naida Melito, Gian Marco Vu, Viet Duc Memon, Afaque R. Schlachta, Christopher De Ribaupierre, Sandrine Patel, Rajnikant Eagleson, Roy Chen, Xiaojun Mächler, Heinrich Kirschke, Jan Stefan de la Rosa, Ezequiel Christ, Patrick Ferdinand Li, Hongwei Bran Ellis, David G. Aizenberg, Michele R. Gatidis, Sergios Küstner, Thomas Shusharina, Nadya Heller, Nicholas Andrearczyk, Vincent Depeursinge, Adrien Hatt, Mathieu Sekuboyina, Anjany Löffler, Maximilian Liebl, Hans Dorent, Reuben Vercauteren, Tom Shapey, Jonathan Kujawa, Aaron Cornelissen, Stefan Langenhuizen, Patrick Ben-Hamadou, Achraf Rekik, Ahmed Pujades, Sergi Boyer, Edmond Bolelli, Federico Grana, Costantino Lumetti, Luca Salehi, Hamidreza Ma, Jun Zhang, Yao Gharleghi, Ramtin Beier, Susann Sowmya, Arcot Garza-Villarreal, Eduardo A. Balducci, Thania Angeles-Valdez, Diego Souza, Roberto Rittner, Leticia Frayne, Richard Ji, Yuanfeng Ferrari, Vincenzo Chatterjee, Soumick Dubost, Florian Schreiber, Stefanie Mattern, Hendrik Speck, Oliver Haehn, Daniel John, Christoph Nürnberger, Andreas Pedrosa, João Ferreira, Carlos Aresta, Guilherme Cunha, António Campilho, Aurélio Suter, Yannick Garcia, Jose Lalande, Alain Vandenbossche, Vicky Van Oevelen, Aline Duquesne, Kate Mekhzoum, Hamza Vandemeulebroucke, Jef Audenaert, Emmanuel Krebs, Claudia van Leeuwen, Timo Vereecke, Evie Heidemeyer, Hauke Röhrig, Rainer Hölzle, Frank Badeli, Vahid Krieger, Kathrin Gunzer, Matthias Chen, Jianxu van Meegdenburg, Timo Dada, Amin Balzer, Miriam Fragemann, Jana Jonske, Frederic Rempe, Moritz Malorodov, Stanislav Bahnsen, Fin H. Seibold, Constantin Jaus, Alexander Marinov, Zdravko Jaeger, Paul F. Stiefelhagen, Rainer Santos, Ana Sofia Lindo, Mariana Ferreira, André Alves, Victor Kamp, Michael Abourayya, Amr Nensa, Felix Hörst, Fabian Brehmer, Alexander Hein Girardetstraße 2 Essen45131 Germany Graz University of Technology Inffeldgasse 16c Graz8010 Austria Graz Austria The Department of Computer Science Johns Hopkins University Malone Hall 3400 N Charles St BaltimoreMD21218 United States Rte Cantonale Lausanne1015 Switzerland The Department of Measurement and Electronics AGH University of Science and Technology Krakow Poland Sierre Switzerland Department of Biomedical Engineering University of Basel Hegenheimermattweg Allschwil167C CH-4123 Switzerland The Boston College 140 Commonwealth Ave Chestnut HillMA02467 United States University Hospital B7-200 339 Windermere Road LondonN6A 5A5 Canada The Department of Radiology Renji Hospital School of Medicine Shanghai Jiao Tong University Shanghai200240 China The Research Center for Connected Healthcare Big Data ZhejiangLab Zhejiang Hangzhou311121 China The Faculty of Statistics Technical University Dortmund August-Schmidt-Straße 1 Dortmund44227 Germany The Institute of Mechanics Graz University of Technology Kopernikusgasse 24/IV Graz8010 Austria The Institute of Biomedical Manufacturing and Life Quality Engineering State Key Laboratory of Mechanical System and Vibration School of Mechanical Engineering Shanghai Jiao Tong University 800 Dongchuan Road Shanghai200240 China The Department of Cardiac Surgery Medical University Graz Auenbruggerplatz 29 Graz8036 Austria The Department of Diagnostic and Interventional Radiology University Hospital Giessen Justus-Liebig-University Giessen Klinikstraße 33 Giessen35392 Germany The Department of Mechanical Engineering Mehran University of Engineering and Technology Jamshoro Sindh76062 Pakistan The Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China The Geschäftsführender Oberarzt Abteilung für Interventionelle und Diagnostische Neuroradiologie Universitätsklinikum der Technischen Universität München Ismaningerstr. 22 München81675 Germany icometrix Kolonel Be

Prior to the deep learning era, shape was commonly used to describe the objects. Nowadays, state-of-the-art (SOTA) algorithms in medical imaging are predominantly diverging from computer vision, where voxel grids, meshes, point clouds, and implicit surface models are used. This is seen from numerous shape-related publications in premier vision conferences as well as the growing popularity of ShapeNet (about 51,300 models) and Princeton ModelNet (127,915 models). For the medical domain, we present a large collection of anatomical shapes (e.g., bones, organs, vessels) and 3D models of surgical instrument, called MedShapeNet, created to facilitate the translation of data-driven vision algorithms to medical applications and to adapt SOTA vision algorithms to medical problems. As a unique feature, we directly model the majority of shapes on the imaging data of real patients. As of today, MedShapeNet includes 23 datasets with more than 100,000 shapes that are paired with annotations (ground truth). Our data is freely accessible via a web interface and a Python application programming interface (API) and can be used for discriminative, reconstructive, and variational benchmarks as well as various applications in virtual, augmented, or mixed reality, and 3D printing. Exemplary, we present use cases in the fields of classification of brain tumors, skull reconstructions, multi-class anatomy completion, education, and 3D printing. In future, we will extend the data and improve the interfaces. The project pages are: https://***/ and https://***/Jianningli/*** Codes 68T01 © 2023, CC BY.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Toward a Future with Human Hands-Like Haptics: A Universal Framework for Interfacing Existing and Future Multipoint Haptic Devices

引用

IEEE systems, Man and Cybernetics Magazine 2016年第1期2卷 14-25页

作者： Wei, Lei Zhou, Hailing Nahavandi, Saeid Wang, Dangxiao CISR Deakin University GeelongVIC3216 Australia Centre for Intelligent Systems Research Deakin University GeelongVIC3217 Australia State Key Laboratory of Virtual Reality Technology and Systems Robotics Institute Beihang University Beijing China

The two hands and ten fingers that humans are born with are the most dexterous parts of the body and the intrinsic tools that have created our history. To advance human-computer interaction so that we make use of such dexterity, an intuitive interface is highly desirable. Work in this field has led to the era of haptic interaction, yet the advances of haptic hardware and the corresponding software development kits (SDKs) have remained at the singlepoint stage for many years. Compared to the original intention of having multimanual, multifinger haptic devices that support both kinesthetic and tactile feedbacks, single-point kinesthetic haptic devices (SPHs) are a compromise between intuitive interactions and affordability. They are limited for probing-like operations and incapable of performing more sophisticated tasks. This limitation has caused the SPHs to lose much of their value in real-life applications where the dexterity that human hands possess is essential. Another reason for the slow transition from SPHs to multipoint haptic devices (MPHs) is the unique hardware designs and software implementations for MPHs. Unlike SPHs that share a rather similar architecture that can be easily abstracted for common communications, MPHs can be significantly different in their looks and the underlying interaction models, such as a multimanual model for collaborative hand manipulations and a multifinger model for pinch and grasp. The situation becomes even worse when considering incorporating both kinesthetic and tactile feedbacks together for more comprehensive systems, as these two are usually considered separate under existing hardware and SDK implementations, while they actually both belong to haptics and are interdependent on human hands. © 2015 IEEE.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Too far to see? Not really! - Pedestrian detection with scale-aware localization policy

arXiv

引用

arXiv 2017年

作者： Zhang, Xiaowei Cheng, Li Li, Bo Hu, Hai-Miao School of Computer Science and Engineering Beijing Key Laboratory of Digital Media State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing100191 China Bioinformatics Institute A*STAR Singapore and School of Computing National University of Singapore Singapore

A major bottleneck of pedestrian detection lies on the sharp performance deterioration in the presence of small-size pedestrians that are relatively far from the camera. Motivated by the observation that pedestrians of disparate spatial scales exhibit distinct visual appearances, we propose in this paper an active pedestrian detector that explicitly operates over multiple-layer neuronal representations of the input still image. More specifically, convolutional neural nets such as ResNet [20] and faster R-CNNs [35] are exploited to provide a rich and discriminative hierarchy of feature representations as well as initial pedestrian proposals. Here each pedestrian observation of distinct size could be best characterized in terms of the ResNet feature representation at a certain layer of the hierarchy;Meanwhile, initial pedestrian proposals are attained by faster R-CNNs techniques, i.e. region proposal network and follow-up region of interesting pooling layer employed right after the specific ResNet convolutional layer of interest, to produce joint predictions on the bounding-box proposals' locations and categories (i.e. pedestrian or not). This is engaged as input to our active detector where for each initial pedestrian proposal, a sequence of coordinate transformation actions is carried out to determine its proper x-y 2D location and layer of feature representation, or eventually terminated as being background. Empirically our approach is demonstrated to produce overall lower detection errors on widely-used benchmarks, and it works particularly well with far-scale pedestrians. For example, compared with 60.51% log-average miss rate of the state-of-the-art MS-CNN [47] for far-scale pedestrians (those below 80 pixels in bounding-box height) of the Caltech benchmark, the miss rate of our approach is 41.85%, with a notable reduction of 18.68%. Copyright © 2017, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Visual object tracking- classical and contemporary approaches

引用

Frontiers of Computer Science 2016年第1期10卷 167-188页

作者： Ahmad ALI Abdul JALIL Jianwei NIU Xiaoke ZHAO Saima RATHORE Javed AHMED Muhammad AKSAM IFTIKHAR Department of Computer and Information Sciences Pakistan Institute of Engineering & Applied Sciences Islamabad 44000 Pakistan State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing 100191 China Department of Electrical (Telecom) Engineering NUST Military College of Signals Islamabad 44000 Pakistan COMSATS Institute of Information Technology Lahore 54000 Pakistan

Visual object tracking （VOT） is an important sub- field of computer vision. It has widespread application do- mains, and has been considered as an important part of surveillance and security system. VOA facilitates finding the position of target in image coordinates of video frames. While doing this, VOA also faces many challenges such as noise, clutter, occlusion, rapid change in object appearances, highly maneuvered （complex） object motion, illumination changes. In recent years, VOT has made significant progress due to availability of low-cost high-quality video cameras as well as fast computational resources, and many modern techniques have been proposed to handle the challenges faced by VOT. This article introduces the readers to 1） VOT and its applica- tions in other domains, 2） different issues which arise in it, 3） various classical as well as contemporary approaches for object tracking, 4） evaluation methodologies for VOT, and 5） online resources, i.e., annotated datasets and source code available for various tracking techniques.

关键词： visual object tracking computer vision imageprocessing point tracking kernel tracking silhouette track-ing

来源：评论

学校读者我要写书评

暂无评论

Robot Teaching by Teleoperation Based on Visual Interaction and Neural Network Learning

Robot Teaching by Teleoperation Based on Visual Interaction ...

引用

2017 9th International Conference on Modelling, Identification and Control (ICMIC 2017)

作者： Yang Xu Chenguang Yang Junpei Zhong Hongbin Ma Lijun Zhao Min Wang Key Laboratory of Autonomous Systems and Networked Control College of Automation Science and EngineeringSouth China University of Technology National Institute of Advanced Industrial Science and Technology School of Automation Beijing Institution of Technology State Key Laboratory of Robotics and System Harbin Institute of Technology

Traditional methods of Robot teaching require human demonstrators to program with a teaching pendant,which is a complex and time-consuming *** this paper,we propose a novel method based on teleoperation which allows a demonstrator to train robot in an intuitive *** specifically,at the beginning the demonstrator controls a robot by visual *** then a learning algorithm based on radial basis function(RBF) network is used to transfer the demonstrator's motions to the *** verify the effectiveness of this developed methods,several simulation experiments have been carried out which based on Microsoft Kinect Sensor and the virtual Robot Experimentation Platform(V-REP).The experimental results show that this method has achieved satisfactory *** the help of this method,the robot can not only complete the task autonomously after teaching,but also can learn the details of demonstrator's behavior.

关键词： Robot Teaching Teleoperation radial basis function(RBF) network

来源：评论

学校读者我要写书评

暂无评论

Local shape transfer for image co-segmentation 27

Local shape transfer for image co-segmentation

引用

27th British Machine Vision Conference, BMVC 2016

作者： Teng, Wei Zhang, Yu Chen, Xiaowu Li, Jia He, Zhiqiang State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China International Research Institute for Multidisciplinary Science Beihang University Beijing China Lenovo Research China

Image co-segmentation is a challenging computer vision task that aims to segment all pixels of the common objects in an image set. In real-world cases, however, the common objects often vary greatly in poses, locations and scales, making their global shapes highly inconsistent across images and difficult to be segmented. To address this problem, this paper proposes a novel co-segmentation approach that transfers patch-level local object shapes, which appear more consistently across different images. In our approach, we first employ dense correspondences to construct a patch neighbourhood system, which is refined using Locally Linear Embedding. Based on the patch relationships, an efficient algorithm is developed to jointly segment the objects in each image while transferring their local shapes across different images. Experiments show that our approach performs comparably with or better than the state-of-the-arts on iCoseg dataset [2], while achieving more than 31% relative improvements on a challenging benchmark Fashionista [31]. © 2016 The copyright of this document resides with its authors.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Structure-adaptive shape editing for man-made objects

Structure-adaptive shape editing for man-made objects

引用

作者： Fu, Qiang Chen, Xiaowu Su, Xiaoyu Li, Jia Fu, Hongbo State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University China International Research Institute for Multidisciplinary Science Beihang University China School of Creative Media City University of Hong Kong Hong Kong

One of the challenging problems for shape editing is to adapt shapes with diversified structures for various editing needs. In this paper we introduce a shape editing approach that automatically adapts the structure of a shape being edited with respect to user inputs. Given a category of shapes, our approach first classifies them into groups based on the constituent parts. The group-sensitive priors, including both inter-group and intra-group priors, are then learned through statistical structure analysis and multivariate regression. By using these priors, the inherent characteristics and typical variations of shape structures can be well captured. Based on such group-sensitive priors, we propose a framework for real-time shape editing, which adapts the structure of shape to continuous user editing operations. Experimental results show that the proposed approach is capable of both structure-preserving and structure-varying shape editing. © 2016 The Author(s) Computer Graphics Forum © 2016 The Eurographics Association and John Wiley & Sons Ltd. Published by John Wiley & Sons Ltd.

关键词： Multivariant analysis

来源：评论

学校读者我要写书评

暂无评论

Robust object tracking using valid fragments selection 22nd

Robust object tracking using valid fragments selection

引用

22nd International Conference on MultiMedia Modeling, MMM 2016

作者： Zheng, Jin Li, Bo Tian, Peng Luo, Gang Beijing Key Laboratory of Digital Media School of Computer Science and Engineering Beihang University Beijing100191 China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing100191 China Schepens Eye Research Institute Mass Eye and Ear Harvard Medical School BostonMA02114 United States

ISBN: (纸本)9783319276700

Local features are widely used in visual tracking to improve robustness in cases of partial occlusion, deformation and rotation. This paper proposes a local fragment-based object tracking algorithm. Unlike many existing fragment-based algorithms that allocate the weights to each fragment, this method firstly defines discrimination and uniqueness for local fragment, and builds an automatic pre-selection of useful fragments for tracking. Then, a Harris-SIFT filter is used to choose the current valid fragments, excluding occluded or highly deformed fragments. Based on those valid fragments, fragment-based color histogram provides a structured and effective description for the object. Finally, the object is tracked using a valid fragment template combining the displacement constraint and similarity of each valid fragment. The object template is updated by fusing feature similarity and valid fragments, which is scale-adaptive and robust to partial occlusion. The experimental results show that the proposed algorithm is accurate and robust in challenging scenarios. © Springer International Publishing Switzerland 2016.

关键词： Bandpass filters

来源：评论

学校读者我要写书评

暂无评论

A Mixing Control Method Based on Motion Synthesis for virtual Human

A Mixing Control Method Based on Motion Synthesis for Virtua...

引用

3rd International Conference on Smart Materials and Nanotechnology in Engineering(SMNE 2016)

作者： Xinv Zhu Jiayu Chen Chuan Lv Dong Zhou School of Reliability and Systems Engineering Beihang University Science and Technology on Reliability and Environmental Engineering Laboratory & State Key Laboratory of Virtual Reality Technology and Systems Beihang University

virtual reality technology is now required for maintainability design to shorten design cycle and reduce *** the simulation process, virtual human can be animated by immersive motion capture system or non-immersive algorithmic *** both of these approaches have their own limitations, the simulation reliability cannot be guaranteed in complex maintenance *** this paper, we propose a mixing control method based on motion synthesis to animate virtual human in virtual *** performing an elaborate motion, motion capture system is applied, and if a large or complex scene is needed in a motion, algorithmic control method is *** motion clips generated by the two animation approaches, a coherent and integral simulation task is implemented, and the simulation reliability and efficiency are improved.

关键词： cycle A Mixing Control Method Based on Motion Synthesis for virtual Human virtual

来源：评论

学校读者我要写书评

暂无评论

A Classification Method of Human Motions Based on ApEn and RF

A Classification Method of Human Motions Based on ApEn and R...

引用

3rd International Conference on Smart Materials and Nanotechnology in Engineering(SMNE 2016)

作者： Jiayu Chen Xinv Zhu Dong Zhou Chuan Lv School of Reliability and Systems Engineering Beihang University Science and Technology on Reliability and Environmental Engineering Laboratory & State Key Laboratory of Virtual Reality Technology and Systems Beihang University

According to the non-stationary, nonlinear and high dimensional characteristics of human motion caption data, a classification method for human motions based on approximate entropy(ApEn) and random forest(RF) is proposed in this ***, by preprocessing the motion capture data, key joints are selected to represent the motion instead of the all original ***, the feature vector of each motion is extracted by calculating its ***, the feature vectors are severed as the input vectors of the RF classifier for human motions *** an experiment is conducted and the classification results achieve a high classification accuracy for 3 motion patterns(walk, run and jump), which confirms the highly accurate and effective performance of the proposed method.

关键词： A Classification Method of Human Motions Based on ApEn and RF

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：