检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

1,593 篇 会议
20 篇 期刊文献
5 册 图书

馆藏范围

1,618 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

695 篇 工学
- 455 篇 计算机科学与技术...
- 429 篇 软件工程
- 190 篇 电气工程
- 184 篇 信息与通信工程
- 66 篇 光学工程
- 59 篇 机械工程
- 59 篇 生物医学工程（可授...
- 44 篇 仪器科学与技术
- 44 篇 控制科学与工程
- 42 篇 电子科学与技术（可...
- 28 篇 测绘科学与技术
- 26 篇 土木工程
- 25 篇 建筑学
- 14 篇 环境科学与工程（可...
- 14 篇 生物工程
- 11 篇 材料科学与工程（可...
237 篇 医学
- 217 篇 临床医学
- 23 篇 基础医学(可授医学...
- 23 篇 特种医学
- 20 篇 药学(可授医学、理...
203 篇 理学
- 96 篇 物理学
- 70 篇 数学
- 21 篇 生物学
- 20 篇 化学
- 19 篇 地球物理学
- 18 篇 统计学（可授理学、...
- 12 篇 系统科学
53 篇 管理学
- 32 篇 管理科学与工程(可...
- 24 篇 图书情报与档案管...
- 13 篇 工商管理
5 篇 法学
5 篇 农学
4 篇 经济学
1 篇 教育学
1 篇 文学
1 篇 军事学

主题

289 篇 three-dimensiona...
213 篇 shape
193 篇 cameras
182 篇 solid modeling
175 篇 visualization
175 篇 image reconstruc...
157 篇 data visualizati...
128 篇 layout
95 篇 surface reconstr...
89 篇 data mining
87 篇 geometry
83 篇 robustness
73 篇 training
71 篇 rendering (compu...
70 篇 image segmentati...
70 篇 feature extracti...
70 篇 humans
65 篇 computational mo...
62 篇 computer vision
52 篇 computer science

机构

9 篇 stanford univers...
7 篇 carnegie mellon ...
6 篇 centre for visio...
6 篇 informatics and ...
6 篇 eth zurich
6 篇 google research
6 篇 national laborat...
5 篇 information proc...
5 篇 princeton univer...
5 篇 department of co...
5 篇 technical univer...
5 篇 johns hopkins un...
5 篇 the chinese univ...
4 篇 shanghai jiao to...
4 篇 max planck insti...
4 篇 department of in...
4 篇 university of ch...
4 篇 univ n carolina ...
4 篇 peking univ natl...
4 篇 university of so...

作者

10 篇 adrian hilton
8 篇 m.g. strintzis
8 篇 pollefeys marc
7 篇 luc van gool
7 篇 hongbin zha
7 篇 g.m. cortelazzo
7 篇 l. van gool
6 篇 gerard pons-moll
6 篇 r.b. fisher
6 篇 strintzis mg
6 篇 ioannis stamos
6 篇 marc pollefeys
5 篇 slobodan ilic
5 篇 stefanie wuhrer
5 篇 christopher zach
5 篇 edmond boyer
5 篇 d. tzovaras
5 篇 christian theoba...
5 篇 michael greenspa...
5 篇 federico tombari

语言

1,611 篇 英文
4 篇 中文
2 篇 其他
1 篇 德文

检索条件"任意字段=International Symposium on 3D Data Processing Visualization and Transmission"

共 1618 条记录，以下是1491-1500 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

GAN-Avatar: Controllable Personalized GAN-based Human Head Avatar

GAN-Avatar: Controllable Personalized GAN-based Human Head A...

引用

international Conference on 3d Imaging, Modeling, processing, visualization and transmission (3dIMPVT)

作者： Berna Kabadayi Wojciech Zielonka Bharat Lal Bhatnagar Gerard Pons-Moll Justus Thies Max Planck Institute for Intelligent Systems Tübingen Germany University of Tübingen Max Planck Institute for Informatics Germany Tübingen AI Center 5Max Planck Institute for Informatics Germany Technical University of Darmstadt

ISBN: (数字)9798350362459

ISBN: (纸本)9798350362466

digital humans and, especially, 3d facial avatars have raised a lot of attention in the past years, as they are the backbone of several applications like immersive telepresence in AR or VR. despite the progress, facial avatars reconstructed from commodity hardware are incomplete and miss out on parts of the side and back of the head, severely limiting the usability of the avatar. This limitation in prior work stems from their requirement of face tracking, which fails for profile and back views. To address this issue, we propose to learn person-specific animatable avatars from images without assuming to have access to precise facial expression tracking. At the core of our method, we leverage a 3d-aware generative model that is trained to reproduce the distribution of facial expressions from the training data. To train this appearance model, we only assume to have a collection of 2d images with the corresponding camera parameters. For controlling the model, we learn a mapping from 3dMM facial expression parameters to the latent space of the generative model. This mapping can be learned by sampling the latent space of the appearance model and reconstructing the facial parameters from a normalized frontal view, where facial expression estimation performs well. With this scheme, we decouple 3d appearance reconstruction and animation control to achieve high fidelity in image synthesis. In a series of experiments, we compare our proposed technique to state-of-the-art monocular methods and show superior quality while not requiring expression tracking of the training data.

关键词： Head Three-dimensional displays Telepresence Avatars Training data Aerospace electronics Hardware

来源：评论

学校读者我要写书评

暂无评论

Java-based tool for synthetic aperture radar image analysis

Java-based tool for synthetic aperture radar image analysis

引用

international symposium on Image and Signal processing and Analysis

作者： C. Huallparimachi d. Rodriguez Electrical and Computer Engineering University of Puerto Rico Mayaguez Puerto Rico

This paper describes the design and development of a Java-based distributed system tool-environment for image analysis with special attention given to synthetic aperture radar (SAR) imaging applications. This tool-environment allows a given user to effect important image processing functions such as to visualize, manipulate, improve, filter, detect edges, reduce the noise, as well as to carry out raw data formatting, image formation operations, Kronecker array filtering, and feature extraction on SAR images. Also, this system has the unique option of allowing end-users to add their own customized algorithms as encapsulated operators to act on elements resident on local or remote SAR images-servers on a computer network.

关键词： Java Image analysis Image edge detection Synthetic aperture radar Image processing data visualization Filters Radar detection Noise reduction Filtering

来源：评论

学校读者我要写书评

暂无评论

Efficient surface reconstruction from range curves

Efficient surface reconstruction from range curves

引用

international Conference on 3d Imaging, Modeling, processing, visualization and transmission (3dIMPVT)

作者： d. Tubic P. Hebert d. Laurendeau Computer Vision and Systems Laboratory University Laval Québec Canada Computer Vision and Systems Laboratory University of Laval QUE Canada

We propose an approach for surface reconstruction of free-form rigid objects from an arbitrary set of intersecting range curves. A strategy for updating the reconstructed surface during data acquisition is described as well. Geometric and color information is accumulated in a volumetric structure in which a vector field is built and updated. Moreover, the information that is needed for efficient curve registration is directly available in this vector field. This leads to a unified modeling approach combining surface reconstruction and curve registration. The algorithm implementing the approach is of linear complexity with respect to the number of input curves and makes it suitable for interactive modeling. A compression scheme based on a multiresolution decomposition of vector fields is introduced as well. Simulated data from a set of curvilinear patterns as well as data acquired with a hand-held range sensor are used to validate the approach.

关键词： Surface reconstruction Image reconstruction Surface fitting Vectors Image sensors Reconstruction algorithms Surface emitting lasers Computational complexity Computer vision Laboratories

来源：评论

学校读者我要写书评

暂无评论

Radargrammetric processing for 3-d building extraction from high-resolution airborne SAR data

Radargrammetric processing for 3-D building extraction from ...

引用

IEEE international symposium on Geoscience and Remote Sensing (IGARSS)

作者： E. Simonetto H. Oriot R. Garello J. Le Caillec CEA-DAM DASE/LDG Bruyeres-le-Chatel France ONERA/DTIM/IOR Chatillon France ENST Bretagne TSI Brest France

来源：评论

学校读者我要写书评

暂无评论

Extract and display moving object in all direction by using stereo omnidirectional system (SOS)

Extract and display moving object in all direction by using ...

引用

international Conference on 3d Imaging, Modeling, processing, visualization and transmission (3dIMPVT)

作者： d. Shimada H. Tanahashi K. Kato K. Yamamoto Department of Information Science Gifu University Gifu Japan HOIP Softopia Japan and JST Gifu Japan

ISBN: (纸本)0769509843

In the near future, a robot for use not only in industrial purpose but also a typical families may be introduced. In order to support human behavior it is necessary for robot vision to acquire information in large spaces. To obtain this information, we acquire three dimensional data in all direction by using SOS (Stereo Omnidirectional System), extract the moving object such as a human and display the extracted object. There are many systems for moving object extraction using color information. However the result is influenced greatly by a lighting condition. In this paper to acquire distance information in all directions during real time by SOS, we propose a method that extracts the moving object in all directions by using a depth map. Finally, we also developed an interface that displays the moving object, which is extracted.

关键词： displays Humans Object detection data mining Service robots Orbital robotics Image resolution Information science Cameras Robot vision systems

来源：评论

学校读者我要写书评

暂无评论

data analisis of 4d phase contrast MRI in healthy and non-healthy patients

Data analisis of 4D phase contrast MRI in healthy and non-he...

引用

international symposium on Image and Signal processing and Analysis

作者： Eduardo Soudah Maurizio Bordone Marcelino Rodriguez Jorge S. Pérez Chi-Hion Li Francesc Carreras UPC International Center for Numerical Methods in Engeneering (CIMNE) Spain Clinical and Translational Cardiology Sant Pau Biomedical Research Institute Spain

Time-resolved, 3-dimensional phase-contrast magnetic resonance imaging (3d+t PCMRI) is employed to obtain complete spatial and temporal coverage of the vessels blood combined with spatially registered 3-directional pulsatile blood flow velocities[1][2]. Recent studies have reported that Wall Shear Stress (WSS) quantification from PCMRI are able to use the WSS as biomarkers for different aortas pathologies [3]. Figure [1] shows the pathline visualization of blood flow during one cardiac cycle in the heart of a healthy patient at peak early LV filling, diastasis, peak atrial contraction, and peak systole.

关键词： Blood flow Three-dimensional displays Biomedical imaging Magnetic resonance Magnetic resonance imaging Stress Pathology

来源：评论

学校读者我要写书评

暂无评论

Remote Scene Interactive Exploration Based on Asynchronous Trajectory Controlled Virtual Reality 3d Reconstruction

Remote Scene Interactive Exploration Based on Asynchronous T...

引用

Computer, Control and Robotics (ICCCR), international Conference on

作者： Qifa Wu Shuhua Fang Jiyao Wang Software College Southeast University Suzhou China School of Electrical Engineering Southeast University Nanjing China

ISBN: (数字)9798350373141

ISBN: (纸本)9798350373158

Visual Reality's (VR) application in Remote Scene Exploration and Collaboration (RSEAC) has received widespread attention. Users can immersively perceive a 3d environment via a Head-mounted display (HMd). There have always been two key issues in the application development of RSEAC. One is the processing and representation of scene data, and the other is to realize interactive control of Remote Mobile Exploration Vehicle (RMEV). In this paper, a remote scene interactive acquisition and 3d virtual reconstruction system is developed, allowing users to immersively explore remote unknown environments in real time and realize information interaction with RMEV. This paper proposes a representation method that combines virtual and real, using point cloud fitting methods to fit scene point clouds with regular shapes and using shape parameters to replace point cloud transmission and scene reconstruction. An Adaptive Tracking Control (ATC) scheme is proposed to avoid complicated operation processes, and its asynchronous trajectory control method can still achieve interactive control of RMEV when transmission delays occur. Finally, the designed experiments verified that using the point cloud fitting method can effectively reduce the number of transmitted point clouds while ensuring the user's recognition of the scene, and the ATC scheme can accurately realize information interaction with RMEV.

关键词： Point cloud compression visualization Three-dimensional displays Shape Fitting Process control Virtual reality

来源：评论

学校读者我要写书评

暂无评论

A Cross Branch Fusion-Based Contrastive Learning Framework for Point Cloud Self-supervised Learning

A Cross Branch Fusion-Based Contrastive Learning Framework f...

引用

international Conference on 3d Imaging, Modeling, processing, visualization and transmission (3dIMPVT)

作者： Chengzhi Wu Qianliang Huang Kun Jin Julius Pfrommer Jürgen Beyerer Institute for Anthropomatics and Robotics Karlsruhe Institute of Technology Germany Department of Automation Tsinghua University China System Technologies and Image Exploitation IOSB Fraunhofer Institute of Optronics Germany

ISBN: (数字)9798350362459

ISBN: (纸本)9798350362466

Contrastive learning is an essential method in self-supervised learning. It primarily employs a multi-branch strategy to compare latent representations obtained from different branches and train the encoder. In the case of multi-modal input, diverse modalities of the same object are fed into distinct branches. When using single-modal data, the same input undergoes various augmentations before being fed into different branches. However, all existing contrastive learning frameworks have so far only performed contrastive operations on the learned features at the final loss end, with no information exchange between different branches prior to this stage. In this paper, for point cloud unsupervised learning without the use of extra training data, we propose a Contrastive Cross-branch Attention-based framework for Point cloud data (termed PoCCA), to learn rich $3 d$ point cloud representations. By introducing sub-branches, PoCCA allows information exchange between different branches before the loss end. Experimental results demonstrate that in the case of using no extra training data, the representations learned with our self-supervised model achieve state-of-the-art performances when used for downstream tasks on point clouds.

关键词： Point cloud compression Representation learning Three-dimensional displays Training data Benchmark testing data models Task analysis

来源：评论

学校读者我要写书评

暂无评论

HOC-Search: Efficient CAd Model and Pose Retrieval From RGB-d Scans

HOC-Search: Efficient CAD Model and Pose Retrieval From RGB-...

引用

international Conference on 3d Imaging, Modeling, processing, visualization and transmission (3dIMPVT)

作者： Stefan Ainetter Sinisa Stekovic Friedrich Fraundorfer Vincent Lepetit Institute for Computer Graphics and Vision Graz University of Technology Graz Austria LIGM École des Ponts Univ Gustave Eiffel CNRS Marne-la-Vallée France

ISBN: (数字)9798350362459

ISBN: (纸本)9798350362466

We present an automated and efficient approach for retrieving high-quality CAd models of objects and their poses in a scene captured by a moving RGB-d camera. We first investigate various objective functions to measure similarity between a candidate CAd object model and the available data, and the best objective function appears to be a ”render-and-compare” method comparing depth and mask rendering. We thus introduce a fast-search method that approximates an exhaustive search based on this objective function for simultaneously retrieving the object category, a CAd model, and the pose of an object given an approximate 3d bounding box. This method involves a search tree that organizes the CAd models and object properties including object category and pose for fast retrieval and an algorithm inspired by Monte Carlo Tree Search, that efficiently searches this tree. We show that this method retrieves CAd models that fit the real objects very well, with a speed-up factor of 10$\times$ to 120$\times$ compared to exhaustive search. We used our method to automatically retrieve CAd models for objects in the ScanNet dataset; our annotations are available at https://***/stefanainetter/SCANnotatedataset.

关键词： Training Point cloud compression Solid modeling Three-dimensional displays Monte Carlo methods Object detection Search problems

来源：评论

学校读者我要写书评

暂无评论

SALUdA: Surface-based Automotive Lidar Unsupervised domain Adaptation

SALUDA: Surface-based Automotive Lidar Unsupervised Domain A...

引用

international Conference on 3d Imaging, Modeling, processing, visualization and transmission (3dIMPVT)

作者： Björn Michele Alexandre Boulch Gilles Puy Tuan-Hung Vu Renaud Marlet Nicolas Courty Valeo.ai Paris France CNRS IRISA Univ. Bretagne Sud Vannes France LIGM Ecole des Ponts Univ Gustave Eiffel CNRS Marne-la-Vallée France

ISBN: (数字)9798350362459

ISBN: (纸本)9798350362466

Learning models on one labeled dataset that generalize well on another domain is a difficult task, as several shifts might happen between the data domains. This is notably the case for lidar data, for which models can exhibit large performance discrepancies due for instance to different lidar patterns or changes in acquisition conditions. This paper addresses the corresponding Unsupervised domain Adaptation (UdA) task for semantic segmentation. To mitigate this problem, we introduce an unsupervised auxiliary task of learning an implicit underlying surface representation simultaneously on source and target data. As both domains share the same latent representation, the model is forced to accommodate discrepancies between the two sources of data. This novel strategy differs from classical minimization of statistical divergences or lidar-specific domain adaptation techniques. Our experiments demonstrate that our method achieves a better performance than the current state of the art, both in real-to-real and synthetic-to-real *** project repository: ***/valeoai/SALUdA

关键词： Adaptation models Surface reconstruction Laser radar Three-dimensional displays Semantic segmentation data models Proposals

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共162页 << < 146 147 148 149 150 151 152 153 154 155 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：