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

50 篇 期刊文献
46 篇 会议
2 篇 学位论文

馆藏范围

98 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

94 篇 工学
- 67 篇 计算机科学与技术...
- 33 篇 电气工程
- 11 篇 测绘科学与技术
- 9 篇 控制科学与工程
- 9 篇 软件工程
- 7 篇 信息与通信工程
- 7 篇 土木工程
- 6 篇 建筑学
- 5 篇 环境科学与工程（可...
- 4 篇 交通运输工程
- 3 篇 生物医学工程（可授...
- 2 篇 机械工程
- 2 篇 仪器科学与技术
- 1 篇 动力工程及工程热...
- 1 篇 电子科学与技术（可...
- 1 篇 石油与天然气工程
- 1 篇 安全科学与工程
- 1 篇 网络空间安全
23 篇 医学
- 20 篇 临床医学
- 5 篇 特种医学
- 1 篇 基础医学(可授医学...
13 篇 理学
- 7 篇 地球物理学
- 3 篇 生物学
- 2 篇 数学
- 1 篇 物理学
- 1 篇 化学
- 1 篇 地理学
3 篇 农学
- 3 篇 作物学
3 篇 管理学
- 3 篇 管理科学与工程(可...
2 篇 文学
- 2 篇 新闻传播学

主题

98 篇 3d semantic segm...
16 篇 point cloud
15 篇 deep learning
10 篇 three-dimensiona...
10 篇 point clouds
9 篇 3d object detect...
7 篇 semantics
6 篇 semantic segment...
6 篇 3d instance segm...
5 篇 task analysis
5 篇 lidar
5 篇 multi-modal fusi...
4 篇 autonomous drivi...
4 篇 3d point cloud
4 篇 3d scene underst...
4 篇 feature extracti...
4 篇 point cloud comp...
3 篇 unsupervised dom...
3 篇 transformers
3 篇 3d reconstructio...

机构

3 篇 univ chinese aca...
3 篇 univ hong kong p...
3 篇 tsinghua univ pe...
3 篇 east china norma...
2 篇 swiss fed inst t...
2 篇 yonsei univ sch ...
2 篇 chinese acad sci...
2 篇 southeast univ s...
2 篇 hku peoples r ch...
2 篇 china univ geosc...
2 篇 xiongan inst inn...
2 篇 china univ geosc...
2 篇 tech univ munich...
2 篇 univ chinese aca...
2 篇 natl univ singap...
1 篇 east china norma...
1 篇 karlsruhe inst t...
1 篇 casia sensetime ...
1 篇 sharper shape sa...
1 篇 cuhk sz peoples ...

作者

4 篇 jiang li
4 篇 wu xiaoyang
3 篇 kim hyoungkwan
3 篇 qu yanyun
3 篇 xie yuan
3 篇 kim juhyeon
3 篇 zhang xiaolin
3 篇 kim yohan
3 篇 li jiamao
3 篇 zhao hengshuang
2 篇 ni peizhou
2 篇 peters torben
2 篇 zhang guanghui
2 篇 litany or
2 篇 jiang tao
2 篇 peng bohao
2 篇 lee gim hee
2 篇 weigel hendrik
2 篇 wan jie
2 篇 beyerer juergen

语言

94 篇 英文
4 篇 其他

检索条件"主题词=3D semantic segmentation"

共 98 条记录，以下是91-100 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：

3d Shape segmentation with Geometric deep Learning 20th

3D Shape Segmentation with Geometric Deep Learning

引用

20th International Conference on Image Analysis and Processing (ICIAP)

作者： Boscaini, davide Poiesi, Fabio Fdn Bruno Kessler Technol Vis Via Sommarive 18 I-38123 Trento Italy

ISBN: (纸本)9783030306427;9783030306410

The semantic segmentation of 3d shapes with a high-density of vertices could be impractical due to large memory requirements. To make this problem computationally tractable, we propose a neural-network based approach that produces 3d augmented views of the 3d shape to solve the whole segmentation as sub-segmentation problems. 3d augmented views are obtained by projecting vertices and normals of a 3d shape onto 2d regular grids taken from different viewpoints around the shape. These 3d views are then processed by a Convolutional Neural Network to produce a probability distribution function (pdf) over the set of the semantic classes for each vertex. These pdfs are then re-projected on the original 3d shape and postprocessed using contextual information through Conditional Random Fields. We validate our approach using 3d shapes of publicly available datasets and of real objects that are reconstructed using photogrammetry techniques. We compare our approach against state-of-the-art alternatives.

关键词： 3d semantic segmentation Geometric deep learning

来源：评论

学校读者我要写书评

暂无评论

RANP: Resource Aware Neuron Pruning at Initialization for 3d CNNs 8

RANP: Resource Aware Neuron Pruning at Initialization for 3D...

引用

8th International Conference on 3d Vision (3dV)

作者： Xu, Zhiwei Ajanthan, Thalaiyasingam Vineet, Vibhav Hartley, Richard Australian Natl Univ Canberra ACT Australia Australian Ctr Robot Vis Canberra ACT Australia Microsoft Res Redmond WA USA CSIRO Data61 Brisbane Qld Australia

ISBN: (纸本)9781728181288

Although 3d Convolutional Neural Networks (CNNs) are essential for most learning based applications involving dense 3d data, their applicability is limited due to excessive memory and computational requirements. Compressing such networks by pruning therefore becomes highly desirable. However, pruning 3d CNNs is largely unexplored possibly because of the complex nature of typical pruning algorithms that embeds pruning into an iterative optimization paradigm. In this work, we introduce a Resource Aware Neuron Pruning (RANP) algorithm that prunes 3d CNNs at initialization to high sparsity levels. Specifically, the core idea is to obtain an importance score for each neuron based on their sensitivity to the loss function. This neuron importance is then reweighted according to the neuron resource consumption related to FLOPs or memory. We demonstrate the effectiveness of our pruning method on 3d semantic segmentation with widely used 3d-UNets on ShapeNet and BraTS'18 as well as on video classification with MobileNetV2 and I3d on UCF101 dataset. In these experiments, our RANP leads to roughly 50%-95% reduction in FLOPs and 35%-80% reduction in memory with negligible loss in accuracy compared to the unpruned networks. This significantly reduces the computational resources required to train 3d CNNs. The pruned network obtained by our algorithm can also be easily scaled up and transferred to another dataset for training.

关键词： 3d CNNs 3d semantic segmentation neuron pruning resource efficient video classification

来源：评论

学校读者我要写书评

暂无评论

Breaking Speed Limits with Simultaneous Ultra-Fast MRI Reconstruction and Tissue segmentation 3

Breaking Speed Limits with Simultaneous Ultra-Fast MRI Recon...

引用

3rd Conference on Medical Imaging with deep Learning (MIdL)

作者： Caliva, Francesco Leynes, Andrew P. Shah, Rutwik Bharadwaj, Upasana Upadhyay Majumdar, Sharmila Larson, Peder E. Z. Pedoia, Valentina Univ Calif San Francisco Dept Radiol & Biomed Imaging Ctr Intelligent Imaging San Francisco CA 94143 USA UC Berkeley UC San Francisco Joint Grad Program B San Francisco CA USA

Magnetic Resonance Image (MRI) acquisition, reconstruction and tissue segmentation are usually considered separate problems. This can be limiting when it comes to rapidly extracting relevant clinical parameters. In many applications, availability of reconstructed images with high fidelity may not be a priority as long as biomarker extraction is reliable and feasible. Built upon this concept, we demonstrate that it is possible to perform tissue segmentation directly from highly undersampled k-space and obtain quality results comparable to those in fully-sampled scenarios. We propose 'TB-recon', a 3d task-based reconstruction framework. TB-recon simultaneously reconstructs MRIs from raw data and segments tissues of interest. To do so, we devised a network architecture with a shared encoding path and two task-related decoders where features flow among tasks. We deployed TB-recon on a set of (up to 24x) retrospectively undersampled MRIs from the Osteoarthritis Initiative dataset, where we automatically segmented knee cartilage and menisci. An experimental study was conducted showing the superior performance of the proposed method over a combination of a standard MRI reconstruction and segmentation method, as well as alternative deep learning based solutions. In addition, our ablation study highlighted the importance of skip connections among the decoders for the segmentation task. Ultimately, we conducted a reader study, where two musculoskeletal radiologists assessed the proposed model's reconstruction performance.

关键词： fast MRI task-based MRI reconstruction multitask deep learning 3d regression 3d semantic segmentation knee cartilage segmentation

来源：评论

学校读者我要写书评

暂无评论

2d-3d scene understanding for autonomous driving: Compréhension 2d-3d de scènes pour la conduite autonome

2D-3D scene understanding for autonomous driving: Compréhen...

引用

作者： Jaritz, Maximilian Paris Sciences et Lettres

学位级别：博士

dans cette th32;se, nous abordons les d33;fis de la raret33; des annotations et la fusion de donn33;es h33;t33;rog32;nes tels que les nuages de points 3d et images 2d. d’abord, nous adoptons une ... 详细信息

dans cette thèse, nous abordons les défis de la rareté des annotations et la fusion de données hétérogènes tels que les nuages de points 3d et images 2d. d’abord, nous adoptons une stratégie de conduite de bout en bout où un réseau de neurones est entraîné pour directement traduire l'entrée capteur (image caméra) en contrôles-commandes, ce qui rend cette approche indépendante des annotations dans le domaine visuel. Nous utilisons l’apprentissage par renforcement profond où l'algorithme apprend de la récompense, obtenue par interaction avec un simulateur réaliste. Nous proposons de nouvelles stratégies d'entraînement et fonctions de récompense pour une meilleure conduite et une convergence plus rapide. Cependant, le temps d’apprentissage reste élevé. C'est pourquoi nous nous concentrons sur la perception dans le reste de cette thèse pour étudier la fusion de nuage de points et d'images. Nous proposons deux méthodes différentes pour la fusion 2d-3d. Premièrement, nous projetons des nuages de points LidAR 3d dans l’espace image 2d, résultant en des cartes de profondeur éparses. Nous proposons une nouvelle architecture encodeur-décodeur qui fusionne les informations de l’image et la profondeur pour la tâche de complétion de carte de profondeur, améliorant ainsi la résolution du nuage de points projeté dans l'espace image. deuxièmement, nous fusionnons directement dans l'espace 3d pour éviter la perte d'informations dû à la projection. Pour cela, nous calculons les caractéristiques d’image issues de plusieurs vues avec un CNN 2d, puis nous les projetons dans un nuage de points 3d global pour les fusionner avec l’information 3d. Par la suite, ce nuage de point enrichi sert d'entrée à un réseau "point-based" dont la tâche est l'inférence de la sémantique 3d par point. Sur la base de ce travail, nous introduisons la nouvelle tâche d'adaptation de domaine non supervisée inter-modalités où on a accès à des données multi-capteurs dans une base de données source annotée et une

关键词： segmentation sémantique 3d Fusion 2d-3d Adaptation de domaine non supervisée Complétion de profondeur Nuage de points Conduite de bout en bout 3d semantic segmentation 2d-3d fusion Unsupervised domain adaptation depth completion Point cloud End-to-end driving 629.89

来源：评论

学校读者我要写书评

暂无评论

Automatic segmentation of the Prostate on 3d CT Images by Using Multiple deep Learning Networks 18

Automatic Segmentation of the Prostate on 3D CT Images by Us...

引用

5th International Conference on Biomedical and Bioinformatics Engineering (ICBBE)

作者： Xiong, Jiayang Jiang, Luan Li, Qiang Shanghai Jiao Tong Univ 800 Dongchuan Shanghai Peoples R China Shanghai United Imaging Healthcare Co Ltd 2258 Chengbei Rd Shanghai 201815 Peoples R China

ISBN: (纸本)9781450365611

Automatic segmentation of the prostate on CT images has many applications in prostate cancer diagnosis and therapy. However, prostate segmentation from CT images is a very challenging task due to the low contrast of soft tissue and the large variations of the prostate shape. In this paper, we propose an automatic segmentation method by using a two dimension (2-d) and a three dimension (3-d) convolutional neural network (CNN). First, instead of segmenting the whole image, we extract the volumes of interest (VOI) accurately to remove irrelevant regions by using a CNN based VOI extraction method (CBVEM). Then, we use the 3-d CNN to learn the holistic three-dimension deep features for distinguishing the prostate voxels from the non-prostate voxels in order to obtain the segmentation results. deep learning networks can automatically learn the deep features based on the data, which are different from the handcrafted features. The proposed method has been evaluated on a dataset of 150 prostate CT images. Experimental results show that our method achieved a dice similarity coefficient of 89.74% compared to the manual segmentation. Our deep learning based method is faster and returns similar results compared to those atlas-based, deformable model-based and feature-based classification methods. due to the CBVEM and 3-d CNN, our method also achieves better performances on the same data in a minimum processing time compared to other deep CNN based methods. This proposed method for automatic segmentation of the prostate on 3-d CT images can have a variety of clinical applications.

关键词： 3d semantic segmentation CT images deep learning prostate

来源：评论

学校读者我要写书评

暂无评论

GLSNet: Global and Local Streams Network for 3d Point Cloud Classification

GLSNet: Global and Local Streams Network for 3D Point Cloud ...

引用

IEEE Applied Imagery Pattern Recognition Workshop (AIPR)

作者： Bao, Rina Palaniappan, Kannappan Zhao, Yunxin Seetharaman, Guna Zeng, Wenjun Univ Missouri Columbia MO 65211 USA Naval Res Lab Washington DC 20375 USA

ISBN: (纸本)9781728147321

We propose a novel deep architecture for semantic labeling of 3d point clouds referred to as Global and Local Streams Network (GLSNet) which is designed to capture both global and local structures and contextual information for large scale 3d point cloud classification. Our GLSNet tackles a hard problem - large differences of object sizes in large-scale point cloud segmentation including extremely large objects like water, and small objects like buildings and trees, and we design a two-branch deep network architecture to decompose the complex problem to separate processing problems at global and local scales and then fuse their predictions. GLSNet combines the strength of Submanifold Sparse Convolutional Network [1] for learning global structure with the strength of PointNet++ [2] for incorporating local information. The first branch of GLSNet processes a full point cloud in the global stream, and it captures long range information about the geometric structure by using a U-Net structured Submanifold Sparse Convolutional Network (SSCN-U) architecture. The second branch of GLSNet processes a point cloud in the local stream, and it partitions 3d points into slices and processes one slice of the cloud at a time by using the PointNet++ architecture. The two streams of information are fused by max pooling over their classification prediction vectors. Our results on the IEEE GRSS data Fusion Contest Urban semantic 3d, Track 4 (dFT4) [3] [4] [5] point cloud classification dataset have shown that GLSNet achieved performance gains of almost 4% in mIOU and 1% in overall accuracy over the individual streams on the held-back testing dataset.

关键词： Point clouds 3d semantic segmentation Global and local streams

来源：评论

学校读者我要写书评

暂无评论

GLSNet: Global and Local Streams Network for 3d Point Cloud Classification

GLSNet: Global and Local Streams Network for 3D Point Cloud ...

引用

Applied Imagery Pattern Recognition Workshop (AIPR)

作者： Rina Bao Kannappan Palaniappan Yunxin Zhao Guna Seetharaman Wenjun Zeng Dept. of Electrical Engineering and Computer Science University of Missouri Columbia MO USA Naval Research Laboratory Washington D.C. USA

ISBN: (数字)9781728147321

ISBN: (纸本)9781728147338

We propose a novel deep architecture for semantic labeling of 3d point clouds referred to as Global and Local Streams Network (GLSNet) which is designed to capture both global and local structures and contextual information for large scale 3d point cloud classification. Our GLSNet tackles a hard problem - large differences of object sizes in large-scale point cloud segmentation including extremely large objects like water, and small objects like buildings and trees, and we design a two-branch deep network architecture to decompose the complex problem to separate processing problems at global and local scales and then fuse their predictions. GLSNet combines the strength of Submanifold Sparse Convolutional Network [1] for learning global structure with the strength of PointNet++ [2] for incorporating local information. The first branch of GLSNet processes a full point cloud in the global stream, and it captures long range information about the geometric structure by using a U-Net structured Submanifold Sparse Convolutional Network (SSCN-U) architecture. The second branch of GLSNet processes a point cloud in the local stream, and it partitions 3d points into slices and processes one slice of the cloud at a time by using the PointNet ++ architecture. The two streams of information are fused by max pooling over their classification prediction vectors. Our results on the IEEE GRSS data Fusion Contest Urban semantic 3d, Track 4 (dFT4) [3] [4] [5] point cloud classification dataset have shown that GLSNet achieved performance gains of almost 4% in mIOU and 1% in overall accuracy over the individual streams on the held-back testing dataset.

关键词： Point clouds 3d semantic segmentation Global and local streams Clouds streams rivers geometrical construction Taxonomy NETWORK STRUCTURE Three dimensions

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach Based on Cluster-group for Classification of 3d Residential Scene

A Novel Approach Based on Cluster-group for Classification o...

引用

International Conference on Information Science, Electronics and Electrical Engineering (ISEEE)

作者： Lu, Guiliang Zhou, Yu Yu, Yao du, Sidan Nanjing Univ Sch Elect Sci & Engn Nanjing Peoples R China

ISBN: (纸本)9781479931972

To understand scenes and help autonomous robots and cars, researchers' attention is directed through the problem of classifying 3d point cloud. In this paper, we present a novel approach to semantically segment 3d point cloud of residential scenes captured by a lidar sensor. Our approach is based on a dual-scale analysis: a small-scale clustering and a large-scale grouping. Features used to train our AdaBoost classifier are then extracted from clusters and groups. We evaluate our method with a challenging lidar data set. The result shows our approach can classify scene objects accurately.

关键词： 3d semantic segmentation Classification Point Cloud Lidar

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10页 << < 1 2 3 4 5 6 7 8 9 10 > >>

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：