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

22,774 篇 会议
111 篇 期刊文献
23 册 图书

馆藏范围

22,907 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

13,400 篇 工学
- 10,881 篇 计算机科学与技术...
- 3,451 篇 软件工程
- 2,430 篇 机械工程
- 1,722 篇 光学工程
- 1,011 篇 控制科学与工程
- 997 篇 电气工程
- 762 篇 信息与通信工程
- 394 篇 仪器科学与技术
- 337 篇 生物工程
- 257 篇 生物医学工程（可授...
- 215 篇 电子科学与技术（可...
- 113 篇 化学工程与技术
- 113 篇 安全科学与工程
- 98 篇 测绘科学与技术
- 94 篇 交通运输工程
- 86 篇 建筑学
- 82 篇 土木工程
3,362 篇 医学
- 3,348 篇 临床医学
- 79 篇 基础医学(可授医学...
3,252 篇 理学
- 1,953 篇 物理学
- 1,665 篇 数学
- 567 篇 统计学（可授理学、...
- 484 篇 生物学
- 245 篇 系统科学
- 110 篇 化学
507 篇 管理学
- 299 篇 图书情报与档案管...
- 220 篇 管理科学与工程(可...
- 75 篇 工商管理
252 篇 艺术学
- 252 篇 设计学（可授艺术学...
62 篇 法学
- 59 篇 社会学
40 篇 农学
25 篇 教育学
19 篇 经济学
11 篇 军事学
3 篇 文学

主题

10,127 篇 computer vision
4,025 篇 pattern recognit...
2,900 篇 training
1,958 篇 computational mo...
1,792 篇 cameras
1,759 篇 visualization
1,485 篇 shape
1,466 篇 image segmentati...
1,448 篇 feature extracti...
1,412 篇 three-dimensiona...
1,288 篇 robustness
1,169 篇 computer archite...
1,144 篇 layout
1,141 篇 computer science
1,134 篇 semantics
1,070 篇 object detection
1,043 篇 conferences
1,009 篇 benchmark testin...
967 篇 codes
810 篇 face recognition

机构

135 篇 univ sci & techn...
118 篇 univ chinese aca...
118 篇 chinese univ hon...
110 篇 carnegie mellon ...
99 篇 tsinghua univers...
99 篇 microsoft resear...
94 篇 swiss fed inst t...
92 篇 zhejiang univ pe...
82 篇 university of sc...
81 篇 zhejiang univers...
77 篇 shanghai ai lab ...
77 篇 university of ch...
72 篇 shanghai jiao to...
68 篇 microsoft res as...
65 篇 national laborat...
65 篇 alibaba grp peop...
64 篇 tsinghua univ pe...
63 篇 adobe research
60 篇 peking univ peop...
59 篇 peng cheng labor...

作者

78 篇 van gool luc
72 篇 timofte radu
63 篇 zhang lei
45 篇 luc van gool
40 篇 yang yi
37 篇 loy chen change
33 篇 xiaoou tang
33 篇 li stan z.
33 篇 qi tian
32 篇 sun jian
31 篇 liu yang
31 篇 li fei-fei
30 篇 chen chen
30 篇 tian qi
30 篇 pascal fua
29 篇 darrell trevor
28 篇 ying shan
27 篇 li xin
27 篇 vasconcelos nuno
27 篇 hanqing lu

语言

22,831 篇 英文
50 篇 其他
20 篇 中文
5 篇 土耳其文
2 篇 日文

检索条件"任意字段=1994 IEEE Computer-Society Conference on Computer Vision and Pattern Recognition"

共 22908 条记录，以下是4481-4490 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：

clDice - a Novel Topology-Preserving Loss Function for Tubular Structure Segmentation

clDice - a Novel Topology-Preserving Loss Function for Tubul...

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Shit, Suprosanna Paetzold, Johannes C. Sekuboyina, Anjany Ezhov, Ivan Unger, Alexander Zhylka, Andrey Pluim, Josien P. W. Bauer, Ulrich Menze, Bjoern H. Tech Univ Munich Munich Germany Eindhoven Univ Technol Eindhoven Netherlands

ISBN: (纸本)9781665445092

Accurate segmentation of tubular, network-like structures, such as vessels, neurons, or roads, is relevant to many fields of research. For such structures, the topology is their most important characteristic;particularly preserving connectedness: in the case of vascular networks, missing a connected vessel entirely alters the blood-flow dynamics. We introduce a novel similarity measure termed centerline-Dice (short clDice), which is calculated on the intersection of the segmentation masks and their (morphological) skeleta. We theoretically prove that clDice guarantees topology preservation up to homotopy equivalence for binary 2D and 3D segmentation. Extending this, we propose a computationally efficient, differentiable loss function (soft-clDice) for training arbitrary neural segmentation networks. We benchmark the soft-clDice loss on five public datasets, including vessels, roads and neurons (2D and 3D). Training on soft-clDice leads to segmentation with more accurate connectivity information, higher graph similarity, and better volumetric scores.

关键词： Training computer vision Three-dimensional displays Network topology Roads Neurons Neural networks

来源：评论

学校读者我要写书评

暂无评论

Recurrent Multi-view Alignment Network for Unsupervised Surface Registration

Recurrent Multi-view Alignment Network for Unsupervised Surf...

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Feng, Wanquan Zhang, Juyong Cai, Hongrui Xu, Haofei Hou, Junhui Bao, Hujun Univ Sci & Technol China Hefei Anhui Peoples R China City Univ Hong Kong Hong Kong Peoples R China Zhejiang Univ Hangzhou Zhejiang Peoples R China

ISBN: (纸本)9781665445092

Learning non-rigid registration in an end-to-end manner is challenging due to the inherent high degrees of freedom and the lack of labeled training data. In this paper, we resolve these two challenges simultaneously. First, we propose to represent the non-rigid transformation with a point-wise combination of several rigid transformations. This representation not only makes the solution space well-constrained but also enables our method to be solved iteratively with a recurrent framework, which greatly reduces the difficulty of learning. Second, we introduce a differentiable loss function that measures the 3D shape similarity on the projected multi-view 2D depth images so that our full framework can be trained end-to-end without ground truth supervision. Extensive experiments on several different datasets demonstrate that our proposed method outperforms the previous state-of-the-art by a large margin.

关键词： Training computer vision Three-dimensional displays Shape Shape measurement Training data Loss measurement

来源：评论

学校读者我要写书评

暂无评论

Monitoring Social Insect Activity with Minimal Human Supervision

Monitoring Social Insect Activity with Minimal Human Supervi...

引用

ieee computer society conference on computer vision and pattern recognition Workshops (CVPRW)

作者： Tarun Sharma Julian M. Wagner Sara Beery William B. Dickson Michael H. Dickinson Joseph Parker California Institute of Technology USA MIT USA

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Tracking the behavior of animals and their group dynamics in nature offers a crucial look into the delicate ecological networks that compose wildlife diversity. The velvety tree ant (Liometopum occidentale) is an ecologically dominant ant species found in South Western North America; their extensive foraging activity shapes forest communities, and their nests are a biodiversity hot-spot for a multitude of symbiotic invertebrates (myrmecophiles). Despite their vital role in the ecosystem, their activity is largely unstudied. In this work, we develop a multi-sensor camera trap, named ’Ethocam,’ to capture ant behavioral patterns in the field, and combine this technology with a computer vision approach to track colony activity in an undisturbed fashion. We demonstrate an accurate system for counting ants built with minimal human labeling. We show that L. occidentale activity drops rapidly through the morning and study the effect of environmental conditions on ant count. We also report the occurrences of the ants’ interactions with other invertebrates in our camera trap data. Together, these findings demonstrate the potential of our system to capture the behavior of Liometopum occidentale as well as its complex associations with various local species including symbionts, potentially at landscape scale. Our study provides proof of concept for the promise of low-cost remote monitoring of social insect populations.

关键词： Symbiosis computer vision Shape Insects Wildlife Vegetation Cameras

来源：评论

学校读者我要写书评

暂无评论

ContactOpt: Optimizing Contact to Improve Grasps

ContactOpt: Optimizing Contact to Improve Grasps

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Grady, Patrick Tang, Chengcheng Twigg, Christopher D. Minh Vo Brahmbhatt, Samarth Kemp, Charles C. Georgia Inst Technol Atlanta GA 30332 USA Facebook Real Labs Res Redmond WA USA Intel Labs Hillsboro OR USA

ISBN: (纸本)9781665445092

Physical contact between hands and objects plays a critical role in human grasps. We show that optimizing the pose of a hand to achieve expected contact with an object can improve hand poses inferred via image-based methods. Given a hand mesh and an object mesh, a deep model trained on ground truth contact data infers desirable contact across the surfaces of the meshes. Then, ContactOpt efficiently optimizes the pose of the hand to achieve desirable contact using a differentiable contact model. Notably, our contact model encourages mesh interpenetration to approximate deformable soft tissue in the hand. In our evaluations, our methods result in grasps that better match ground truth contact, have lower kinematic error, and are significantly preferred by human participants. Code and models are available online(1).

关键词： Deformable models computer vision Codes Pose estimation Biological tissues Kinematics Data models

来源：评论

学校读者我要写书评

暂无评论

Posterior Promoted GAN with Distribution Discriminator for Unsupervised Image Synthesis

Posterior Promoted GAN with Distribution Discriminator for U...

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Zhang, Xianchao Cheng, Ziyang Zhang, Xiaotong Liu, Han Dalian Univ Technol Sch Software Key Lab Ubiquitous Network & Serv Software Liaoni Dalian Peoples R China

ISBN: (纸本)9781665445092

Sufficient real information in generator is a critical point for the generation ability of GAN. However, GAN and its variants suffer from lack of this point, resulting in brittle training processes. In this paper, we propose a novel variant of GAN, Posterior Promoted GAN (P(2)GAN), which promotes generator with the real information in the posterior distribution produced by discriminator. In our framework, different from other variants of GAN, the discriminator maps images to a multivariate Gaussian distribution and extracts real information. The generator employs the real information by AdaIN and a latent code regularizer. Besides, reparameterization trick and pretraining is applied to guarantee a stable training process in practice. The convergence of P(2)GAN is theoretically proved. Experimental results on typical high-dimensional multi-modal datasets demonstrate that P(2)GAN has achieved comparable results with the state-of-the-art variants of GAN on unsupervised image synthesis.

关键词： Training Manifolds Interpolation computer vision Image synthesis Computational modeling Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Exploring Sparsity in Image Super-Resolution for Efficient Inference

Exploring Sparsity in Image Super-Resolution for Efficient I...

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Wang, Longguang Dong, Xiaoyu Wang, Yingqian Ying, Xinyi Lin, Zaiping An, Wei Guo, Yulan Natl Univ Def Technol Changsha Peoples R China Univ Tokyo Tokyo Japan RIKEN AIP Tokyo Japan

ISBN: (纸本)9781665445092

Current CNN-based super-resolution (SR) methods process all locations equally with computational resources being uniformly assigned in space. However, since missing details in low-resolution (LR) images mainly exist in regions of edges and textures, less computational resources are required for those flat regions. Therefore, existing CNN-based methods involve redundant computation in flat regions, which increases their computational cost and limits their applications on mobile devices. In this paper, we explore the sparsity in image SR to improve inference efficiency of SR networks. Specifically, we develop a Sparse Mask SR (SMSR) network to learn sparse masks to prune redundant computation. Within our SMSR, spatial masks learn to identify "important" regions while channel masks learn to mark redundant channels in those "unimportant" regions. Consequently, redundant computation can be accurately localized and skipped while maintaining comparable performance. It is demonstrated that our SMSR achieves state-of-the-art performance with 41%/33%/27% FLOPs being reduced for x2/3/4 SR.

关键词： Performance evaluation computer vision Codes Image edge detection Superresolution Mobile handsets Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

VolRAFT: Volumetric Optical Flow Network for Digital Volume Correlation of Synchrotron Radiation-based Micro-CT Images of Bone-Implant Interfaces

VolRAFT: Volumetric Optical Flow Network for Digital Volume ...

引用

ieee computer society conference on computer vision and pattern recognition Workshops (CVPRW)

作者： Tak Ming Wong Julian Moosmann Berit Zeller-Plumhoff Institute of Metallic Biomaterials Helmholtz-Zentrum Hereon Germany Institute of Materials Physics Helmholtz-Zentrum Hereon Germany

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

In materials science research, digital volume correlation (DVC) analysis is commonly used to track deformations and strains to elucidate morphology-function relationships. Optical flow-based DVC is particularly popular because of its robustness to estimate the correlation as a dense deformation vector. Recently, computer vision researchers showed that network-based optical flow approaches can outperform classical iterative optical flow approaches. In this paper, we propose a supervised machine learning approach for digital volume correlation, VolRAFT, that estimates the 3D displacement vector between the reference volume and the deformed volume. The proposed approach extends the state-of-the-art network-based optical flow method, RAFT, from 2D images to 3D volumes such that it predicts the volumetric displacement vector from the input volume pairs. Experiments show that the proposed network performs well in estimating different displacement fields when compared to cutting-edge iterative DVC methods for bone-implant materials based on high resolution synchrotron-radiation micro-computed tomography imaging data.

关键词： Training computer vision Materials science and technology Correlation Three-dimensional displays Deformation Tomography

来源：评论

学校读者我要写书评

暂无评论

KOALAnet: Blind Super-Resolution using Kernel-Oriented Adaptive Local Adjustment

KOALAnet: Blind Super-Resolution using Kernel-Oriented Adapt...

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Kim, Soo Ye Sim, Hyeonjun Kim, Munchurl Korea Adv Inst Sci & Technol Daejeon South Korea

ISBN: (纸本)9781665445092

Blind super-resolution (SR) methods aim to generate a high quality high resolution image from a low resolution image containing unknown degradations. However, natural images contain various types and amounts of blur: some may be due to the inherent degradation characteristics of the camera, but some may even be intentional, for aesthetic purposes (e.g. Bokeh effect). In the case of the latter, it becomes highly difficult for SR methods to disentangle the blur to remove, and that to leave as is. In this paper, we propose a novel blind SR framework based on kernel-oriented adaptive local adjustment (KOALA) of SR features, called KOALAnet, which jointly learns spatially-variant degradation and restoration kernels in order to adapt to the spatially-variant blur characteristics in real images. Our KOALAnet outperforms recent blind SR methods for synthesized LR images obtained with randomized degradations, and we further show that the proposed KOALAnet produces the most natural results for artistic photographs with intentional blur, which are not over-sharpened, by effectively handling images mixed with in-focus and out-of-focus areas.

关键词： Degradation computer vision Codes Filtering Superresolution Cameras Data models

来源：评论

学校读者我要写书评

暂无评论

Understanding Object Dynamics for Interactive Image-to-Video Synthesis

Understanding Object Dynamics for Interactive Image-to-Video...

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Blattmann, Andreas Milbich, Timo Dorkenwald, Michael Ommer, Bjoern Heidelberg Univ Interdisciplinary Ctr Sci Comp HCI Heidelberg Germany

ISBN: (纸本)9781665445092

What would be the effect of locally poking a static scene? We present an approach that learns naturally-looking global articulations caused by a local manipulation at a pixel level. Training requires only videos of moving objects but no information of the underlying manipulation of the physical scene. Our generative model learns to infer natural object dynamics as a response to user interaction and learns about the interrelations between different object body regions. Given a static image of an object and a local poking of a pixel, the approach then predicts how the object would deform over time. In contrast to existing work on video prediction, we do not synthesize arbitrary realistic videos but enable local interactive control of the deformation. Our model is not restricted to particular object categories and can transfer dynamics onto novel unseen object instances. Extensive experiments on diverse objects demonstrate the effectiveness of our approach compared to common video prediction frameworks. Project page is available st https://***/3cxfa2L.

关键词： Training computer vision Limiting Shape Computational modeling Video sequences Data models

来源：评论

学校读者我要写书评

暂无评论

Beyond Bounding-Box: Convex-hull Feature Adaptation for Oriented and Densely Packed Object Detection

Beyond Bounding-Box: Convex-hull Feature Adaptation for Orie...

引用

ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Guo, Zonghao Liu, Chang Zhang, Xiaosong Jiao, Jianbin Ji, Xiangyang Ye, Qixiang Univ Chinese Acad Sci Beijing Peoples R China Tsinghua Univ Beijing Peoples R China

ISBN: (纸本)9781665445092

Detecting oriented and densely packed objects remains challenging for spatial feature aliasing caused by the intersection of reception fields between objects. In this paper, we propose a convex-hull feature adaptation (CFA) approach for configuring convolutional features in accordance with oriented and densely packed object layouts. CFA is rooted in convex-hull feature representation, which defines a set of dynamically predicted feature points guided by the convex intersection over union (CIoU) to bound the extent of objects. CFA pursues optimal feature assignment by constructing convex-hull sets and dynamically splitting positive or negative convex-hulls. By simultaneously considering overlapping convex-hulls and objects and penalizing convex-hulls shared by multiple objects, CFA alleviates spatial feature aliasing towards optimal feature adaptation. Experiments on DOTA and SKU110K-R datasets show that CFA significantly outperforms the baseline approach, achieving new state-of-the-art detection performance.

关键词： Convolutional codes computer vision Layout Object detection Detectors Benchmark testing Feature extraction

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500页 << < 445 446 447 448 449 450 451 452 453 454 > >>

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：