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

22,998 篇 会议
107 册 图书
93 篇 期刊文献

馆藏范围

23,197 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

13,621 篇 工学
- 11,107 篇 计算机科学与技术...
- 3,478 篇 软件工程
- 2,445 篇 机械工程
- 1,715 篇 光学工程
- 1,076 篇 电气工程
- 1,013 篇 控制科学与工程
- 784 篇 信息与通信工程
- 411 篇 仪器科学与技术
- 352 篇 生物工程
- 251 篇 生物医学工程（可授...
- 196 篇 电子科学与技术（可...
- 114 篇 化学工程与技术
- 107 篇 安全科学与工程
- 100 篇 测绘科学与技术
- 88 篇 建筑学
- 85 篇 交通运输工程
- 84 篇 土木工程
3,494 篇 医学
- 3,481 篇 临床医学
- 81 篇 基础医学(可授医学...
3,240 篇 理学
- 1,939 篇 物理学
- 1,639 篇 数学
- 563 篇 统计学（可授理学、...
- 500 篇 生物学
- 249 篇 系统科学
- 106 篇 化学
521 篇 管理学
- 311 篇 图书情报与档案管...
- 223 篇 管理科学与工程(可...
- 76 篇 工商管理
276 篇 艺术学
- 276 篇 设计学（可授艺术学...
66 篇 法学
- 63 篇 社会学
38 篇 农学
28 篇 教育学
22 篇 经济学
10 篇 军事学
3 篇 文学

主题

10,186 篇 computer vision
3,967 篇 pattern recognit...
3,005 篇 training
2,007 篇 computational mo...
1,817 篇 visualization
1,815 篇 cameras
1,515 篇 feature extracti...
1,481 篇 shape
1,455 篇 three-dimensiona...
1,438 篇 image segmentati...
1,287 篇 robustness
1,205 篇 computer archite...
1,155 篇 semantics
1,147 篇 conferences
1,107 篇 layout
1,093 篇 computer science
1,088 篇 object detection
1,025 篇 benchmark testin...
970 篇 codes
922 篇 face recognition

机构

136 篇 univ sci & techn...
121 篇 univ chinese aca...
118 篇 chinese univ hon...
107 篇 carnegie mellon ...
101 篇 tsinghua univers...
101 篇 microsoft resear...
95 篇 swiss fed inst t...
93 篇 zhejiang univ pe...
82 篇 university of sc...
81 篇 zhejiang univers...
80 篇 university of ch...
77 篇 shanghai ai lab ...
72 篇 shanghai jiao to...
69 篇 national laborat...
67 篇 microsoft res as...
67 篇 alibaba grp peop...
64 篇 adobe research
62 篇 tsinghua univ pe...
60 篇 peking univ peop...
59 篇 univ oxford oxfo...

作者

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

语言

23,131 篇 英文
38 篇 其他
22 篇 中文
5 篇 土耳其文
2 篇 日文

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

共 23198 条记录，以下是4941-4950 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：

Deep Video Matting via Spatio-Temporal Alignment and Aggregation

Deep Video Matting via Spatio-Temporal Alignment and Aggrega...

引用

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

作者： Sun, Yanan Wang, Guanzhi Gu, Qiao Tang, Chi-Keung Tai, Yu-Wing HKUST Daejeon South Korea Stanford Univ Stanford CA 94305 USA Carnegie Mellon Univ Pittsburgh PA 15213 USA Kuaishou Technol Seoul South Korea

ISBN: (纸本)9781665445092

Despite the significant progress made by deep learning in natural image matting, there has been so far no representative work on deep learning for video matting due to the inherent technical challenges in reasoning temporal domain and lack of large-scale video matting datasets. In this paper, we propose a deep learning-based video matting framework which employs a novel and effective spatio-temporal feature aggregation module (ST-FAM). As optical flow estimation can be very unreliable within matting regions, ST-FAM is designed to effectively align and aggregate information across different spatial scales and temporal frames within the network decoder. To eliminate frame-by-frame trimap annotations, a lightweight interactive trimap propagation network is also introduced. The other contribution consists of a large-scale video matting dataset with groundtruth alpha mattes for quantitative evaluation and real-world high-resolution videos with trimaps for qualitative evaluation. Quantitative and qualitative experimental results show that our framework significantly outperforms conventional video matting and deep image matting methods applied to video in presence of multi frame temporal information.

关键词： Deep learning computer vision Annotations Estimation Coherence Predictive models Cognition

来源：评论

学校读者我要写书评

暂无评论

All You Need is Beyond a Good Init: Exploring Better Solution for Training Extremely Deep Convolutional Neural Networks with Orthonormality and Modulation 30

All You Need is Beyond a Good Init: Exploring Better Solutio...

引用

30th ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Xie, Di Xiong, Jiang Pu, Shiliang Hikvis Res Inst Hangzhou Zhejiang Peoples R China

ISBN: (纸本)9781538604571

Deep neural network is difficult to train and this predicament becomes worse as the depth increases. The essence of this problem exists in the magnitude of backpropagated errors that will result in gradient vanishing or exploding phenomenon. We show that a variant of regularizer which utilizes orthonormality among different filter banks can alleviate this problem. Moreover, we design a backward error modulation mechanism based on the quasi-isometry assumption between two consecutive parametric layers. Equipped with these two ingredients, we propose several novel optimization solutions that can be utilized for training a specific-structured (repetitively triple modules of Conv-BNReLU) extremely deep convolutional neural network (CNN) WITHOUT any shortcuts/identity mappings from scratch. Experiments show that our proposed solutions can achieve distinct improvements for a 44-layer and a 110-layer plain networks on both the CIFAR-10 and ImageNet datasets. Moreover, we can successfully train plain CNNs to match the performance of the residual counterparts. Besides, we propose new principles for designing network structure from the insights evoked by orthonormality. Combined with residual structure, we achieve comparative performance on the ImageNet dataset.

关键词： Modulation Neural networks Training Jacobian matrices Convolution computer vision Network architecture

来源：评论

学校读者我要写书评

暂无评论

DIVeR: Real-time and Accurate Neural Radiance Fields with Deterministic Integration for Volume Rendering

DIVeR: Real-time and Accurate Neural Radiance Fields with De...

引用

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

作者： Wu, Liwen Lee, Jae Yong Bhattad, Anand Wang, Yu-Xiong Forsyth, David Univ Illinois Champaign IL 61820 USA

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

DIVeR builds on the key ideas of NeRF and its variants-density models and volume rendering - to learn 3D object models that can be rendered realistically from small numbers of images. In contrast to all previous NeRF methods, DIVeR uses deterministic rather than stochastic estimates of the volume rendering integral. DIVeR's representation is a voxel based field of features. To compute the volume rendering integral, a ray is broken into intervals, one per voxel;components of the volume rendering integral are estimated from the features for each interval using an MLP, and the components are aggregated. As a result, DIVeR can render thin translucent structures that are missed by other integrators. Furthermore, DIVeR's representation has semantics that is relatively exposed compared to other such methods - moving feature vectors around in the voxel space results in natural edits. Extensive qualitative and quantitative comparisons to current state-of-the-art methods show that DIVeR produces models that (1) render at or above state-of-the-art quality, (2) are very small without being baked, (3) render very fast without being baked, and (4) can be edited in natural ways. Our real-time code is available at: https://***/lwwu2/diver-rt

关键词： Solid modeling computer vision Three-dimensional displays Codes Computational modeling Semantics Stochastic processes

来源：评论

学校读者我要写书评

暂无评论

Generalizing to the Open World: Deep Visual Odometry with Online Adaptation

Generalizing to the Open World: Deep Visual Odometry with On...

引用

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

作者： Li, Shunkai Wu, Xin Cao, Yingdian Zha, Hongbin Peking Univ Sch EECS Key Lab Machine Percept MOE PKU SenseTime Machine Vis Joint Lab Beijing Peoples R China

ISBN: (数字)9781665445092

ISBN: (纸本)9781665445092

Despite learning-based visual odometry (VO) has shown impressive results in recent years, the pretrained networks may easily collapse in unseen environments. The large domain gap between training and testing data makes them difficult to generalize to new scenes. In this paper, we propose an online adaptation framework for deep VO with the assistance of scene-agnostic geometric computations and Bayesian inference. In contrast to learning-based pose estimation, our method solves pose from optical flow and depth while the single-view depth estimation is continuously improved with new observations by online learned uncertainties. Meanwhile, an online learned photometric uncertainty is used for further depth and pose optimization by a differentiable Gauss-Newton layer. Our method enables fast adaptation of deep VO networks to unseen environments in a self-supervised manner. Extensive experiments including Cityscapes to KITTI and outdoor KITTI to indoor TUM demonstrate that our method achieves state-of-the-art generalization ability among self-supervised VO methods.

关键词： Training Optical filters Uncertainty Pose estimation Bayes methods pattern recognition Optimization

来源：评论

学校读者我要写书评

暂无评论

Segment-Fusion: Hierarchical Context Fusion for Robust 3D Semantic Segmentation

Segment-Fusion: Hierarchical Context Fusion for Robust 3D Se...

引用

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

作者： Thyagharajan, Anirud Ummenhofer, Benjamin Laddha, Prashant Omer, Om Ji Subramoney, Sreenivas Intel Labs Processor Architecture Res Lab India Bangalore Karnataka India Intel Labs Autonomous Agents Lab Germany Bangalore Karnataka India

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

3D semantic segmentation is a fundamental building block for several scene understanding applications such as autonomous driving, robotics and AR/VR. Several state-of-the-art semantic segmentation models suffer from the part-misclassification problem, wherein parts of the same object are labelled incorrectly. Previous methods have utilized hierarchical, iterative methods to fuse semantic and instance information, but they lack learnability in context fusion, and are computationally complex and heuristic driven. This paper presents Segment-Fusion, a novel attention-based method for hierarchical fusion of semantic and instance information to address the part misclassifications. The presented method includes a graph segmentation algorithm for grouping points into segments that pools point-wise features into segment-wise features, a learnable attention-based network to fuse these segments based on their semantic and instance features, and followed by a simple yet effective connected component labelling algorithm to convert segment features to instance labels. Segment-Fusion can be flexibly employed with any network architecture for semantic/instance segmentation. It improves the qualitative and quantitative performance of several semantic segmentation backbones by upto 5% on the ScanNet and S3DIS datasets.

关键词： Solid modeling Three-dimensional displays Fuses Computational modeling Semantics Network architecture pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Real-time Hyperspectral Imaging in Hardware via Trained Metasurface Encoders

Real-time Hyperspectral Imaging in Hardware via Trained Meta...

引用

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

作者： Makarenko, Maksim Burguete-Lopez, Arturo Wang, Qizhou Getman, Fedor Giancola, Silvio Ghanem, Bernard Fratalocchi, Andrea King Abdullah Univ Sci & Technol KAUST Thuwal 239556900 Saudi Arabia

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Hyperspectral imaging has attracted significant attention to identify spectral signatures for image classification and automated pattern recognition in computer vision. State-of-the-art implementations of snapshot hyperspectral imaging rely on bulky, non-integrated, and expensive optical elements, including lenses, spectrometers, and filters. These macroscopic components do not allow fast data processing for, e.g. real-time and high-resolution videos. This work introduces Hyplex (TM), a new integrated architecture addressing the limitations discussed above. Hyplex (TM) is a CMOS-compatible, fast hyperspectral camera that replaces bulk optics with nanoscale metasurfaces inversely designed through artificial intelligence. Hyplex (TM) does not require spectrometers but makes use of conventional monochrome cameras, opening up the possibility for real-time and high-resolution hyperspectral imaging at inexpensive costs. Hyplex (TM) exploits a model-driven optimization, which connects the physical metasurfaces layer with modern visual computing approaches based on end-to-end training. We design and implement a prototype version of Hyplex (TM) and compare its performance against the state-of-the-art for typical imaging tasks such as spectral reconstruction and semantic segmentation. In all benchmarks, Hyplex (TM) reports the smallest reconstruction error. We additionally present what is, to the best of our knowledge, the largest publicly available labeled hyperspectral dataset for semantic segmentation.(1)

关键词： Optical filters Image segmentation computer vision Semantics Metasurfaces Cameras Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Low-Shot Learning from Imaginary Data 31

Low-Shot Learning from Imaginary Data

引用

31st ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Wang, Yu-Xiong Girshick, Ross Hebert, Martial Hariharan, Bharath FAIR Santa Monica CA 90401 USA Carnegie Mellon Univ Pittsburgh PA 15213 USA Cornell Univ Ithaca NY 14853 USA

ISBN: (纸本)9781538664209

Humans can quickly learn new visual concepts, perhaps because they can easily visualize or imagine what novel objects look like from different views. Incorporating this ability to hallucinate novel instances of new concepts might help machine vision systems perform better low-shot learning, i.e., learning concepts from few examples. We present a novel approach to low-shot learning that uses this idea. Our approach builds on recent progress in meta-learning ("learning to learn") by combining a meta-learner with a "hallucinator" that produces additional training examples, and optimizing both models jointly. Our hallucinator can be incorporated into a variety of meta-learners and provides significant gains: up to a 6 point boost in classification accuracy when only a single training example is available, yielding state-of-the-art performance on the challenging ImageNet low-shot classification benchmark.

关键词： Training Strain Visualization Data visualization Task analysis Feature extraction Machine vision

来源：评论

学校读者我要写书评

暂无评论

Deep Progressive Reinforcement Learning for Skeleton-based Action recognition 31

Deep Progressive Reinforcement Learning for Skeleton-based A...

引用

31st ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Tang, Yansong Tian, Yi Lu, Jiwen Li, Peiyang Zhou, Jie Tsinghua Univ Dept Automat Beijing Peoples R China Tsinghua Univ State Key Lab Intelligent Technol & Syst Beijing Peoples R China Beijing Natl Res Ctr Informat Sci & Technol Beijing Peoples R China

ISBN: (纸本)9781538664209

In this paper, we propose a deep progressive reinforcement learning (DPRL) method for action recognition in skeleton-based videos, which aims to distil the most informative frames and discard ambiguous frames in sequences for recognizing actions. Since the choices of selecting representative frames are multitudinous for each video, we model the frame selection as a progressive process through deep reinforcement learning, during which we progressively adjust the chosen frames by taking two important factors into account: (1) the quality of the selected frames and (2) the relationship between the selected frames to the whole video. Moreover, considering the topology of human body inherently lies in a graph-based structure, where the vertices and edges represent the hinged joints and rigid bones respectively, we employ the graph-based convolutional neural network to capture the dependency between the joints for action recognition. Our approach achieves very competitive performance on three widely used benchmarks.

关键词： Joints Videos Biological system modeling Three-dimensional displays computer vision

来源：评论

学校读者我要写书评

暂无评论

Exploring Unlabeled Faces for Novel Attribute Discovery

Exploring Unlabeled Faces for Novel Attribute Discovery

引用

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

作者： Bahng, Hyojin Chung, Sunghyo Yoo, Seungjoo Choo, Jaegul Korea Univ Seoul South Korea Kakao Corp Jeju Si South Korea Korea Adv Inst Sci & Technol Daejeon South Korea

ISBN: (纸本)9781728171685

Despite remarkable success in unpaired image-to-image translation, existing approaches still require a large amount of labeled images. This is a bottleneck against their realworld applications;in practice, a model trained on a labeled dataset, such as CelebA dataset, does not work well for test images from a different distribution - limiting their applications to unlabeled images of a much larger quantity. In this paper;we attempt to alleviate this necessity for labeled data in the facial image translation domain. We aim to explore the degree to which you can discover novel attributes from unlabeled faces and perform high-quality translation. Ib this end, we use prior knowledge about the visual world as guidance to discover novel attributes and transfer them via a novel normalization method. Experiments show that our method trained on unlabeled data produces high-quality translations, preserves identity, and is perceptually realistic, as good as, or better than, state-of-the-art methods trained on labeled data.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

End-to-End Learnable Geometric vision by Backpropagating PnP Optimization

End-to-End Learnable Geometric Vision by Backpropagating PnP...

引用

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

作者： Chen, Bo Parra, Alvaro Cao, Jiewei Li, Nan Chin, Tat-Jun Univ Adelaide Adelaide SA Australia Shenzhen Univ Shenzhen Peoples R China

ISBN: (纸本)9781728171685

Deep networks excel in learning patterns from large amounts of data. On the other hand, many geometric vision tasks are specified as optimization problems. To seamlessly combine deep learning and geometric vision, it is vital to perform learning and geometric optimization end-to-end. Towards this aim, we present BPnP, a novel network module that backpropagates gradients through a Perspective-nPoints (PnP) solver to guide parameter updates of a neural network. Based on implicit differentiation, we show that the gradients of a "self-contained" PnP solver can be derived accurately and efficiently, as if the optimizer block were a differentiable function. We validate BPnP by incorporating it in a deep model that can learn camera intrinsics, camera extrinsics (poses) and 3D structure from training datasets. Further, we develop an end-to-end trainable pipeline for object pose estimation, which achieves greater accuracy by combining feature-based heatmap losses with 2D-3D reprojection errors. Since our approach can be extended to other optimization problems, our work helps to pave the way to perform learnable geometric vision in a principled manner. Our PyTorch implementation of BPnP is available on http://***/BoChenYS/BPnP.

关键词： Cameras

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 << < 491 492 493 494 495 496 497 498 499 500 > >>

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：