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

22,771 篇 会议
112 篇 期刊文献
23 册 图书

馆藏范围

22,905 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

13,398 篇 工学
- 10,880 篇 计算机科学与技术...
- 3,450 篇 软件工程
- 2,430 篇 机械工程
- 1,721 篇 光学工程
- 1,010 篇 控制科学与工程
- 998 篇 电气工程
- 761 篇 信息与通信工程
- 393 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
- 112 篇 安全科学与工程
- 98 篇 测绘科学与技术
- 92 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...
3,250 篇 理学
- 1,953 篇 物理学
- 1,664 篇 数学
- 567 篇 统计学（可授理学、...
- 484 篇 生物学
- 245 篇 系统科学
- 109 篇 化学
506 篇 管理学
- 299 篇 图书情报与档案管...
- 219 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

10,126 篇 computer vision
4,025 篇 pattern recognit...
2,900 篇 training
1,958 篇 computational mo...
1,792 篇 cameras
1,758 篇 visualization
1,485 篇 shape
1,466 篇 image segmentati...
1,447 篇 feature extracti...
1,412 篇 three-dimensiona...
1,288 篇 robustness
1,169 篇 computer archite...
1,144 篇 layout
1,142 篇 computer science
1,134 篇 semantics
1,071 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

22,844 篇 英文
35 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 22906 条记录，以下是4741-4750 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：

Maximum-likelihood template matching

Maximum-likelihood template matching

引用

ieee conference on computer vision and pattern recognition, CVPR 2000

作者： Olson, Clark F. California Inst of Technology Pasadena CA United States

In image matching applications such as tracking and stereo matching, it is common to use the sum-of-squared-differences (SSD) measure to determine the best match for an image template. However, this measure is sensitive to outliers and is not robust to template variations. We describe a robust measure and efficient search strategy for template matching with a binary or greyscale template using a maximum-likelihood formulation. In addition to subpixel localization and uncertainty estimation, these techniques allow optimal feature selection based on minimizing the localization uncertainty. We examine the use of these techniques for object recognition, stereo matching, feature selection, and tracking.

关键词： pattern matching

来源：评论

学校读者我要写书评

暂无评论

Bootstrapping ViTs: Towards Liberating vision Transformers from Pre-training

Bootstrapping ViTs: Towards Liberating Vision Transformers f...

引用

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

作者： Zhang, Haofei Duan, Jiarui Xue, Mengqi Song, Jie Sun, Li Song, Mingli Zhejiang Univ Hangzhou Zhejiang Peoples R China Zhejiang Univ Shanghai Inst Adv Study Hangzhou Zhejiang Peoples R China

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Recently, vision Transformers (ViTs) are developing rapidly and starting to challenge the domination of convolutional neural networks (CNNs) in the realm of computer vision (CV). With the general-purpose Transformer architecture replacing the hard-coded inductive biases of convolution, ViTs have surpassed CNNs, especially in datasufficient circumstances. However, ViTs are prone to over-fit on small datasets and thus rely on large-scale pre-training, which expends enormous time. In this paper, we strive to liberate ViTs from pre-training by introducing CNNs' inductive biases back to ViTs while preserving their network architectures for higher upper bound and setting up more suitable optimization objectives. To begin with, an agent CNN is designed based on the given ViT with inductive biases. Then a bootstrapping training algorithm is proposed to jointly optimize the agent and ViT with weight sharing, during which the ViT learns inductive biases from the intermediate features of the agent. Extensive experiments on CIFAR-10/100 and ImageNet-1k with limited training data have shown encouraging results that the inductive biases help ViTs converge significantly faster and outperform conventional CNNs with even fewer parameters.

关键词： Training computer vision Upper bound Neural networks Training data Network architecture Transformers

来源：评论

学校读者我要写书评

暂无评论

Know Your Neighbors: Improving Single-View Reconstruction via Spatial vision-Language Reasoning

Know Your Neighbors: Improving Single-View Reconstruction vi...

引用

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

作者： Li, Rui Fischer, Tobias Segu, Mattia Pollefeys, Marc Van Gool, Luc Tombari, Federico Swiss Fed Inst Technol Zurich Switzerland Google Mountain View CA 94043 USA Tech Univ Munich Munich Germany

ISBN: (纸本)9798350353006

Recovering the 3D scene geometry from a single view is a fundamental yet ill-posed problem in computer vision. While classical depth estimation methods infer only a 2.5D scene representation limited to the image plane, recent approaches based on radiance fields reconstruct a full 3D representation. However, these methods still struggle with occluded regions since inferring geometry without visual observation requires (i) semantic knowledge of the surroundings, and (ii) reasoning about spatial context. We propose KYN, a novel method for single-view scene reconstruction that reasons about semantic and spatial context to predict each point's density. We introduce a vision-language modulation module to enrich point features with fine-grained semantic information. We aggregate point representations across the scene through a language-guided spatial attention mechanism to yield per-point density predictions aware of the 3D semantic context. We show that KYN improves 3D shape recovery compared to predicting density for each 3D point in isolation. We achieve state-of-the-art results in scene and object reconstruction on KITTI-360, and show improved zero-shot generalization compared to prior work. Project page: https://***/kyn.

关键词： radiance field spatial attention spatial context vision-language model

来源：评论

学校读者我要写书评

暂无评论

Transferability Metrics for Selecting Source Model Ensembles

Transferability Metrics for Selecting Source Model Ensembles

引用

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

作者： Agostinelli, Andrea Uijlings, Jasper Mensink, Thomas Ferrari, Vittorio Google Res Mountain View CA 94043 USA

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

We address the problem of ensemble selection in transfer learning: Given a large pool of source models we want to select an ensemble of models which, after fine-tuning on the target training set, yields the best performance on the target test set. Since fine-tuning all possible ensembles is computationally prohibitive, we aim at predicting performance on the target dataset using a computationally efficient transferability metric. We propose several new transferability metrics designed for this task and evaluate them in a challenging and realistic transfer learning setup for semantic segmentation: we create a large and diverse pool of source models by considering 17 source datasets covering a wide variety of image domain, two different architectures, and two pre-training schemes. Given this pool, we then automatically select a subset to form an ensemble performing well on a given target dataset. We compare the ensemble selected by our method to two baselines which select a single source model, either (1) from the same pool as our method;or (2) from a pool containing large source models, each with similar capacity as an ensemble. Averaged over 17 target datasets, we outperform these baselines by 6.0% and 2.5% relative mean IoU, respectively.

关键词： Measurement Training Image segmentation Computational modeling Transfer learning Semantics computer architecture

来源：评论

学校读者我要写书评

暂无评论

Autoregressive Stylized Motion Synthesis with Generative Flow

Autoregressive Stylized Motion Synthesis with Generative Flo...

引用

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

作者： Wen, Yu-Hui Yang, Zhipeng Fu, Hongbo Gao, Lin Sun, Yanan Liu, Yong-Jin Tsinghua Univ BNRist CS Dept Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China City Univ Hong Kong Sch Creat Media Hong Kong Peoples R China Chinese Acad Sci Beijing Key Lab Mobile Comp & Pervas Device ICT Beijing Peoples R China

ISBN: (纸本)9781665445092

Motion style transfer is an important problem in many computer graphics and computer vision applications, including human animation, games, and robotics. Most existing deep learning methods for this problem are supervised and trained by registered motion pairs. In addition, these methods are often limited to yielding a deterministic output, given a pair of style and content motions. In this paper, we propose an unsupervised approach for motion style transfer by synthesizing stylized motions autoregressively using a generative flow model M. M is trained to maximize the exact likelihood of a collection of unlabeled motions, based on an autoregressive context of poses in previous frames and a control signal representing the movement of a root joint. Thanks to invertible flow transformations, latent codes that encode deep properties of motion styles are efficiently inferred by M. By combining the latent codes (from an input style motion S) with the autoregressive context and control signal (from an input content motion C), M outputs a stylized motion which transfers style from S to C. Moreover, our model is probabilistic and is able to generate various plausible motions with a specific style. We evaluate the proposed model on motion capture datasets containing different human motion styles. Experiment results show that our model outperforms the state-of-the-art methods, despite not requiring manually labeled training data.

关键词： Training Deep learning computer vision Codes Training data Games Probabilistic logic

来源：评论

学校读者我要写书评

暂无评论

Space-sweep approach to true multi-image matching

Space-sweep approach to true multi-image matching

引用

Proceedings of the 1996 ieee computer society conference on computer vision and pattern recognition

作者： Collins, Robert T. Univ of Massachusetts Amherst United States

The problem of determining feature correspondences across multiple views is considered. The term 'true multi-image' matching is introduced to describe techniques that make full and efficient use of the geometric relationships between multiple images and the scene. A true multi-image technique must generalize to any number of images, be of linear algorithmic complexity in the number of images, and use all the images in an equal manner. A new space-sweep approach to true multi-image matching is presented that simultaneously determines 2D feature correspondences and the 3D positions of feature points in the scene. The method is illustrated on a seven-image matching example from the aerial image domain.

关键词： Stereo vision

来源：评论

学校读者我要写书评

暂无评论

Learning Placeholders for Open-Set recognition

Learning Placeholders for Open-Set Recognition

引用

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

作者： Zhou, Da-Wei Ye, Han-Jia Zhan, De-Chuan Nanjing Univ State Key Lab Novel Software Technol Nanjing Peoples R China

ISBN: (纸本)9781665445092

Traditional classifiers are deployed under closed-set setting, with both training and test classes belong to the same set. However, real-world applications probably face the input of unknown categories, and the model will recognize them as known ones. Under such circumstances, open-set recognition is proposed to maintain classification performance on known classes and reject unknowns. The closed-set models make overconfident predictions over familiar known class instances, so that calibration and thresholding across categories become essential issues when extending to an open-set environment. To this end, we proposed to learn PlaceholdeRs for Open-SEt recognition (PRosER), which prepares for the unknown classes by allocating placeholders for both data and classifier. In detail, learning data placeholders tries to anticipate open-set class data, thus transforms closed-set training into open-set training. Besides, to learn the invariant information between target and non-target classes, we reserve classifier placeholders as the class-specific boundary between known and unknown. The proposed PROS ER efficiently generates novel class by manifold mixup, and adaptively sets the value of reserved open-set classifier during training. Experiments on various datasets validate the effectiveness of our proposed method.

关键词： Training Manifolds computer vision Face recognition MIMICs Transforms Predictive models

来源：评论

学校读者我要写书评

暂无评论

Style-based Point Generator with Adversarial Rendering for Point Cloud Completion

Style-based Point Generator with Adversarial Rendering for P...

引用

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

作者： Xie, Chulin Wang, Chuxin Zhang, Bo Yang, Hao Chen, Dong Wen, Fang Univ Illinois Champaign IL 61820 USA Univ Sci & Technol China Hefei Anhui Peoples R China Microsoft Res Asia Beijing Peoples R China

ISBN: (纸本)9781665445092

In this paper, we proposed a novel Style-based Point Generator with Adversarial Rendering (SpareNet) for point cloud completion. Firstly, we present the channel-attentive EdgeConv to fully exploit the local structures as well as the global shape in point features. Secondly, we observe that the concatenation manner used by vanilla foldings limits its potential of generating a complex and faithful shape. Enlightened by the success of StyleGAN, we regard the shape feature as style code that modulates the normalization layers during the folding, which considerably enhances its capability. Thirdly, we realize that existing point supervisions, e.g., Chamfer Distance or Earth Mover's Distance, cannot faithfully reflect the perceptual quality of the reconstructed points. To address this, we propose to project the completed points to depth maps with a differentiable renderer and apply adversarial training to advocate the perceptual realism under different viewpoints. Comprehensive experiments on ShapeNet and KITTI prove the effectiveness of our Method, which achieves state-of the-art quantitative performance while offering superior visual quality.

关键词： Training Earth Visualization Shape Image edge detection Rendering (computer graphics) Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Masked-attention Mask Transformer for Universal Image Segmentation

Masked-attention Mask Transformer for Universal Image Segmen...

引用

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

作者： Cheng, Bowen Misra, Ishan Schwing, Alexander G. Kirillov, Alexander Girdhar, Rohit Facebook AI Res FAIR Menlo Pk CA 94025 USA Univ Illinois Urbana Champaign UIUC Champaign IL 61820 USA

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Image segmentation groups pixels with different semantics, e.g., category or instance membership. Each choice of semantics defines a task. While only the semantics of each task differ, current research focuses on designing specialized architectures for each task. We present Masked-attention Mask Transformer (Mask2Former), a new architecture capable of addressing any image segmentation task (panoptic, instance or semantic). Its key components include masked attention, which extracts localized features by constraining cross-attention within predicted mask regions. In addition to reducing the research effort by at least three times, it outperforms the best specialized architectures by a significant margin on four popular datasets. Most notably, Mask2Former sets a new state-of-the-art for panoptic segmentation (57.8 PQ on COCO), instance segmentation (50.1 AP on COCO) and semantic segmentation (57.7 mIoU on ADE20K).

关键词： Image segmentation Shape Computational modeling Semantics computer architecture Transformers Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Actor and Observer: Joint Modeling of First and Third-Person Videos 31

Actor and Observer: Joint Modeling of First and Third-Person...

引用

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

作者： Sigurdsson, Gunnar A. Gupta, Abhinav Schmid, Cordelia Farhadi, Ali Alahari, Karteek Carnegie Mellon Univ Pittsburgh PA 15213 USA Univ Grenoble Alpes INRIA CNRS Grenoble INPLJK F-38000 Grenoble France Allen Inst Artificial Intelligence Seattle WA USA INRIA Grenoble France

ISBN: (纸本)9781538664209

Several theories in cognitive neuroscience suggest that when people interact with the world, or simulate interactions, they do so from a first-person egocentric perspective, and seamlessly transfer knowledge between third-person (observer) and first-person (actor). Despite this, learning such models for human action recognition has not been achievable due to the lack of data. This paper takes a step in this direction, with the introduction of Charades-Ego, a large-scale dataset of paired first-person and third-person videos, involving 112 people, with 4000 paired videos. This enables learning the link between the two, actor and observer perspectives. Thereby, we address one of the biggest bottlenecks facing egocentric vision research, providing a link from first-person to the abundant third-person data on the web. We use this data to learn a joint representation of first and third-person videos, with only weak supervision, and show its effectiveness for transferring knowledge from the third-person to the first-person domain.

关键词： Videos Cameras Portable computers Data models Task analysis Computational modeling computer vision

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 << < 471 472 473 474 475 476 477 478 479 480 > >>

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：