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

22,772 篇 会议
112 篇 期刊文献
23 册 图书

馆藏范围

22,906 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

13,399 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
- 1,011 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

10,127 篇 computer vision
4,025 篇 pattern recognit...
2,900 篇 training
1,958 篇 computational mo...
1,793 篇 cameras
1,759 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

22,845 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 22907 条记录，以下是4501-4510 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：

Mean-Shift Feature Transformer

Mean-Shift Feature Transformer

引用

conference on computer vision and pattern recognition (CVPR)

作者： Takumi Kobayashi National Institute of Advanced Industrial Science and Technology Japan University of Tsukuba Japan

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Transformer models developed in NLP make a great impact on computer vision fields, producing promising performance on various tasks. While multi-head attention, a characteristic mechanism of the transformer, attracts keen research interest such as for reducing computation cost, we analyze the transformer model from a viewpoint of feature transformation based on a distribution of input feature to-kens. The analysis inspires us to derive a novel transformation method from mean-shift update which is an effective gradient ascent to seek a local mode of distinctive repre-sentation on the token distribution. We also present an efficient projection approach to reduce parameter size of linear projections constituting the proposed multi-head feature transformation. In the experiments on ImageNet-lK dataset, the proposed methods embedded into various network models exhibit favorable performance improvement in place of the transformer module. Codes are available at https://***/tk1980/MSFtransformer.

关键词： computer vision Analytical models Costs Codes Computational modeling Transformers pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Spatially Consistent Representation Learning

Spatially Consistent Representation Learning

引用

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

作者： Roh, Byungseok Shin, Wuhyun Kim, Ildoo Kim, Sungwoong Kakao Brain Seoul South Korea

ISBN: (纸本)9781665445092

Self-supervised learning has been widely used to obtain transferrable representations from unlabeled images. Especially, recent contrastive learning methods have shown impressive performances on downstream image classification tasks. While these contrastive methods mainly focus on generating invariant global representations at the image-level under semantic-preserving transformations, they are prone to overlook spatial consistency of local representations and therefore have a limitation in pretraining for localization tasks such as object detection and instance segmentation. Moreover, aggressively cropped views used in existing contrastive methods can minimize representation distances between the semantically different regions of a single image. In this paper, we propose a spatially consistent representation learning algorithm (SCRL) for multi-object and location-specific tasks. In particular, we devise a novel self-supervised objective that tries to produce coherent spatial representations of a randomly cropped local region according to geometric translations and zooming operations. On various downstream localization tasks with benchmark datasets, the proposed SCRL shows significant performance improvements over the image-level supervised pretraining as well as the state-of-the-art self-supervised learning methods.

关键词： Location awareness Learning systems Image segmentation computer vision Codes Object detection Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Weakly Supervised Instance Segmentation for Videos with Temporal Mask Consistency

Weakly Supervised Instance Segmentation for Videos with Temp...

引用

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

作者： Liu, Qing Ramanathan, Vignesh Mahajan, Dhruv Yuille, Alan Yang, Zhenheng Johns Hopkins Univ Baltimore MD 21218 USA Facebook Menlo Pk CA USA

ISBN: (纸本)9781665445092

Weakly supervised instance segmentation reduces the cost of annotations required to train models. However, existing approaches which rely only on image-level class labels predominantly suffer from errors due to (a) partial segmentation of objects and (b) missing object predictions. We show that these issues can be better addressed by training with weakly labeled videos instead of images. In videos, motion and temporal consistency of predictions across frames provide complementary signals which can help segmentation. We are the first to explore the use of these video signals to tackle weakly supervised instance segmentation. We propose two ways to leverage this information in our model. First, we adapt inter-pixel relation network (IRN) [1] to effectively incorporate motion information during training. Second, we introduce a new MaskConsist module, which addresses the problem of missing object instances by transferring stable predictions between neighboring frames during training. We demonstrate that both approaches together improve the instance segmentation metric AP(50) on video frames of two datasets: Youtube-VIS and Cityscapes by 5% and 3% respectively.

关键词： Training Measurement Image segmentation computer vision Costs Motion segmentation Computational modeling

来源：评论

学校读者我要写书评

暂无评论

UnsupervisedR&R: Unsupervised Point Cloud Registration via Differentiable Rendering

UnsupervisedR&R: Unsupervised Point Cloud Registration via D...

引用

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

作者： El Banani, Mohamed Gao, Luya Johnson, Justin Univ Michigan Ann Arbor MI 48109 USA

ISBN: (纸本)9781665445092

Aligning partial views of a scene into a single whole is essential to understanding one's environment and is a key component of numerous robotics tasks such as SLAM and SfM. Recent approaches have proposed end-to-end systems that can outperform traditional methods by leveraging pose supervision. However, with the rising prevalence of cameras with depth sensors, we can expect a new stream of raw RGB-D data without the annotations needed for supervision. We propose UnsupervisedR&R: an end-to-end unsupervised approach to learning point cloud registration from raw RGB-D video. The key idea is to leverage differentiable alignment and rendering to enforce photometric and geometric consistency between frames. We evaluate our approach on indoor scene datasets and find that we outperform existing traditional approaches with classical and learned descriptors while being competitive with supervised geometric point cloud registration approaches.

关键词： Training Simultaneous localization and mapping Robot vision systems Feature extraction Rendering (computer graphics) Cameras Sensors

来源：评论

学校读者我要写书评

暂无评论

JRDB-Social: A Multifaceted Robotic Dataset for Understanding of Context and Dynamics of Human Interactions Within Social Groups

JRDB-Social: A Multifaceted Robotic Dataset for Understandin...

引用

conference on computer vision and pattern recognition (CVPR)

作者： Simindokht Jahangard Zhixi Cai Shiki Wen Hamid Rezatofighi Monash University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Understanding human social behaviour is crucial in computer vision and robotics. Micro-level observations like in-dividual actions fall short, necessitating a comprehensive approach that considers individual behaviour, intra-group dynamics, and social group levels for a thorough under-standing. To address dataset limitations, this paper intro-duces JRDB-Social, an extension of JRDB [2]. Designed to fill gaps in human understanding across diverse indoor and outdoor social contexts, JRDB-Social provides annotations at three levels: individual attributes, intra-group in-teractions, and social group context. This dataset aims to enhance our grasp of human social dynamics for robotic applications. Utilizing the recent cutting-edge multi-modal large language models, we evaluated our benchmark to ex-plore their capacity to decipher social human behaviour.

关键词： computer vision Social groups Annotations Large language models Computational modeling Training data pattern recognition

来源：评论

学校读者我要写书评

暂无评论

What If We Only Use Real Datasets for Scene Text recognition? Toward Scene Text recognition With Fewer Labels

What If We Only Use Real Datasets for Scene Text Recognition...

引用

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

作者： Baek, Jeonghun Matsui, Yusuke Aizawa, Kiyoharu Univ Tokyo Tokyo Japan

ISBN: (纸本)9781665445092

Scene text recognition (STR) task has a common practice: All state-of-the-art STR models are trained on large synthetic data. In contrast to this practice, training STR models only on fewer real labels (STR with fewer labels) is important when we have to train STR models without synthetic data: for handwritten or artistic texts that are difficult to generate synthetically and for languages other than English for which we do not always have synthetic data. However, there has been implicit common knowledge that training STR models on real data is nearly impossible because real data is insufficient. We consider that this common knowledge has obstructed the study of STR with fewer labels. In this work, we would like to reactivate STR with fewer labels by disproving the common knowledge. We consolidate recently accumulated public real data and show that we can train STR models satisfactorily only with real labeled data. Subsequently, we find simple data augmentation to fully exploit real data. Furthermore, we improve the models by collecting unlabeled data and introducing semi- and self-supervised methods. As a result, we obtain a competitive model to state-of-the-art methods. To the best of our knowledge, this is the first study that 1) shows sufficient performance by only using real labels and 2) introduces semi- and self-supervised methods into STR with fewer labels.

关键词： Training computer vision Codes Text recognition Data models Task analysis

来源：评论

学校读者我要写书评

暂无评论

PCLs: Geometry-aware Neural Reconstruction of 3D Pose with Perspective Crop Layers

PCLs: Geometry-aware Neural Reconstruction of 3D Pose with P...

引用

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

作者： Yu, Frank Salzmann, Mathieu Fua, Pascal Rhodin, Helge Univ British Columbia Vancouver BC Canada Ecole Polytech Fed Lausanne Lausanne Switzerland

ISBN: (纸本)9781665445092

Local processing is an essential feature of CNNs and other neural network architectures-it is one of the reasons why they work so well on images where relevant information is, to a large extent, local. However, perspective effects stemming from the projection in a conventional camera vary for different global positions in the image. We introduce Perspective Crop Layers (PCLs)-a form of perspective crop of the region of interest based on the camera geometry- and show that accounting for the perspective consistently improves the accuracy of state-of-theart 3D pose reconstruction methods. PCLs are modular neural network layers, which, when inserted into existing CNN and MLP architectures, deterministically remove the location-dependent perspective effects while leaving end-to-end training and the number of parameters of the underlying neural network unchanged. We demonstrate that PCL leads to improved 3D human pose reconstruction accuracy for CNN architectures that use cropping operations, such as spatial transformer networks (STN), and, somewhat surprisingly, MLPs used for 2D-to-3D keypoint lifting. Our conclusion is that it is important to utilize camera calibration information when available, for classical and deep-learning-based computer vision alike. PCL offers an easy way to improve the accuracy of existing 3D reconstruction networks by making them geometry-aware.

关键词： Training computer vision Three-dimensional displays Neural networks Crops computer architecture Cameras

来源：评论

学校读者我要写书评

暂无评论

DriveGAN: Towards a Controllable High-Quality Neural Simulation

DriveGAN: Towards a Controllable High-Quality Neural Simulat...

引用

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

作者： Kim, Seung Wook Philion, Jonah Torralba, Antonio Fidler, Sanja NVIDIA Santa Clara CA 95051 USA Univ Toronto Toronto ON Canada Vector Inst Toronto ON Canada MIT Cambridge MA 02139 USA

ISBN: (纸本)9781665445092

Realistic simulators are critical for training and verifying robotics systems. While most of the contemporary simulators are hand-crafted, a scaleable way to build simulators is to use machine learning to learn how the environment behaves in response to an action, directly from data. In this work, we aim to learn to simulate a dynamic environment directly in pixel-space, by watching unannotated sequences offrames and their associated actions. We introduce a novel high-quality neural simulator referred to as DriveGAN that achieves controllability by disentangling different components without supervision. In addition to steering controls, it also includes controls for sampling features of a scene, such as the weather as well as the location of non player objects. Since DriveGAN is a filly differentiable simulator, it further allows for re-simulation of a given video sequence, offering an agent to drive through a recorded scene again, possibly taking different actions. We train DriveGAN on multiple datasets, including 160 hours of real-world driving data. We showcase that our approach greatly surpasses the performance of previous data-driven simulators, and allows for new key features not explored before.

关键词： Training computer vision Computational modeling Video sequences Machine learning Generative adversarial networks Controllability

来源：评论

学校读者我要写书评

暂无评论

Prototype-Guided Saliency Feature Learning for Person Search

Prototype-Guided Saliency Feature Learning for Person Search

引用

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

作者： Kim, Hanjae Joung, Sunghun Kim, Ig-Jae Sohn, Kwanghoon Yonsei Univ Seoul South Korea Korea Inst Sci & Technol KIST Seoul South Korea

ISBN: (纸本)9781665445092

Existing person search methods integrate person detection and re-identification (re-ID) module into a unified system. Though promising results have been achieved, the misalignment problem, which commonly occurs in person search, limits the discriminative feature representation for re-ID. To overcome this limitation, we introduce a novel framework to learn the discriminative representation by utilizing prototype in OIM loss. Unlike conventional methods using prototype as a representation of person identity, we utilize it as guidance to allow the attention network to consistently highlight multiple instances across different poses. Moreover, we propose a new prototype update scheme with adaptive momentum to increase the discriminative ability across different instances. Extensive ablation experiments demonstrate that our method can significantly enhance the feature discriminative power, outperforming the state-of-the-art results on two person search benchmarks including CUHK-SYSU and PRW.

关键词： computer vision Adaptation models Annotations Computational modeling Prototypes Benchmark testing Search problems

来源：评论

学校读者我要写书评

暂无评论

Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text recognition

Read Like Humans: Autonomous, Bidirectional and Iterative La...

引用

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

作者： Fang, Shancheng Xie, Hongtao Wang, Yuxin Mao, Zhendong Zhang, Yongdong Univ Sci & Technol China Hefei Anhui Peoples R China

ISBN: (纸本)9781665445092

Linguistic knowledge is of great benefit to scene text recognition. However, how to effectively model linguistic rules in end-to-end deep networks remains a research challenge. In this paper, we argue that the limited capacity of language models comes from: 1) implicitly language modeling;2) unidirectional feature representation;and 3) language model with noise input. Correspondingly, we propose an autonomous, bidirectional and iterative ABINet for scene text recognition. Firstly, the autonomous suggests to block gradient flow between vision and language models to enforce explicitly language modeling. Secondly, a novel bidirectional doze network (BCN) as the language model is proposed based on bidirectional feature representation. Thirdly, we propose an execution manner of iterative correction for language model which can effectively alleviate the impact of noise input. Additionally, based on the ensemble of iterative predictions, we propose a self-training method which can learn from unlabeled images effectively. Extensive experiments indicate that ABINet has superiority on low-quality images and achieves state-of-the-art results on several mainstream benchmarks. Besides, the ABINet trained with ensemble self-training shows promising improvement in realizing human-level recognition.

关键词： computer vision Codes Text recognition Linguistics Benchmark testing Semisupervised learning Predictive models

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 << < 447 448 449 450 451 452 453 454 455 456 > >>

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：