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

50,479 篇 会议
1,421 册 图书
1,041 篇 期刊文献
1 篇 学位论文

馆藏范围

52,940 篇 电子文献
4 种 纸本馆藏

日期分布

学科分类号

31,811 篇 工学
- 24,804 篇 计算机科学与技术...
- 12,568 篇 软件工程
- 5,153 篇 光学工程
- 4,756 篇 电气工程
- 4,436 篇 信息与通信工程
- 4,257 篇 机械工程
- 3,956 篇 控制科学与工程
- 2,474 篇 生物工程
- 1,728 篇 生物医学工程（可授...
- 1,584 篇 仪器科学与技术
- 1,317 篇 电子科学与技术（可...
- 793 篇 化学工程与技术
- 698 篇 安全科学与工程
- 542 篇 交通运输工程
- 379 篇 建筑学
- 331 篇 土木工程
11,839 篇 理学
- 6,434 篇 物理学
- 5,405 篇 数学
- 2,761 篇 生物学
- 1,910 篇 统计学（可授理学、...
- 801 篇 化学
- 669 篇 系统科学
5,305 篇 医学
- 5,094 篇 临床医学
- 729 篇 基础医学(可授医学...
- 459 篇 药学(可授医学、理...
3,350 篇 管理学
- 1,953 篇 图书情报与档案管...
- 1,535 篇 管理科学与工程(可...
- 479 篇 工商管理
720 篇 艺术学
- 718 篇 设计学（可授艺术学...
428 篇 法学
- 401 篇 社会学
297 篇 农学
197 篇 教育学
163 篇 经济学
63 篇 文学
49 篇 军事学

主题

17,385 篇 computer vision
9,017 篇 pattern recognit...
4,196 篇 training
3,815 篇 feature extracti...
3,134 篇 cameras
2,870 篇 computational mo...
2,789 篇 image segmentati...
2,622 篇 visualization
2,573 篇 shape
2,533 篇 face recognition
2,171 篇 robustness
2,123 篇 computer science
1,973 篇 object detection
1,959 篇 computer archite...
1,878 篇 layout
1,853 篇 object recogniti...
1,802 篇 three-dimensiona...
1,725 篇 neural networks
1,708 篇 humans
1,691 篇 image recognitio...

机构

165 篇 univ chinese aca...
144 篇 tsinghua univers...
136 篇 national laborat...
108 篇 univ sci & techn...
104 篇 zhejiang univers...
100 篇 shanghai jiao to...
95 篇 microsoft resear...
94 篇 university of sc...
86 篇 zhejiang univ pe...
84 篇 shanghai ai lab ...
74 篇 school of comput...
69 篇 computer vision ...
68 篇 peking univ peop...
68 篇 chinese acad sci...
65 篇 chinese univ hon...
63 篇 institute of inf...
62 篇 google res mount...
61 篇 univ oxford oxfo...
59 篇 univ toronto on
57 篇 swiss fed inst t...

作者

91 篇 van gool luc
87 篇 umapada pal
76 篇 zhang lei
64 篇 lee seong-whan
49 篇 vittorio murino
42 篇 yang yi
34 篇 nassir navab
33 篇 li xin
33 篇 jie yang
32 篇 liu yang
31 篇 escalera sergio
31 篇 loy chen change
30 篇 ling haibin
30 篇 h. bischof
29 篇 zhou jie
29 篇 vasconcelos nuno
29 篇 jan-michael frah...
29 篇 hanqing lu
28 篇 blumenstein mich...
27 篇 jia yunde

语言

51,871 篇 英文
835 篇 其他
241 篇 中文
22 篇 土耳其文
5 篇 西班牙文
2 篇 日文
2 篇 葡萄牙文
2 篇 俄文

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

共 52943 条记录，以下是4961-4970 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：

DER: Dynamically Expandable Representation for Class Incremental Learning

DER: Dynamically Expandable Representation for Class Increme...

引用

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

作者： Yan, Shipeng Xie, Jiangwei He, Xuming ShanghaiTech Univ Sch Informat Sci & Technol Shanghai Peoples R China Shanghai Engn Res Ctr Intelligent Vis & Imaging Shanghai Peoples R China Chinese Acad Sci Shanghai Inst Microsyst & Informat Technol Shanghai Peoples R China Univ Chinese Acad Sci Beijing Peoples R China

ISBN: (纸本)9781665445092

We address the problem of class incremental learning, which is a core step towards achieving adaptive vision intelligence. In particular, we consider the task setting of incremental learning with limited memory and aim to achieve better stability-plasticity trade-off. To this end, we propose a novel two-stage learning approach that utilizes a dynamically expandable representation for more effective incremental concept modeling. Specifically, at each incremental step, we freeze the previously learned representation and augment it with additional feature dimensions from a new learnable feature extractor. This enables us to integrate new visual concepts with retaining learned knowledge. We dynamically expand the representation according to the complexity of novel concepts by introducing a channel-level mask-based pruning strategy. Moreover, we introduce an auxiliary loss to encourage the model to learn diverse and discriminate features for novel concepts. We conduct extensive experiments on the three class incremental learning benchmarks and our method consistently outperforms other methods with a large margin.(1)

关键词： Visualization computer vision Adaptation models Benchmark testing Feature extraction pattern recognition Complexity theory

来源：评论

学校读者我要写书评

暂无评论

OmniLayout: Room Layout Reconstruction from Indoor Spherical Panoramas

OmniLayout: Room Layout Reconstruction from Indoor Spherical...

引用

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

作者： Rao, Shivansh Kumar, Vikas Kifer, Daniel Giles, C. Lee Mali, Ankur Penn State Univ University Pk PA 16802 USA

ISBN: (纸本)9781665448994

Given a single RGB panorama, the goal of 3D layout reconstruction is to estimate the room layout by predicting the corners, floor boundary, and ceiling boundary. A common approach has been to use standard convolutional networks to predict the corners and boundaries, followed by post-processing to generate the 3D layout. However, the space-varying distortions in panoramic images are not compatible with the translational equivariance property of standard convolutions, thus degrading performance. Instead, we propose to use spherical convolutions. The resulting network, which we call OmniLayout performs convolutions directly on the sphere surface, sampling according to inverse equirectangular projection and hence invariant to equirectangular distortions. Using a new evaluation metric, we show that our network reduces the error in the heavily distorted regions (near the poles) by approximate to 25% when compared to standard convolutional networks. Experimental results show that OmniLayout outperforms the state-of-the-art by approximate to 4% on two different benchmark datasets (PanoContext and Stanford 2D-3D). Code is available at https://***/rshivansh/OmniLayout.

关键词： Convolutional codes Three-dimensional displays Layout Benchmark testing Distortion Predistortion pattern recognition

来源：评论

学校读者我要写书评

暂无评论

IMODAL: creating learnable user-defined deformation models

IMODAL: creating learnable user-defined deformation models

引用

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

作者： Lacroix, Leander Charlier, Benjamin Trouve, Alain Gris, Barbara Univ Paris Saclay INSERM U1299 Gif Sur Yvette France Univ Montpellier IMAG Montpellier France ENS Paris Saclay Ctr Borelli Cachan France Sorbonne Univ CNRS LJLL Paris France

ISBN: (纸本)9781665445092

A natural way to model the evolution of an object (growth of a leaf for instance) is to estimate a plausible deforming path between two observations. This interpolation process can generate deceiving results when the set of considered deformations is not relevant to the observed data. To overcome this issue, the framework of deformation modules allows to incorporate in the model structured deformation patterns coming from prior knowledge on the data. The goal of this article is twofold. First defining new deformation modules incorporating structures coming from the elastic properties of the objects. Second, presenting the IMODAL library allowing to perform registration through structured deformations. This library is modular: adapted priors can be easily defined by the user, several priors can be combined into a global one and various types of data can be considered such as curves, meshes or images. It can be downloaded at https://***/imodal.

关键词： Deformable models Adaptation models Interpolation computer vision Computational modeling Libraries Data models

来源：评论

学校读者我要写书评

暂无评论

Layer Importance Estimation with Imprinting for Neural Network Quantization

Layer Importance Estimation with Imprinting for Neural Netwo...

引用

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

作者： Liu, Hongyang Elkerdawy, Sara Ray, Nilanjan Elhoushi, Mostafa Univ Alberta Edmonton AB Canada Huawei Shenzhen Peoples R China

ISBN: (纸本)9781665448994

Neural network quantization has achieved a high compression rate using fixed low bit-width representation of weights and activations while maintaining the accuracy of the high-precision original network. However, mixed precision (per-layer bit-width precision) quantization requires careful tuning to maintain accuracy while achieving further compression and higher granularity than fixed-precision quantization. We propose an accuracy-aware criterion to quantify the layer's importance rank. Our method applies imprinting per layer which acts as a proxy module for accuracy estimation in an efficient way. We rank the layers based on the accuracy gain from previous modules and iteratively quantize first those with less accuracy gain. Previous mixed-precision methods either rely on expensive search techniques such as reinforcement learning (RL) or end-to-end optimization with a lack of interpretation to the quantization configuration scheme. Our method is a one-shot, efficient, accuracy-aware information estimation and thus draws better interpretability to the selected bit-width configuration.

关键词： Training Quantization (signal) Search methods Neural networks Estimation Reinforcement learning pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Reinforced Attention for Few-Shot Learning and Beyond

Reinforced Attention for Few-Shot Learning and Beyond

引用

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

作者： Hong, Jie Fang, Pengfei Li, Weihao Zhang, Tong Simon, Christian Harandi, Mehrtash Petersson, Lars Australian Natl Univ Canberra ACT Australia Data61 CSIRO Canberra ACT Australia Ecole Polytech Fed Lausanne Lausanne Switzerland Monash Univ Clayton Vic Australia

ISBN: (纸本)9781665445092

Few-shot learning aims to correctly recognize query samples from unseen classes given a limited number of support samples, often by relying on global embeddings of images. In this paper, we propose to equip the backbone network with an attention agent, which is trained by reinforcement learning. The policy gradient algorithm is employed to train the agent towards adaptively localizing the representative regions on feature maps over time. We further design a reward function based on the prediction of the held-out data, thus helping the attention mechanism to generalize better across the unseen classes. The extensive experiments show, with the help of the reinforced attention, that our embedding network has the capability to progressively generate a more discriminative representation in few-shot learning. Moreover, experiments on the task of image classification also show the effectiveness of the proposed design.

关键词： computer vision Image recognition Computational modeling Reinforcement learning Prediction algorithms Data models pattern recognition

来源：评论

学校读者我要写书评

暂无评论

BalaGAN: Cross-Modal Image Translation Between Imbalanced Domains

BalaGAN: Cross-Modal Image Translation Between Imbalanced Do...

引用

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

作者： Patashnik, Or Danon, Dov Zhang, Hao Cohen-Or, Daniel Tel Aviv Univ Tel Aviv Israel Simon Fraser Univ Burnaby BC Canada

ISBN: (纸本)9781665448994

State-of-the-art image translation methods tend to struggle in an imbalanced domain setting, where one image domain lacks richness and diversity. We introduce a new unsupervised translation network, BalaGAN, specifically designed to tackle the domain imbalance problem. We leverage the latent modalities of the richer domain to turn the image-to-image translation problem, between two imbalanced domains, into a multi-class translation problem, more resembling the style transfer setting. Specifically, we analyze the source domain and learn a decomposition of it into a set of latent modes or classes, without any supervision. This leaves us with a multitude of balanced crossdomain translation tasks, between all pairs of classes, including the target domain. During inference, the trained network takes as input a source image, as well as a reference style image from one of the modes as a condition, and produces an image which resembles the source on the pixel-wise level, but shares the same mode as the reference. We show that employing modalities within the dataset improves the quality of the translated images, and that BalaGAN outperforms strong baselines of both unconditioned and style-transfer-based image-to-image translation methods, in terms of image quality and diversity.

关键词： Training Image quality computer vision conferences pattern recognition Task analysis

来源：评论

学校读者我要写书评

暂无评论

A General Framework for Jersey Number recognition in Sports Video

A General Framework for Jersey Number Recognition in Sports ...

引用

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

作者： Maria Koshkina James H. Elder York University Toronto Canada

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Jersey number recognition is an important task in sports video analysis, partly due to its importance for long-term player tracking. It can be viewed as a variant of scene text recognition. However, there is a lack of published attempts to apply scene text recognition models on jersey number data. Here we introduce a novel public jersey number recognition dataset for hockey and study how scene text recognition methods can be adapted to this problem. We address issues of occlusions and assess the degree to which training on one sport (hockey) can be generalized to another (soccer). For the latter, we also consider how jersey number recognition at the single-image level can be aggregated across frames to yield tracklet-level jersey number labels. We demonstrate high performance on image- and tracklet-level tasks, achieving 91.4% accuracy for hockey images and 87.4% for soccer tracklets. Code, models, and data are available at https://***/mkoshkina/jerseynumber-pipeline.

关键词： Training computer vision Adaptation models Codes Accuracy Text recognition conferences

来源：评论

学校读者我要写书评

暂无评论

Automatic Correction of Internal Units in Generative Neural Networks

Automatic Correction of Internal Units in Generative Neural ...

引用

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

作者： Tousi, Ali Jeong, Haedong Han, Jiyeon Choi, Hwanil Choi, Jaesik Korea Adv Inst Sci & Technol KAIST Daejeon South Korea Ulsan Natl Inst Sci & Technol UNIST Ulsan South Korea INEEJI Seoul South Korea

ISBN: (纸本)9781665445092

Generative Adversarial Networks (GANs) have shown satisfactory performance in synthetic image generation by devising complex network structure and adversarial training scheme. Even though GANs are able to synthesize realistic images, there exists a number of generated images with defective visual patterns which are known as artifacts. While most of the recent work tries to fix artifact generations by perturbing latent code, few investigate internal units of a generator to fix them. In this work, we devise a method that automatically identifies the internal units generating various types of artifact images. We further propose the sequential correction algorithm which adjusts the generation flow by modifying the detected artifact units to improve the quality of generation while preserving the original outline. Our method outperforms the baseline method in terms of FID-score and shows satisfactory results with human evaluation.

关键词： Training Visualization computer vision Codes Image synthesis Neural networks Complex networks

来源：评论

学校读者我要写书评

暂无评论

Partial Person Re-identification with Part-Part Correspondence Learning

Partial Person Re-identification with Part-Part Corresponden...

引用

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

作者： He, Tianyu Shen, Xu Huang, Jianqiang Chen, Zhibo Hua, Xian-Sheng Alibaba Grp DAMO Acad Hangzhou Peoples R China Univ Sci & Technol China Hefei Peoples R China

ISBN: (纸本)9781665445092

Driven by the success of deep learning, the last decade has seen rapid advances in person re-identification (re-ID). Nonetheless, most of approaches assume that the input is given with the fulfillment of expectations, while imperfect input remains rarely explored to date, which is a non-trivial problem since directly apply existing methods without adjustment can cause significant performance degradation. In this paper, we focus on recognizing partial (flawed) input with the assistance of proposed Part-Part Correspondence Learning (PPCL), a self-supervised learning framework that learns correspondence between image patches without any additional part-level supervision. Accordingly, we propose Part-Part Cycle (PP-Cycle) constraint and Part-Part Triplet (PP-Triplet) constraint that exploit the duality and uniqueness between corresponding image patches respectively. We verify our proposed PPCL on several partial person re-ID benchmarks. Experimental results demonstrate that our approach can surpass previous methods in terms of the standard evaluation metric.

关键词： Measurement Degradation Deep learning computer vision Image recognition Benchmark testing pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Domain Adaptation for Video Transformers in Action recognition 26

Unsupervised Domain Adaptation for Video Transformers in Act...

引用

26th International conference on pattern recognition / 8th International Workshop on Image Mining - Theory and Applications (IMTA)

作者： da Costa, Victor G. Turrisi Zara, Giacomo Rota, Paolo Oliveira-Santos, Thiago Sebe, Nicu Murino, Vittorio Ricci, Elisa Univ Trento Trento Italy Univ Fed Espirito Santo Vitoria ES Brazil Univ Verona Verona Italy Ist Italiano Tecnol Pattern Anal & Comp Vis PAVIS Genoa Italy Fdn Bruno Kessler Povo Italy

ISBN: (数字)9781665490627

ISBN: (纸本)9781665490627

Over the last few years, Unsupervised Domain Adaptation (UDA) techniques have acquired remarkable importance and popularity in computer vision. However, when compared to the extensive literature available for images, the field of videos is still relatively unexplored. On the other hand, the performance of a model in action recognition is heavily affected by domain shift. In this paper, we propose a simple and novel UDA approach for video action recognition. Our approach leverages recent advances on spatio-temporal transformers to build a robust source model that better generalises to the target domain. Furthermore, our architecture learns domain invariant features thanks to the introduction of a novel alignment loss term derived from the Information Bottleneck principle. We report results on two video action recognition benchmarks for UDA, showing state-of-the-art performance on HMDB <-> UCF, as well as on Kinetics -> NEC-Drone, which is more challenging. This demonstrates the effectiveness of our method in handling different levels of domain shift. The source code is available at https://***/vturrisi/UDAVT.

关键词： Adaptation models Visualization computer vision Source coding computer architecture Benchmark testing Transformers

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：