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

11,416 篇 会议
9 篇 期刊文献

馆藏范围

11,425 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

7,983 篇 工学
- 7,536 篇 计算机科学与技术...
- 805 篇 机械工程
- 401 篇 电气工程
- 393 篇 软件工程
- 233 篇 控制科学与工程
- 59 篇 光学工程
- 42 篇 生物工程
- 37 篇 信息与通信工程
- 19 篇 生物医学工程（可授...
- 14 篇 电子科学与技术（可...
- 13 篇 化学工程与技术
- 9 篇 安全科学与工程
- 8 篇 交通运输工程
- 6 篇 仪器科学与技术
- 5 篇 土木工程
- 3 篇 建筑学
3,139 篇 医学
- 3,139 篇 临床医学
- 8 篇 基础医学(可授医学...
- 5 篇 药学(可授医学、理...
- 4 篇 公共卫生与预防医...
310 篇 理学
- 200 篇 系统科学
- 66 篇 物理学
- 43 篇 生物学
- 32 篇 数学
- 16 篇 化学
- 15 篇 统计学（可授理学、...
29 篇 管理学
- 17 篇 图书情报与档案管...
- 13 篇 管理科学与工程(可...
- 5 篇 工商管理
3 篇 法学
- 3 篇 社会学
2 篇 教育学
2 篇 农学
1 篇 经济学
1 篇 艺术学

主题

5,612 篇 computer vision
2,584 篇 training
2,092 篇 pattern recognit...
1,682 篇 computational mo...
1,496 篇 visualization
1,343 篇 three-dimensiona...
1,098 篇 semantics
1,007 篇 benchmark testin...
1,005 篇 codes
927 篇 computer archite...
898 篇 deep learning
790 篇 task analysis
708 篇 feature extracti...
571 篇 conferences
563 篇 face recognition
520 篇 transformers
517 篇 neural networks
493 篇 object detection
476 篇 image segmentati...
452 篇 cameras

机构

172 篇 univ sci & techn...
150 篇 univ chinese aca...
148 篇 tsinghua univ pe...
145 篇 carnegie mellon ...
136 篇 chinese univ hon...
116 篇 peng cheng lab p...
106 篇 zhejiang univ pe...
97 篇 swiss fed inst t...
96 篇 sensetime res pe...
95 篇 tsinghua univers...
91 篇 shanghai ai lab ...
85 篇 shanghai jiao to...
83 篇 alibaba grp peop...
81 篇 peng cheng labor...
80 篇 zhejiang univers...
80 篇 stanford univ st...
78 篇 univ hong kong p...
77 篇 university of ch...
75 篇 australian natl ...
75 篇 tech univ munich...

作者

64 篇 timofte radu
60 篇 van gool luc
50 篇 zhang lei
44 篇 yang yi
39 篇 tao dacheng
35 篇 loy chen change
32 篇 tian qi
31 篇 zhou jie
31 篇 sun jian
30 篇 liu yang
29 篇 vasconcelos nuno
29 篇 qi tian
29 篇 zha zheng-jun
28 篇 chen chen
27 篇 boxin shi
26 篇 li xin
26 篇 luc van gool
26 篇 pollefeys marc
25 篇 liu xiaoming
25 篇 ying shan

语言

11,420 篇 英文
5 篇 其他

检索条件"任意字段=2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021"

共 11425 条记录，以下是241-250 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：

Virtual Fully-Connected Layer: Training a Large-Scale Face recognition Dataset with Limited Computational Resources

Virtual Fully-Connected Layer: Training a Large-Scale Face R...

引用

ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Li, Pengyu Wang, Biao Zhang, Lei Alibaba Grp Artificial Intelligence Ctr DAMO Acad Hangzhou Peoples R China Hong Kong Polytech Univ Dept Comp Hong Kong Peoples R China

ISBN: (纸本)9781665445092

Recently, deep face recognition has achieved significant progress because of Convolutional Neural Networks (CNNs) and large-scale datasets. However, training CNNs on a large-scale face recognition dataset with limited computational resources is still a challenge. This is because the classification paradigm needs to train a fully-connected layer as the category classifier, and its parameters will be in the hundreds of millions if the training dataset contains millions of identities. This requires many computational resources, such as GPU memory. The metric learning paradigm is an economical computation method, but its performance is greatly inferior to that of the classification paradigm. To address this challenge, we propose a simple but effective CNN layer called the Virtual fully-connected (Virtual FC) layer to reduce the computational consumption of the classification paradigm. Without bells and whistles, the proposed Virtual FC reduces the parameters by more than 100 times with respect to the fully-connected layer and achieves competitive performance on mainstream face recognition evaluation datasets. Moreover, the performance of our Virtual FC layer on the evaluation datasets is superior to that of the metric learning paradigm by a significant margin. Our code will be released in hopes of disseminating our idea to other domains1.

关键词： Training Measurement computer vision Codes Face recognition Memory management Graphics processing units

来源：评论

学校读者我要写书评

暂无评论

Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations

Continual Semantic Segmentation via Repulsion-Attraction of ...

引用

ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Michieli, Umberto Zanuttigh, Pietro Univ Padua Dept Informat Engn Padua Italy

ISBN: (纸本)9781665445092

Deep neural networks suffer from the major limitation of catastrophic forgetting old tasks when learning new ones. In this paper we focus on class incremental continual learning in semantic segmentation, where new categories are made available over time while previous training data is not retained. The proposed continual learning scheme shapes the latent space to reduce forgetting whilst improving the recognition of novel classes. Our framework is driven by three novel components which we also combine on top of existing techniques effortlessly. First, prototypes matching enforces latent space consistency on old classes, constraining the encoder to produce similar latent representation for previously seen classes in the subsequent steps. Second, features sparsification allows to make room in the latent space to accommodate novel classes. Finally, contrastive learning is employed to cluster features according to their semantics while tearing apart those of different classes. Extensive evaluation on the Pascal VOC2012 and ADE20K datasets demonstrates the effectiveness of our approach, significantly outperforming state-of-the-art methods.

关键词： Deep learning computer vision Limiting Shape Semantics Prototypes Training data

来源：评论

学校读者我要写书评

暂无评论

3D Spatial recognition without Spatially Labeled 3D

3D Spatial Recognition without Spatially Labeled 3D

引用

ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Ren, Zhongzheng Misra, Ishan Schwing, Alexander G. Girdhar, Rohit Facebook AI Res Menlo Pk CA 94025 USA Univ Illinois Urbana IL 61801 USA

ISBN: (纸本)9781665445092

We introduce WyPR, a Weakly-supervised framework for Point cloud recognition, requiring only scene-level class tags as supervision. WyPR jointly addresses three core 3D recognition tasks: point-level semantic segmentation, 3D proposal generation, and 3D object detection, coupling their predictions through self and cross-task consistency losses. We show that in conjunction with standard multiple-instance learning objectives, WyPR can detect and segment objects in point cloud data without access to any spatial labels at training time. We demonstrate its efficacy using the ScanNet and S3DIS datasets, outperforming prior state of the art on weakly-supervised segmentation by more than 6% mIoU. In addition, we set up the first benchmark for weakly-supervised 3D object detection on both datasets, where WyPR outperforms standard approaches and establishes strong baselines for future work.

关键词： Training Couplings computer vision Three-dimensional displays Semantics Object detection pattern recognition

来源：评论

学校读者我要写书评

暂无评论

DeepLM: Large-scale Nonlinear Least Squares on Deep Learning Frameworks using Stochastic Domain Decomposition

DeepLM: Large-scale Nonlinear Least Squares on Deep Learning...

引用

ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Huang, Jingwei Huang, Shan Sun, Mingwei Huawei Technol Rieman Lab Shenzhen Guangdong Peoples R China Wuhan Univ Wuhan Hubei Peoples R China

ISBN: (纸本)9781665445092

We propose a novel approach for large-scale nonlinear least squares problems based on deep learning frameworks. Nonlinear least squares are commonly solved with the Levenberg-Marquardt (LM) algorithm for fast convergence. We implement a general and efficient LM solver on a deep learning framework by designing a new backward jacobian network to enable automatic sparse jacobian matrix computation. Furthermore, we introduce a stochastic domain decomposition approach that enables batched optimization and preserves convergence for large problems. We evaluate our method by solving bundle adjustment as a fundamental problem. Experiments show that our optimizer significantly outperforms the state-of-the-art solutions and existing deep learning solvers considering quality, efficiency, and memory. Our stochastic domain decomposition enables distributed optimization, consumes little memory and time, and achieves similar quality compared to a global solver. As a result, our solver effectively solves nonlinear least squares on an extremely large scale. Our code will be available based on Pytorch(1) and Mindspore(2).

关键词： Deep learning Jacobian matrices Bundle adjustment computer vision Codes Memory management pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Wasserstein Contrastive Representation Distillation

Wasserstein Contrastive Representation Distillation

引用

ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Chen, Liqun Wang, Dong Gan, Zhe Liu, Jingjing Henao, Ricardo Carin, Lawrence Duke Univ Durham NC 27706 USA Microsoft Corp Redmond WA 98052 USA

ISBN: (纸本)9781665445092

The primary goal of knowledge distillation (KD) is to encapsulate the information of a model learned from a teacher network into a student network, with the latter being more compact than the former. Existing work, e.g., using Kullback-Leibler divergence for distillation, may fail to capture important structural knowledge in the teacher network and often lacks the ability for feature generalization, particularly in situations when teacher and student are built to address different classification tasks. We propose Wasserstein Contrastive Representation Distillation (WCoRD), which leverages both primal and dual forms of Wasserstein distance for KD. The dual form is used for global knowledge transfer, yielding a contrastive learning objective that maximizes the lower bound of mutual information between the teacher and the student networks. The primal form is used for local contrastive knowledge transfer within a mini-batch, effectively matching the distributions of features between the teacher and the student networks. Experiments demonstrate that the proposed WCoRD method outperforms state-of-the-art approaches on privileged information distillation, model compression and cross-modal transfer.

关键词： Knowledge engineering Measurement computer vision Computational modeling Collaborative work Robustness pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers

Deep Occlusion-Aware Instance Segmentation with Overlapping ...

引用

ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Ke, Lei Tai, Yu-Wing Tang, Chi-Keung Hong Kong Univ Sci & Technol Hong Kong Peoples R China Kuaishou Technol Beijing Peoples R China

ISBN: (数字)9781665445092

ISBN: (纸本)9781665445092

Segmenting highly-overlapping objects is challenging, because typically no distinction is made between real object contours and occlusion boundaries. Unlike previous two-stage instance segmentation methods, we model image formation as composition of two overlapping layers, and propose Bilayer Convolutional Network (BCNet), where the top GCN layer detects the occluding objects (occluder) and the bottom GCN layer infers partially occluded instance (occludee). The explicit modeling of occlusion relationship with bilayer structure naturally decouples the boundaries of both the occluding and occluded instances, and considers the interaction between them during mask regression. We validate the efficacy of bilayer decoupling on both one-stage and two-stage object detectors with different backbones and network layer choices. Despite its simplicity, extensive experiments on COCO and KINS show that our occlusion-aware BCNet achieves large and consistent performance gain especially for heavy occlusion cases. Code is available at https://***/lkeab/BCNet.

关键词： Convolutional codes Image segmentation computer vision Computational modeling Detectors Performance gain pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Building Reliable Explanations of Unreliable Neural Networks: Locally Smoothing Perspective of Model Interpretation

Building Reliable Explanations of Unreliable Neural Networks...

引用

ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Lim, Dohun Lee, Hyeonseok Kim, Sungchan Jeonbuk Natl Univ Div Comp Sci & Engn Jeonju South Korea

ISBN: (纸本)9781665445092

We present a novel method for reliably explaining the predictions of neural networks. We consider an explanation reliable if it identifies input features relevant to the model output by considering the input and the neighboring data points. Our method is built on top of the assumption of smooth landscape in a loss function of the model prediction: locally consistent loss and gradient profile. A theoretical analysis established in this study suggests that those locally smooth model explanations are learned using a batch of noisy copies of the input with the LI regularization for a saliency map. Extensive experiments support the analysis results, revealing that the proposed saliency maps retrieve the original classes of adversarial examples crafted against both naturally and adversarially trained models, significantly outperforming previous methods. We further demonstrated that such good performance results from the learning capability of this method to identify input features that are truly relevant to the model output of the input and the neighboring data points, fulfilling the requirements of a reliable explanation.

关键词： Analytical models computer vision Smoothing methods computer network reliability Neural networks Predictive models Reliability theory

来源：评论

学校读者我要写书评

暂无评论

Cloud2Curve: Generation and Vectorization of Parametric Sketches

Cloud2Curve: Generation and Vectorization of Parametric Sket...

引用

ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Das, Ayan Yang, Yongxin Hospedales, Timothy Xiang, Tao Song, Yi-Zhe Univ Surrey CVSSP SketchX Guildford Surrey England iFlyTek Surrey Joint Res Ctr Artificial Intellige Guildford Surrey England Univ Edinburgh Edinburgh Midlothian Scotland

ISBN: (纸本)9781665445092

Analysis of human sketches in deep learning has advanced immensely through the use of waypoint-sequences rather than raster-graphic representations. We further aim to model sketches as a sequence of low-dimensional parametric curves. To this end, we propose an inverse graphics framework capable of approximating a raster or waypoint based stroke encoded as a point-cloud with a variable-degree Bezier curve. Building on this module, we present Cloud2Curve, a generative model for scalable high-resolution vector sketches that can be trained end-to-end using point-cloud data alone. As a consequence, our model is also capable of deterministic vectorization which can map novel raster or waypoint based sketches to their corresponding high-resolution scalable Bezier equivalent. We evaluate the generation and vectorization capabilities of our model on Quick, Draw! and K-MNIST datasets.

关键词： Training Graphics Deep learning computer vision Computational modeling Fitting computer architecture

来源：评论

学校读者我要写书评

暂无评论

Towards Real-World Blind Face Restoration with Generative Facial Prior

Towards Real-World Blind Face Restoration with Generative Fa...

引用

ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Wang, Xintao Li, Yu Zhang, Honglun Shan, Ying Tencent PCG Appl Res Ctr ARC Shenzhen Peoples R China

ISBN: (纸本)9781665445092

Blind face restoration usually relies on facial priors, such as facial geometry prior or reference prior, to restore realistic and faithful details. However, very low-quality inputs cannot offer accurate geometric prior while high-quality references are inaccessible, limiting the applicability in real-world scenarios. In this work, we propose GFP-GAN that leverages rich and diverse priors encapsulated in a pretrained face GAN for blind face restoration. This Generative Facial Prior (GFP) is incorporated into the face restoration process via spatial feature transform layers, which allow our method to achieve a good balance of realness and fidelity. Thanks to the powerful generative facial prior and delicate designs, our GFP-GAN could jointly restore facial details and enhance colors with just a single forward pass, while GAN inversion methods require image-specific optimization at inference. Extensive experiments show that our method achieves superior performance to prior art on both synthetic and real-world datasets.

关键词： Geometry computer vision Art Limiting Image color analysis Face recognition Transforms

来源：评论

学校读者我要写书评

暂无评论

Delta Sampling R-BERT for limited data and low-light action recognition

Delta Sampling R-BERT for limited data and low-light action ...

引用

ieee/cvf conference on computer vision and pattern recognition (cvpr)

作者： Hira, Sanchit Das, Ritwik Modi, Abhinav Pakhomov, Daniil Johns Hopkins Univ Baltimore MD 21218 USA

ISBN: (纸本)9781665448994

We present an approach to perform supervised action recognition in the dark. In this work, we present our results on the ARID dataset[60]. Most previous works only evaluate performance on large, well illuminated datasets like Kinetics and HMDB51. We demonstrate that our work is able to achieve a very low error rate while being trained on a much smaller dataset of dark videos. We also explore a variety of training and inference strategies including domain transfer methodologies and also propose a simple but useful frame selection strategy. Our empirical results demonstrate that we beat previously published baseline models by 11%.

关键词： Training Deep learning Technological innovation Schedules computer vision conferences pattern recognition

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 << < 21 22 23 24 25 26 27 28 29 30 > >>

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：