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

29,399 篇 会议
1,396 册 图书
226 篇 期刊文献

馆藏范围

31,019 篇 电子文献
2 种 纸本馆藏

日期分布

学科分类号

17,289 篇 工学
- 13,630 篇 计算机科学与技术...
- 5,205 篇 软件工程
- 2,971 篇 机械工程
- 2,646 篇 光学工程
- 1,413 篇 控制科学与工程
- 1,407 篇 电气工程
- 1,335 篇 信息与通信工程
- 656 篇 生物工程
- 579 篇 仪器科学与技术
- 513 篇 生物医学工程（可授...
- 466 篇 电子科学与技术（可...
- 251 篇 化学工程与技术
- 214 篇 安全科学与工程
- 142 篇 交通运输工程
- 132 篇 建筑学
- 121 篇 材料科学与工程（可...
- 119 篇 土木工程
5,060 篇 理学
- 3,128 篇 物理学
- 2,407 篇 数学
- 824 篇 生物学
- 802 篇 统计学（可授理学、...
- 300 篇 系统科学
- 229 篇 化学
3,832 篇 医学
- 3,800 篇 临床医学
- 187 篇 基础医学(可授医学...
- 140 篇 药学(可授医学、理...
1,061 篇 管理学
- 617 篇 图书情报与档案管...
- 469 篇 管理科学与工程(可...
- 145 篇 工商管理
373 篇 艺术学
- 373 篇 设计学（可授艺术学...
116 篇 法学
81 篇 农学
48 篇 教育学
43 篇 经济学
18 篇 军事学
8 篇 文学

主题

12,597 篇 computer vision
5,699 篇 pattern recognit...
3,181 篇 training
2,263 篇 cameras
2,178 篇 computational mo...
2,117 篇 feature extracti...
2,049 篇 image segmentati...
1,971 篇 visualization
1,967 篇 shape
1,642 篇 robustness
1,491 篇 layout
1,476 篇 three-dimensiona...
1,442 篇 computer science
1,338 篇 computer archite...
1,294 篇 object detection
1,220 篇 semantics
1,143 篇 face recognition
1,107 篇 conferences
1,077 篇 benchmark testin...
1,056 篇 humans

机构

137 篇 univ sci & techn...
134 篇 tsinghua univers...
134 篇 univ chinese aca...
118 篇 chinese univ hon...
101 篇 microsoft resear...
97 篇 zhejiang univers...
95 篇 national laborat...
93 篇 shanghai jiao to...
93 篇 zhejiang univ pe...
85 篇 university of sc...
79 篇 shanghai ai lab ...
78 篇 swiss fed inst t...
65 篇 microsoft res as...
62 篇 adobe research
62 篇 computer vision ...
61 篇 peking univ peop...
58 篇 univ oxford oxfo...
57 篇 google mountain ...
57 篇 hong kong univ s...
56 篇 google res mount...

作者

107 篇 umapada pal
81 篇 van gool luc
68 篇 zhang lei
59 篇 timofte radu
41 篇 yang yi
37 篇 loy chen change
37 篇 hanqing lu
33 篇 liu yang
33 篇 xiaoou tang
32 篇 nassir navab
32 篇 wang liang
30 篇 tian qi
29 篇 h. bischof
29 篇 jan-michael frah...
29 篇 vittorio murino
29 篇 darrell trevor
27 篇 li xin
27 篇 vasconcelos nuno
27 篇 murino vittorio
27 篇 chen chen

语言

30,855 篇 英文
96 篇 其他
90 篇 中文
6 篇 土耳其文
2 篇 日文
2 篇 俄文
1 篇 西班牙文

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

共 31021 条记录，以下是4421-4430 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：

Invisible Perturbations: Physical Adversarial Examples Exploiting the Rolling Shutter Effect

Invisible Perturbations: Physical Adversarial Examples Explo...

引用

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

作者： Sayles, Athena Hooda, Ashish Gupta, Mohit Chatterjee, Rahul Fernandes, Earlence Univ Wisconsin Madison WI 53706 USA

ISBN: (纸本)9781665445092

Physical adversarial examples for camera-based computer vision have so far been achieved through visible artifacts - a sticker on a Stop sign, colorful borders around eyeglasses or a 3D printed object with a colorful texture. An implicit assumption here is that the perturbations must be visible so that a camera can sense them. By contrast, we contribute a procedure to generate, for the first time, physical adversarial examples that are invisible to human eyes. Rather than modifying the victim object with visible artifacts, we modify light that illuminates the object. We demonstrate how an attacker can craft a modulated light signal that adversarially illuminates a scene and causes targeted misclassifications on a state-of-the-art ImageNet deep learning model. Concretely, we exploit the radiometric rolling shutter effect in commodity cameras to create precise striping patterns that appear on images. To human eyes, it appears like the object is illuminated, but the camera creates an image with stripes that will cause ML models to output the attacker-desired classification. We conduct a range of simulation and physical experiments with LEDs, demonstrating targeted attack rates up to 84%.

关键词： Deep learning computer vision Three-dimensional displays Computational modeling Perturbation methods Cameras Radiometry

来源：评论

学校读者我要写书评

暂无评论

Learning Deep Latent Variable Models by Short-Run MCMC Inference with Optimal Transport Correction

Learning Deep Latent Variable Models by Short-Run MCMC Infer...

引用

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

作者： An, Dongsheng Xie, Jianwen Li, Ping Baidu Res Cognit Comp Lab 10900 NE 8th St Bellevue WA 98004 USA

ISBN: (纸本)9781665445092

Learning latent variable models with deep top-down architectures typically requires inferring the latent variables for each training example based on the posterior distribution of these latent variables. The inference step typically relies on either time-consuming long-run Markov chain Monte Carlo (MCMC) sampling or a separate inference model for variational learning. In this paper, we propose to use a short-run MCMC, such as a short-run Langevin dynamics, as an approximate flow-based inference engine. The bias existing in the output distribution of the non-convergent short-run Langevin dynamics is corrected by the optimal transport (OT), which aims at transforming the biased distribution produced by the finite-step MCMC to the prior distribution with a minimum transport cost. Our experiments not only verify the effectiveness of the OT correction for the short-run MCMC, but also demonstrate that the latent variable model trained by the proposed strategy performs better than the variational auto-encoder (VAE) in terms of image reconstruction/generation and anomaly detection.

关键词： Training Monte Carlo methods Costs Image synthesis Markov processes pattern recognition Task analysis

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

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

PLOP: Learning without Forgetting for Continual Semantic Segmentation

PLOP: Learning without Forgetting for Continual Semantic Seg...

引用

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

作者： Douillard, Arthur Chen, Yifu Dapogny, Arnaud Cord, Matthieu Sorbonne Univ Paris France Heuritech Paris France Datakalab Paris France Valeoai Paris France

ISBN: (纸本)9781665445092

Deep learning approaches are nowadays ubiquitously used to tackle computer vision tasks such as semantic segmentation, requiring large datasets and substantial computational power. Continual learning for semantic segmentation (CSS) is an emerging trend that consists in updating an old model by sequentially adding new classes. However, continual learning methods are usually prone to catastrophic forgetting. This issue is further aggravated in CSS where, at each step, old classes from previous iterations are collapsed into the background. In this paper, we propose Local POD, a multi-scale pooling distillation scheme that preserves long- and short-range spatial relationships at feature level. Furthermore, we design an entropy-based pseudo-labelling of the background w.r.t. classes predicted by the old model to deal with background shift and avoid catastrophic forgetting of the old classes. Our approach, called PLOP, significantly outperforms state-of-the-art methods in existing CSS scenarios, as well as in newly proposed challenging benchmarks(1).

关键词： Learning systems computer vision Semantics Benchmark testing Predictive models Market research Stability analysis

来源：评论

学校读者我要写书评

暂无评论

TearingNet: Point Cloud Autoencoder to Learn Topology-Friendly Representations

TearingNet: Point Cloud Autoencoder to Learn Topology-Friend...

引用

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

作者： Pang, Jiahao Li, Duanshun Tian, Dong InterDigital Princeton NJ 08540 USA

ISBN: (纸本)9781665445092

Topology matters. Despite the recent success of point cloud processing with geometric deep learning, it remains arduous to capture the complex topologies of point cloud data with a learning model. Given a point cloud dataset containing objects with various genera, or scenes with multiple objects, we propose an autoencoder, TearingNet, which tackles the challenging task of representing the point clouds using a fixed-length descriptor. Unlike existing works directly deforming predefined primitives of genus zero (e.g., a 2D square patch) to an object-level point cloud, our TearingNet is characterized by a proposed Tearing network module and a Folding network module interacting with each other iteratively. Particularly, the Tearing network module learns the point cloud topology explicitly. By breaking the edges of a primitive graph, it tears the graph into patches or with holes to emulate the topology of a target point cloud, leading to faithful reconstructions. Experimentation shows the superiority of our proposal in terms of reconstructing point clouds as well as generating more topology friendly representations than benchmarks.

关键词： Deep learning Surface reconstruction Network topology Shape Topology pattern recognition Proposals

来源：评论

学校读者我要写书评

暂无评论

Mining Diverse Clues with Transformers for Person Re-identification 5th

Mining Diverse Clues with Transformers for Person Re-identif...

引用

5th Chinese conference on pattern recognition and computer vision (PRCV)

作者： Song, Xiaolin Feng, Jin Du, Tianming Zhang, Honggang Beijing Univ Posts & Telecommun Beijing Peoples R China

ISBN: (纸本)9783031189128;9783031189135

Person Re-identification (ReID) is a challenging task due to the inherently large intra-class variation and subtle inter-class differences. Early works mainly tackle this problem by learning a discriminative pedestrian feature representation. Recently, vision transformer (ViT) has shown outstanding performance in many tasks, where the self-attention mechanism plays a key role that links every patch tokens with the class token. Intuitively, the class token could serve as a good global feature that captures local details naturally. Experiments demonstrate that the vanilla ViT can achieve impressive performance when directly applied to the ReID problem. Nevertheless, the class token may pay much attention to most salient patches while ignoring less salient but informative ones and missing some potential clues. To reduce this limitation, we propose a novel network MDCTNet to mine divers clues for person re-identification with transformers. Based on the cascaded architecture of transformer encoder, a Patch Suppression Module (PSM) is incorporated into the last several transformer layers, which aims to progressively discard some most salient patch tokens andmake less salient ones passed to the next layer. Thus, the model is enforced to mine more potential useful clues in the remained patches and the resulting pedestrian representation can be more robust. Extensive experiments on three mainstream datasets including Market1501, DukeMTMC-ReID and MSMT17 validate the effectiveness of our method.

关键词： Person re-identification vision transformer Self-attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Machine Learning and Symbolic Learning for the recognition of Leukemia L1, L2 and L3 14th

Machine Learning and Symbolic Learning for the Recognition o...

引用

14th Mexican conference on pattern recognition (MCPR)

作者： Ochoa-Montiel, Rocio Sossa, Humberto Olague, Gustavo Sanchez-Lopez, Carlos Inst Politecn Nacl Ctr Invest Comp Av Juan de Dios Batiz & M Othon de Mendizabal Mexico City 07738 Mexico Univ Autonoma Tlaxcala Fac Ciencias Basicas Ingn & Tecnol Apizaco Mexico CICESE Res Ctr EvoVis Lab Ensenada Mexico Tecnol Monterrey Escuela Ingn & Ciencias Av Gen Ramon Corona Zapopan 2514 Jalisco Mexico

ISBN: (纸本)9783031077500;9783031077494

Leukemia is a health problem that affects to world population causing thousands of kills yearly, thus accurate and human-readable diagnostic methods are required. Symbolic learning uses methods based on high-level representations of problems, which is useful to design interpretable models to understand the solutions found to solve a problem. In this work, we analyze the performance of 3 classifiers used frequently in machine learning, which are independently embedded into a model of symbolic learning named brain programming. Results suggest that the classifiers as MLP and SVM are robust to noisy data, with the MLP demonstrating the most stable behavior into the symbolic learning model, which is fundamental in models of evolutionary vision as the brain programming.

关键词： Symbolic learning Evolutionary vision Leukemia recognition

来源：评论

学校读者我要写书评

暂无评论

Confluent Vessel Trees with Accurate Bifurcations

Confluent Vessel Trees with Accurate Bifurcations

引用

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

作者： Zhang, Zhongwen Marin, Dmitrii Drangova, Maria Boykov, Yuri Univ Waterloo Waterloo ON Canada Vector Res Inst Toronto ON Canada Robarts Res London ON Canada

ISBN: (纸本)9781665445092

We are interested in unsupervised reconstruction of complex near-capillary vasculature with thousands of bifurcations where supervision and learning are infeasible. Unsupervised methods can use many structural constraints, e.g. topology, geometry, physics. Common techniques use variants of MST on geodesic tubular graphs minimizing symmetric pairwise costs, i.e. distances. We show limitations of such standard undirected tubular graphs producing typical errors at bifurcations where flow\directedness" is critical. We introduce a new general concept of confluence for continuous oriented curves forming vessel trees and show how to enforce it on discrete tubular graphs. While confluence is a high-order property, we present an efficient practical algorithm for reconstructing confluent vessel trees using minimum arborescence on a directed graph enforcing confluence via simple flow-extrapolating arc construction. Empirical tests on large near-capillary sub-voxel vasculature volumes demonstrate significantly improved reconstruction accuracy at bifurcations. Our code has also been made publicly available(1).

关键词： Geometry computer vision Costs Codes Directed graphs Bifurcation Topology

来源：评论

学校读者我要写书评

暂无评论

DreamNet: A Deep Riemannian Manifold Network for SPD Matrix Learning 16th

DreamNet: A Deep Riemannian Manifold Network for SPD Matrix...

引用

16th Asian conference on computer vision, ACCV 2022

作者： Wang, Rui Wu, Xiao-Jun Chen, Ziheng Xu, Tianyang Kittler, Josef School of Artificial Intelligence and Computer Science Jiangnan University Wuxi214122 China Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi214122 China University of Surrey GuildfordGU2 7XH United Kingdom

ISBN: (纸本)9783031263507

The methods of symmetric positive definite (SPD) matrix learning have attracted considerable attention in many pattern recognition tasks, as they are eligible to capture and learn appropriate statistical features while respecting the Riemannian geometry of SPD manifold where the data reside on. Accompanied with the advanced deep learning techniques, several Riemannian networks (RiemNets) for SPD matrix nonlinear processing have recently been studied. However, it is pertinent to ask, whether greater accuracy gains can be realized by simply increasing the depth of RiemNets. The answer appears to be negative, as deeper RiemNets may be difficult to train. To explore a possible solution to this issue, we propose a new architecture for SPD matrix learning. Specifically, to enrich the deep representations, we build a stacked Riemannian autoencoder (SRAE) on the tail of the backbone network, i.e., SPDNet [23]. With this design, the associated reconstruction error term can prompt the embedding functions of both SRAE and of each RAE to approach an identity mapping, which helps to prevent the degradation of statistical information. Then, we implant several residual-like blocks using shortcut connections to augment the representational capacity of SRAE, and to simplify the training of a deeper network. The experimental evidence demonstrates that our DreamNet can achieve improved accuracy with increased depth. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： 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 << < 439 440 441 442 443 444 445 446 447 448 > >>

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：