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

20,798 篇 会议
88 篇 期刊文献
5 册 图书

馆藏范围

20,890 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

13,275 篇 工学
- 10,923 篇 计算机科学与技术...
- 2,484 篇 机械工程
- 2,307 篇 软件工程
- 913 篇 光学工程
- 771 篇 电气工程
- 556 篇 控制科学与工程
- 405 篇 信息与通信工程
- 210 篇 测绘科学与技术
- 131 篇 生物医学工程（可授...
- 104 篇 电子科学与技术（可...
- 100 篇 生物工程
- 92 篇 仪器科学与技术
- 56 篇 化学工程与技术
- 52 篇 建筑学
- 48 篇 土木工程
- 44 篇 安全科学与工程
- 38 篇 力学（可授工学、理...
- 38 篇 航空宇航科学与技...
- 35 篇 交通运输工程
3,457 篇 医学
- 3,449 篇 临床医学
- 34 篇 基础医学(可授医学...
2,315 篇 理学
- 1,154 篇 数学
- 1,132 篇 物理学
- 417 篇 统计学（可授理学、...
- 386 篇 生物学
- 252 篇 系统科学
- 57 篇 化学
353 篇 管理学
- 184 篇 图书情报与档案管...
- 176 篇 管理科学与工程(可...
- 32 篇 工商管理
28 篇 法学
20 篇 农学
15 篇 教育学
9 篇 经济学
8 篇 艺术学
5 篇 文学
5 篇 军事学

主题

8,203 篇 computer vision
2,966 篇 pattern recognit...
2,732 篇 training
1,769 篇 computational mo...
1,653 篇 visualization
1,483 篇 cameras
1,415 篇 shape
1,369 篇 three-dimensiona...
1,369 篇 face recognition
1,285 篇 image segmentati...
1,272 篇 feature extracti...
1,178 篇 robustness
1,090 篇 semantics
1,040 篇 layout
1,007 篇 object detection
975 篇 object recogniti...
969 篇 computer science
948 篇 computer archite...
946 篇 benchmark testin...
931 篇 codes

机构

174 篇 univ sci & techn...
154 篇 carnegie mellon ...
148 篇 univ chinese aca...
144 篇 chinese univ hon...
112 篇 microsoft resear...
103 篇 zhejiang univ pe...
99 篇 swiss fed inst t...
97 篇 tsinghua univ pe...
93 篇 tsinghua univers...
91 篇 microsoft res as...
88 篇 shanghai ai lab ...
81 篇 zhejiang univers...
76 篇 alibaba grp peop...
74 篇 hong kong univ s...
73 篇 university of sc...
72 篇 peking univ peop...
69 篇 university of ch...
68 篇 shanghai jiao to...
66 篇 google res mount...
66 篇 univ oxford oxfo...

作者

80 篇 van gool luc
71 篇 zhang lei
59 篇 timofte radu
48 篇 yang yi
46 篇 xiaoou tang
44 篇 darrell trevor
43 篇 tian qi
43 篇 luc van gool
42 篇 loy chen change
42 篇 sun jian
42 篇 li fei-fei
40 篇 li stan z.
40 篇 qi tian
37 篇 liu yang
37 篇 chen xilin
36 篇 shan shiguang
35 篇 liu xiaoming
35 篇 vasconcelos nuno
35 篇 torralba antonio
32 篇 zhou jie

语言

20,868 篇 英文
14 篇 中文
6 篇 其他
2 篇 日文
2 篇 土耳其文

检索条件"任意字段=2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009"

共 20891 条记录，以下是4971-4980 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：

Structured Gradient-Based Interpretations via Norm-Regularized Adversarial Training

Structured Gradient-Based Interpretations via Norm-Regulariz...

引用

conference on computer vision and pattern recognition (cvpr)

作者： Shizhan Gong Qi Dou Farzan Farnia The Chinese University of Hong Kong

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Gradient-based saliency maps have been widely used to explain the decisions of deep neural network classifiers. However, standard gradient-based interpretation maps, including the simple gradient and integrated gradient algorithms, often lack desired structures such as sparsity and connectedness in their application to real-world computer vision models. A frequently used approach to inducing sparsity structures into gradient-based saliency maps is to alter the simple gradient scheme using sparsification or norm-based regularization. A drawback with such post-processing methods is their frequently-observed significant loss in fidelity to the original simple gradient map. In this work, we propose to apply adversarial training as an inprocessing scheme to train neural networks with structured simple gradient maps. We show a duality relation between the regularized norms of the adversarial perturbations and gradient-based maps, based on which we design adversarial training loss functions promoting sparsity and group-sparsity properties in simple gradient maps. We present several numerical results to show the influence of our proposed norm-based adversarial training methods on the standard gradient-based maps of standard neural network architectures on benchmark image datasets 1 1 The paper's code is available at: https://***/peterant330/AdvGrad.

关键词： Training computer vision Perturbation methods Benchmark testing Stability analysis Robustness pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Learning Compositional Radiance Fields of Dynamic Human Heads

Learning Compositional Radiance Fields of Dynamic Human Head...

引用

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

作者： Wang, Ziyan Bagautdinov, Timur Lombardi, Stephen Simon, Tomas Saragih, Jason Hodgins, Jessica Zollhofer, Michael Carnegie Mellon Univ Pittsburgh PA 15213 USA Facebook AI Res Menlo Pk CA USA Facebook Real Labs Res Menlo Pk CA 94025 USA

ISBN: (纸本)9781665445092

Photorealistic rendering of dynamic humans is an important capability for telepresence systems, virtual shopping, special effects in movies, and interactive experiences such as games. Recently, neural rendering methods have been developed to create high-fidelity models of humans and objects. Some of these methods do not produce results with high-enough fidelity for driveable human models (Neural Volumes) whereas others have extremely long rendering times (NeRF). We propose a novel compositional 3D representation that combines the best of previous methods to produce both higher-resolution and faster results. Our representation bridges the gap between discrete and continuous volumetric representations by combining a coarse 3D-structure-aware grid of animation codes with a continuous learned scene function that maps every position and its corresponding local animation code to a view-dependent emitted radiance and local volume density. Differentiable volume rendering is employed to compute photo-realistic novel views of the human head and upper body as well as to train our novel representation end-to-end using only 2D supervision. In addition, we show that the learned dynamic radiance field can be used to synthesize novel unseen expressions based on a global animation code. Our approach achieves state-of-the-art results for synthesizing novel views of dynamic human heads and the upper body. See our project page' for more results.

关键词： Interpolation Codes Telepresence Three-dimensional displays Aerospace electronics Rendering (computer graphics) Animation

来源：评论

学校读者我要写书评

暂无评论

Patchwise Generative ConvNet: Training Energy-Based Models from a Single Natural Image for Internal Learning

Patchwise Generative ConvNet: Training Energy-Based Models f...

引用

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

作者： Zheng, Zilong Xie, Jianwen Li, Ping Univ Calif Los Angeles Los Angeles CA 90095 USA Baidu Res Cognit Comp Lab Bellevue WA USA

ISBN: (纸本)9781665445092

Exploiting internal statistics of a single natural image has long been recognized as a significant research paradigm where the goal is to learn the internal distribution of patches within the image without relying on external training data. Different from prior works that model such a distribution implicitly with a top-down latent variable model (e.g., generator), this paper proposes to explicitly represent the statistical distribution within a single natural image by using an energy-based generative framework, where a pyramid of energy functions, each parameterized by a bottom-up deep neural network, are used to capture the distributions of patches at different resolutions. Meanwhile, a coarse-to-fine sequential training and sampling strategy is presented to train the model efficiently. Besides learning to generate random samples from white noise, the model can learn in parallel with a self-supervised task (e.g., recover the input image from its corrupted version), which can further improve the descriptive power of the learned model. The proposed model is simple and natural in that it does not require an auxiliary model (e.g., discriminator) to assist the training. Besides, it also unifies internal statistics learning and image generation in a single framework. Experimental results presented on various image generation and manipulation tasks, including super-resolution, image editing, harmonization, style transfer, etc, have demonstrated the effectiveness of our model for internal learning.

关键词： Training Image recognition Image synthesis Computational modeling Superresolution Training data Statistical distributions

来源：评论

学校读者我要写书评

暂无评论

Blur, Noise, and Compression Robust Generative Adversarial Networks

Blur, Noise, and Compression Robust Generative Adversarial N...

引用

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

作者： Kaneko, Takuhiro Harada, Tatsuya Univ Tokyo Tokyo Japan RIKEN Tokyo Japan

ISBN: (纸本)9781665445092

Generative adversarial networks (GANs) have gained considerable attention owing to their ability to reproduce images. However, they can recreate training images faithfully despite image degradation in the form of blur, noise, and compression, generating similarly degraded images. To solve this problem, the recently proposed noise robust GAN (NR-GAN) provides a partial solution by demonstrating the ability to learn a clean image generator directly from noisy images using a two-generator model comprising image and noise generators. However, its application is limited to noise, which is relatively easy to decompose owing to its additive and reversible characteristics, and its application to irreversible image degradation, in the form of blur, compression, and combination of all, remains a challenge. To address these problems, we propose blur, noise, and compression robust GAN (BNCR-GAN) that can learn a clean image generator directly from degraded images without knowledge of degradation parameters (e.g., blur kernel types, noise amounts, or quality factor values). Inspired by NR-GAN, BNCR-GAN uses a multiple-generator model composed of image, blur-kernel, noise, and quality-factor generators. However, in contrast to NR-GAN, to address irreversible characteristics, we introduce masking architectures adjusting degradation strength values in a data-driven manner using bypasses before and after degradation. Furthermore, to suppress uncertainty caused by the combination of blur, noise, and compression, we introduce adaptive consistency losses imposing consistency between irreversible degradation processes according to the degradation strengths. We demonstrate the effectiveness of BNCR-GAN through large-scale comparative studies on CIFAR-10 and a generality analysis on FFHQ. In addition, we demonstrate the applicability of BNCR-GAN in image restoration.

关键词： Degradation Training Adaptation models Image coding Uncertainty Computational modeling computer architecture

来源：评论

学校读者我要写书评

暂无评论

Perceptual Loss for Robust Unsupervised Homography Estimation

Perceptual Loss for Robust Unsupervised Homography Estimatio...

引用

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

作者： Koguciuk, Daniel Arani, Elahe Zonooz, Bahram NavInfo Europe Adv Res Lab Eindhoven Netherlands

ISBN: (纸本)9781665448994

Homography estimation is often an indispensable step in many computer vision tasks. The existing approaches, however, are not robust to illumination and/or larger viewpoint changes. In this paper, we propose bidirectional implicit Homography Estimation (biHomE) loss for unsupervised homography estimation. biHomE minimizes the distance in the feature space between the warped image from the source viewpoint and the corresponding image from the target viewpoint. Since we use a fixed pre-trained feature extractor and the only learnable component of our framework is the homography network, we effectively decouple the homography estimation from representation learning. We use an additional photometric distortion step in the synthetic COCO dataset generation to better represent the illumination variation of the real-world scenarios. We show that biHomE achieves state-of-the-art performance on synthetic COCO dataset, which is also comparable or better compared to supervised approaches. Furthermore, the empirical results demonstrate the robustness of our approach to illumination variation compared to existing methods.

关键词： Degradation computer vision conferences Estimation Lighting Feature extraction Distortion

来源：评论

学校读者我要写书评

暂无评论

ParameterNet: Parameters are All You Need for Large-Scale Visual Pretraining of Mobile Networks

ParameterNet: Parameters are All You Need for Large-Scale Vi...

引用

conference on computer vision and pattern recognition (cvpr)

作者： Kai Han Yunhe Wang Jianyuan Guo Enhua Wu Huawei Noah's Ark Lab State Key Lab of Computer Science ISCAS & UCAS The University of Sydney Faculty of Science and Technology University of Macau

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

The large-scale visual pretraining has significantly improve the performance of large vision models. However, we observe the low FLOPs pitfall that the existing low-FLOPs models cannot benefit from large-scale pretraining. In this paper, we introduce a novel design principle, termed ParameterNet, aimed at augmenting the number of parameters in large-scale visual pretraining models while minimizing the increase in FLOPs. We leverage dynamic convolutions to incorporate additional parameters into the networks with only a marginal rise in FLOPs. The ParameterNet approach allows low-FLOPs networks to take advantage of large-scale visual pretraining. Furthermore, we extend the ParameterNet concept to the language domain to enhance inference results while preserving inference speed. Experiments on the large-scale ImageNet-22K have shown the superiority of our ParameterNet scheme. For example, ParameterNet-600M can achieve higher accuracy than the widely-used Swin Transformer (81.6% vs. 80.9%) and has much lower FLOPs (0.6G vs. 4.5G). The code will be released at https://***/.

关键词： Convolutional codes Visualization computer vision Accuracy Transformers pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes

Neural Geometric Level of Detail: Real-time Rendering with I...

引用

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

作者： Takikawa, Towaki Litalien, Joey Yin, Kangxue Kreis, Karsten Loop, Charles Nowrouzezahrai, Derek Jacobson, Alec McGuire, Morgan Fidler, Sanja NVIDIA Santa Clara CA 95051 USA Univ Toronto Toronto ON Canada McGill Univ Montreal PQ Canada Vector Inst Toronto ON Canada

ISBN: (纸本)9781665445092

Neural signed distance functions (SDFs) are emerging as an effective representation for 3D shapes. State-of-the-art methods typically encode the SDF with a large, fixed-size neural network to approximate complex shapes with implicit surfaces. Rendering with these large networks is, however, computationally expensive since it requires many forward passes through the network for every pixel, making these representations impractical for real-time graphics. We introduce an efficient neural representation that, for the first time, enables real-time rendering of high-fidelity neural SDFs, while achieving state-of-the-art geometry reconstruction quality. We represent implicit surfaces using an octree-based feature volume which adaptively fits shapes with multiple discrete levels of detail (LODs), and enables continuous LOD with SDF interpolation. We further develop an efficient algorithm to directly render our novel neural SDF representation in real-time by querying only the necessary LODs with sparse octree traversal. We show that our representation is 2-3 orders of magnitude more efficient in terms of rendering speed compared to previous works. Furthermore, it produces state-of-the-art reconstruction quality for complex shapes under both 3D geometric and 2D image-space metrics.

关键词： Measurement Surface reconstruction Three-dimensional displays Shape Octrees Neural networks Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

Gaussian Context Transformer

Gaussian Context Transformer

引用

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

作者： Ruan, Dongsheng Wang, Daiyin Zheng, Yuan Zheng, Nenggan Zheng, Min Zhejiang Univ Qiushi Acad Adv Studies Hangzhou Zhejiang Peoples R China Zhejiang Univ Coll Opt Sci & Engn Hangzhou Zhejiang Peoples R China Zhejiang Univ Coll Comp Sci & Technol Hangzhou Zhejiang Peoples R China Zhejiang Univ Sch Aeronaut & Astronaut Hangzhou Zhejiang Peoples R China Zhejiang Univ State Key Lab Diag & Treatment Infect Dis Affiliated Hosp 1 Coll Med Hangzhou Zhejiang Peoples R China

ISBN: (纸本)9781665445092

Recently, a large number of channel attention blocks are proposed to boost the representational power of deep convolutional neural networks (CNNs). These approaches commonly learn the relationship between global contexts and attention activations by fully-connected layers or linear transformations. However, we empirically find that though many parameters are introduced, these attention blocks may not learn the relationship well. In this paper, we hypothesize that the relationship is predetermined. Based on this hypothesis, we propose a simple yet extremely efficient channel attention block, called Gaussian Context Transformer (GCT), which achieves contextual feature excitation using a Gaussian function that satisfies the presupposed relationship. According to whether the standard deviation of the Gaussian function is learnable, we develop two versions of GCT: GCT-B0 and GCT-B1. GCT-B0 is a parameter-free channel attention block by fixing the standard deviation. It directly maps global contexts to attention activations without learning. In contrast, GCT-B1 is a parameterized version, which adaptively learns the standard deviation to enhance the mapping ability. Extensive experiments on ImageNet and MS COCO benchmarks demonstrate that our GCTs lead to consistent improvements across various deep CNNs and detectors. Compared with a bank of state-of-the-art channel attention blocks, such as SE [17] and ECA [42], our GCTs are superior in effectiveness and efficiency.

关键词： computer vision Transforms Detectors Benchmark testing Transformers Solids pattern recognition

来源：评论

学校读者我要写书评

暂无评论

A Unified Framework for Human-centric Point Cloud Video Understanding

A Unified Framework for Human-centric Point Cloud Video Unde...

引用

conference on computer vision and pattern recognition (cvpr)

作者： Yiteng Xu Kecheng Ye Xiao Han Yiming Ren Xinge Zhu Yuexin Ma ShanghaiTech University The Chinese University of Hong Kong

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Human-centric Point Cloud Video Understanding (PVU) is an emerging field focused on extracting and interpreting human-related features from sequences of human point clouds, further advancing downstream human-centric tasks and applications. Previous works usually focus on tack-ling one specific task and rely on huge labeled data, which has poor generalization capability. Considering that hu-man has specific characteristics, including the structural semantics of human body and the dynamics of human motions, we propose a unified framework to make full use of the prior knowledge and explore the inherent features in the data itself for generalized human-centric point cloud video understanding. Extensive experiments demonstrate that our method achieves state-of-the-art performance on various human-related tasks, including action recognition and 3D pose estimation. All datasets and code will be re-leased soon.

关键词： Point cloud compression computer vision Three-dimensional displays Codes Semantics Dynamics Pose estimation

来源：评论

学校读者我要写书评

暂无评论

Improved Self-Training for Test-Time Adaptation

Improved Self-Training for Test-Time Adaptation

引用

conference on computer vision and pattern recognition (cvpr)

作者： Jing Ma Huazhong University of Science and Technology

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Test-time adaptation (TTA) is a technique to improve the performance of a pretrained source model on a target distribution without using any labeled data. However, existing self-trained TTA methods often face the challenges of un-reliable pseudo-labels and unstable model optimization. In this paper, we propose an Improved Self-Training (IST) approach, which addresses these challenges by enhancing the pseudo-label quality and stabilizing the adaptation process. Specifically, we use a simple augmentation strategy to gen-erate multiple views of each test sample, and construct a graph structure to correct the pseudo-labels based on the similarity of the latent features. Moreover, we adopt a parameter moving average scheme to smooth the model up-dates and prevent catastrophic forgetting. Instead of using a model with fixed label space, we explore the adaptability of the foundation model CLIP to various downstream tasks at test time. Extensive experiments on various benchmarks show that IST can achieve significant and consistent improvements over the existing TTA methods in classification, detection, and segmentation tasks.

关键词： Adaptation models computer vision Semantic segmentation Face recognition Object detection Benchmark testing Data 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 << < 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：