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

22,771 篇 会议
112 篇 期刊文献
23 册 图书

馆藏范围

22,905 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

13,398 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
- 1,010 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

10,126 篇 computer vision
4,025 篇 pattern recognit...
2,900 篇 training
1,958 篇 computational mo...
1,792 篇 cameras
1,758 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

22,844 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 22906 条记录，以下是4711-4720 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：

Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstruction

Dynamic Neural Radiance Fields for Monocular 4D Facial Avata...

引用

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

作者： Gafni, Guy Thies, Justus Zollhoefer, Michael Niessner, Matthias Tech Univ Munich Munich Germany Facebook Real Labs Res Pittsburgh PA USA

ISBN: (纸本)9781665445092

We present dynamic neural radiance fields for modeling the appearance and dynamics of a human face(1). Digitally modeling and reconstructing a talking human is a key building-block for a variety of applications. Especially, for telepresence applications in AR or VR, a faithful reproduction of the appearance including novel viewpoint or headposes is required. In contrast to state-of-the-art approaches that model the geometry and material properties explicitly, or are purely image-based, we introduce an implicit representation of the head based on scene representation networks. To handle the dynamics of the face, we combine our scene representation network with a low-dimensional morphable model which provides explicit control over pose and expressions. We use volumetric rendering to generate images from this hybrid representation and demonstrate that such a dynamic neural scene representation can be learned from monocular input data only, without the need of a specialized capture setup. In our experiments, we show that this learned volumetric representation allows for photorealistic image generation that surpasses the quality of state-of-the-art video-based reenactment methods.

关键词： Geometry Telepresence Webcams Image synthesis Avatars Rendering (computer graphics) Hybrid power systems

来源：评论

学校读者我要写书评

暂无评论

2D or not 2D? Adaptive 3D Convolution Selection for Efficient Video recognition

2D or not 2D? Adaptive 3D Convolution Selection for Efficien...

引用

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

作者： Li, Hengduo Wu, Zuxuan Shrivastava, Abhinav Davis, Larry S. Univ Maryland College Pk MD 20742 USA Fudan Univ Shanghai Peoples R China

ISBN: (纸本)9781665445092

3D convolutional networks are prevalent for video recognition. While achieving excellent recognition performance on standard benchmarks, they operate on a sequence of frames with 3D convolutions and thus are computationally demanding. Exploiting large variations among different videos, we introduce Ada3D, a conditional computation framework that learns instance-specific 3D usage policies to determine frames and convolution layers to be used in a 3D network. These policies are derived with a two-head lightweight selection network conditioned on each input video clip. Then, only frames and convolutions that are selected by the selection network are used in the 3D model to generate predictions. The selection network is optimized with policy gradient methods to maximize a reward that encourages making correct predictions with limited computation. We conduct experiments on three video recognition benchmarks and demonstrate that our method achieves similar accuracies to state-of-the-art 3D models while requiring 20% - 50% less computation across different datasets. We also show that learned policies are transferable and Ada3D is compatible to different backbones and modern clip selection approaches. Our qualitative analysis indicates that our method allocates fewer 3D convolutions and frames for "static" inputs, yet uses more for motion-intensive clips.

关键词： Solid modeling Gradient methods computer vision Three-dimensional displays Computational modeling Benchmark testing Predictive models

来源：评论

学校读者我要写书评

暂无评论

Learning to Identify Correct 2D-2D Line Correspondences on Sphere

Learning to Identify Correct 2D-2D Line Correspondences on S...

引用

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

作者： Li, Haoang Chen, Kai Zhao, Ji Wang, Jiangliu Kim, Pyojin Liu, Zhe Liu, Yun-Hui Chinese Univ Hong Kong Hong Kong Peoples R China TuSimple Beijing Peoples R China Sookmyung Womens Univ Seoul South Korea Univ Cambridge Cambridge England

ISBN: (纸本)9781665445092

Given a set of putative 2D-2D line correspondences, we aim to identify correct matches. Existing methods exploit the geometric constraints. They are only applicable to structured scenes with orthogonality, parallelism and coplanarity. In contrast, we propose the first approach suitable for both structured and unstructured scenes. Instead of geometric constraint, we leverage the spatial regularity on sphere. Specifically, we propose to map line correspondences into vectors tangent to sphere. We use these vectors to encode both angular and positional variations of image lines, which is more reliable and concise than directly using inclinations, midpoints or endpoints of image lines. Neighboring vectors mapped from correct matches exhibit a spatial regularity called local trend consistency, regardless of the type of scenes. To encode this regularity, we design a neural network and also propose a novel loss function that enforces the smoothness constraint of vector field. In addition, we establish a large real-world dataset for image line matching. Experiments showed that our approach outperforms state-of-the-art ones in terms of accuracy, efficiency and robustness, and also leads to high generalization.

关键词： computer vision computer network reliability Neural networks Parallel processing Market research Robustness pattern recognition

来源：评论

学校读者我要写书评

暂无评论

DeAR: Debiasing vision-Language Models with Additive Residuals

DeAR: Debiasing Vision-Language Models with Additive Residua...

引用

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

作者： Seth, Ashish Hemani, Mayur Agarwal, Chirag IIT Madras Madras India Adobe Inc San Jose CA USA

ISBN: (纸本)9798350301298

Large pre-trained vision-language models (VLMs) reduce the time for developing predictive models for various vision-grounded language downstream tasks by providing rich, adaptable image and text representations. However, these models suffer from societal biases owing to the skewed distribution of various identity groups in the training data. These biases manifest as the skewed similarity between the representations for specific text concepts and images of people of different identity groups and, therefore, limit the usefulness of such models in real-world high-stakes applications. In this work, we present DEAR (Debiasing with Additive Residuals), a novel debiasing method that learns additive residual image representations to offset the original representations, ensuring fair output representations. In doing so, it reduces the ability of the representations to distinguish between the different identity groups. Further, we observe that the current fairness tests are performed on limited face image datasets that fail to indicate why a specific text concept should/should not apply to them. To bridge this gap and better evaluate DEAR, we introduce the PROTECTED ATTRIBUTE TAG ASSOCIATION (PATA) dataset - a new context-based bias benchmarking dataset for evaluating the fairness of large pre-trained VLMs. Additionally, PATA provides visual context for a diverse human population in different scenarios with both positive and negative connotations. Experimental results for fairness and zero-shot performance preservation using multiple datasets demonstrate the efficacy of our framework. The dataset is released here.

关键词： accountability ethics in vision fairness privacy Transparency

来源：评论

学校读者我要写书评

暂无评论

Context-Aware Sequence Alignment using 4D Skeletal Augmentation

Context-Aware Sequence Alignment using 4D Skeletal Augmentat...

引用

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

作者： Kwon, Taein Tekin, Bugra Tang, Siyu Pollefeys, Marc Swiss Fed Inst Technol Dept Comp Sci Zurich Switzerland Microsoft MR & AI Lab Zurich Switzerland

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Temporal alignment of fine-grained human actions in videos is important for numerous applications in computer vision, robotics, and mixed reality. State-of-the-art methods directly learn image-based embedding space by leveraging powerful deep convolutional neural networks. While being straightforward, their results are far from satisfactory, the aligned videos exhibit severe temporal discontinuity without additional post-processing steps. The recent advancements in human body and hand pose estimation in the wild promise new ways of addressing the task of human action alignment in videos. In this work, based on off-the-shelf human pose estimators, we propose a novel context-aware self-supervised learning architecture to align sequences of actions. We name it CASA. Specifically, CASA employs self-attention and cross-attention mechanisms to incorporate the spatial and temporal context of human actions, which can solve the temporal discontinuity problem. Moreover, we introduce a self-supervised learning scheme that is empowered by novel 4D augmentation techniques for 3D skeleton representations. We systematically evaluate the key components of our method. Our experiments on three public datasets demonstrate CASA significantly improves phase progress and Kendall's Tau scores over the previous state-of-the-art methods.

关键词： Training computer vision Three-dimensional displays Pose estimation Self-supervised learning Transforms Transformers

来源：评论

学校读者我要写书评

暂无评论

Fast Approximate Karhunen-Loeve Transform for Three-Way Array Data 16

Fast Approximate Karhunen-Loeve Transform for Three-Way Arra...

引用

16th ieee International conference on computer vision (ICCV)

作者： Itoh, Hayato Imiya, Atsushi Sakai, Tomoya Nagoya Univ Chikusa Ku Furo Cho Nagoya Aichi 4648601 Japan Chiba Univ IMIT Inage Ku Yayoi Cho 1-33 Chiba 2638522 Japan Nagasaki Univ Bunkyo 1-14 Nagasaki 8528521 Japan

ISBN: (纸本)9781538610343

Organs, cells and microstructures in cells dealt with in biomedical image analysis are volumetric data. We are required to process and analyse these data as volumetric data without embedding into higher-dimensional vector space from the viewpoints of object oriented data analysis. Sampled values of volumetric data are expressed as three-way array data. Therefore, principal component analysis of multi-way data is an essential technique for subspace-based pattern recognition, data retrievals and data compression of volumetric data. For one-way array (the vector form) problem the discrete cosine transform matrix is a good relaxed solution of the eigenmatrix for principal component analysis. This algebraic property of principal component analysis, derives an approximate fast algorithm for PCA of three-way data arrays.

关键词： Tensile stress Principal component analysis Arrays pattern recognition Discrete cosine transforms Optimization

来源：评论

学校读者我要写书评

暂无评论

Deep Quantization: Encoding Convolutional Activations with Deep Generative Model 30

Deep Quantization: Encoding Convolutional Activations with D...

引用

30th ieee/CVF conference on computer vision and pattern recognition (CVPR)

作者： Qiu, Zhaofan Yao, Ting Mei, Tao Univ Sci & Technol China Hefei Anhui Peoples R China Microsoft Res Beijing Peoples R China

ISBN: (纸本)9781538604571

Deep convolutional neural networks (CNNs) have proven highly effective for visual recognition, where learning a universal representation from activations of convolutional layer plays a fundamental problem. In this paper, we present Fisher Vector encoding with Variational Auto-Encoder (FV-VAE), a novel deep architecture that quantizes the local activations of convolutional layer in a deep generative model, by training them in an end-to-end manner. To incorporate FV encoding strategy into deep generative models, we introduce Variational Auto-Encoder model, which steers a variational inference and learning in a neural network which can be straightforwardly optimized using standard stochastic gradient method. Different from the FV characterized by conventional generative models (e.g., Gaussian Mixture Model) which parsimoniously fit a discrete mixture model to data distribution, the proposed FV-VAE is more flexible to represent the natural property of data for better generalization. Extensive experiments are conducted on three public datasets, i.e., UCF101, ActivityNet, and CUB-200-2011 in the context of video action recognition and fine-grained image classification, respectively. Superior results are reported when compared to state-of-theart representations. Most remarkably, our proposed FVVAE achieves to-date the best published accuracy of 94.2% on UCF101.

关键词： Visualization Encoding computer architecture Training Quantization (signal) Computational modeling Optimization computer Architecture Computational modeling Visualization Functional training Variational Inference Training coding Neural network data distribution Image classification Mixture models Quantization

来源：评论

学校读者我要写书评

暂无评论

Object-specific figure-ground segregation

Object-specific figure-ground segregation

引用

2003 ieee computer society conference on computer vision and pattern recognition, CVPR 2003

作者： Yu, Stella X. Shi, Jianbo Robotics Institute Carnegie Mellon University Ctr. Neural Basis of Cognition Pittsburgh PA 15213-3890 United States Dept. of Comp. and Information Sci. University of Pennsylvania Philadelphia PA 19104-6389 United States

We consider the problem of segmenting an image into foreground and background, with foreground containing solely objects of interest known a priori. We propose an integration model that incorporates both edge detection and object part detection results. It consists of two parallel processes: low-level pixel grouping and high-level patch grouping. We seek a solution that optimizes a joint grouping criterion in a reduced space enforced by grouping correspondence between pixels and patches. Using spectral graph partitioning, we show that a near global optimum can be found by solving a constrained eigenvalue problem. We report promising experimental results on a dataset of 15 objects under clutter and occlusion.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

SIMBAR: Single Image-Based Scene Relighting For Effective Data Augmentation For Automated Driving vision Tasks

SIMBAR: Single Image-Based Scene Relighting For Effective Da...

引用

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

作者： Zhang, Xianling Tseng, Nathan Syed, Ameerah Bhasin, Rohan Jaipuria, Nikita Ford Greenfield Labs Palo Alto CA 94304 USA Univ Michigan Ann Arbor MI 48109 USA

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Real-world autonomous driving datasets comprise of images aggregated from different drives on the road. The ability to relight captured scenes to unseen lighting conditions, in a controllable manner, presents an opportunity to augment datasets with a richer variety of lighting conditions, similar to what would be encountered in the real-world. This paper presents a novel image-based relighting pipeline, SIMBAR, that can work with a single image as input. To the best of our knowledge, there is no prior work on scene relighting leveraging explicit geometric representations from a single image. We present qualitative comparisons with prior multi-view scene relighting baselines. To further validate and effectively quantify the benefit of leveraging SIMBAR for data augmentation for automated driving vision tasks, object detection and tracking experiments are conducted with a state-of-the-art method, a Multiple Object Tracking Accuracy (MOTA) of 93.3% is achieved with CenterTrack on SIMBAR-augmented KITTI - an impressive 9.0% relative improvement over the baseline MOTA of 85.6% with CenterTrack on original KITTI, both models trained from scratch and tested on Virtual KITTI. For more details and sample relit datasets, please visit our project website (https://***).

关键词： Geometry Three-dimensional displays Roads Pipelines Lighting Estimation Object detection

来源：评论

学校读者我要写书评

暂无评论

INTELLIGENT IMAGE INTERFACE TO 3D IMAGES WITH 3D IMAGE UNDERSTANDING AND PRESENTATION 11

INTELLIGENT IMAGE INTERFACE TO 3D IMAGES WITH 3D IMAGE UNDER...

引用

conference A: computer vision and Applications, at the 11th IAPR International conference on pattern recognition

作者： TORIWAKI, J NAGOYA UNIV FAC ENGNDEPT INFORMAT ENGNCHIKUSA KUNAGOYA 46401JAPAN

ISBN: (纸本)081862910X

We study a highly intelligent image interface which makes it possible to realize the human-computer communication using pictorial information flexibly as in human communication. The image interface should have functions of computer graphics and image pattern recognition/understanding since any kind of pictorial information may be used as media and messages. In the paper we functions of the image interface briefly, and a pilot model implemented with the computer-aided surgical planning system we developed. © 1992 ieee.

关键词： computer graphics

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 << < 468 469 470 471 472 473 474 475 476 477 > >>

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：