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

11,133 篇 会议
8 篇 期刊文献

馆藏范围

11,141 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

7,837 篇 工学
- 7,396 篇 计算机科学与技术...
- 804 篇 机械工程
- 426 篇 软件工程
- 390 篇 电气工程
- 240 篇 控制科学与工程
- 99 篇 光学工程
- 53 篇 生物工程
- 37 篇 信息与通信工程
- 13 篇 生物医学工程（可授...
- 12 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
- 7 篇 电子科学与技术（可...
- 4 篇 环境科学与工程（可...
3,070 篇 医学
- 3,068 篇 临床医学
- 6 篇 基础医学(可授医学...
- 5 篇 特种医学
- 4 篇 公共卫生与预防医...
349 篇 理学
- 200 篇 系统科学
- 107 篇 物理学
- 55 篇 生物学
- 31 篇 数学
- 15 篇 化学
- 14 篇 统计学（可授理学、...
34 篇 管理学
- 19 篇 管理科学与工程(可...
- 16 篇 图书情报与档案管...
- 11 篇 工商管理
6 篇 法学
- 6 篇 社会学
6 篇 农学
- 6 篇 作物学
5 篇 经济学
- 5 篇 应用经济学
1 篇 军事学

主题

5,441 篇 computer vision
2,546 篇 training
2,108 篇 pattern recognit...
1,640 篇 computational mo...
1,455 篇 visualization
1,311 篇 three-dimensiona...
1,078 篇 semantics
985 篇 codes
974 篇 benchmark testin...
917 篇 computer archite...
879 篇 deep learning
765 篇 task analysis
691 篇 feature extracti...
570 篇 conferences
530 篇 face recognition
523 篇 neural networks
511 篇 transformers
474 篇 object detection
469 篇 image segmentati...
451 篇 cameras

机构

169 篇 univ sci & techn...
143 篇 univ chinese aca...
143 篇 tsinghua univ pe...
142 篇 carnegie mellon ...
133 篇 chinese univ hon...
120 篇 peng cheng lab p...
105 篇 zhejiang univ pe...
94 篇 sensetime res pe...
93 篇 swiss fed inst t...
88 篇 shanghai ai lab ...
88 篇 tsinghua univers...
84 篇 stanford univ st...
82 篇 shanghai jiao to...
79 篇 zhejiang univers...
76 篇 alibaba grp peop...
76 篇 univ hong kong p...
74 篇 peng cheng labor...
74 篇 australian natl ...
73 篇 tech univ munich...
71 篇 university of sc...

作者

61 篇 timofte radu
60 篇 van gool luc
50 篇 zhang lei
43 篇 yang yi
36 篇 tao dacheng
35 篇 loy chen change
31 篇 liu yang
30 篇 zhou jie
30 篇 tian qi
30 篇 sun jian
29 篇 zha zheng-jun
28 篇 chen chen
27 篇 qi tian
26 篇 vasconcelos nuno
26 篇 boxin shi
25 篇 li xin
25 篇 pollefeys marc
24 篇 liu xiaoming
24 篇 zheng wei-shi
24 篇 luo ping

语言

11,131 篇 英文
10 篇 其他

检索条件"任意字段=2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022"

共 11141 条记录，以下是61-70 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：

Incremental Learning in Semantic Segmentation from Image Labels

Incremental Learning in Semantic Segmentation from Image Lab...

引用

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

作者： Cermelli, Fabio Fontanel, Dario Tavera, Antonio Ciccone, Marco Caputo, Barbara Politecn Torino Turin Italy Italian Inst Technol Genoa Italy

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Although existing semantic segmentation approaches achieve impressive results, they still struggle to update their models incrementally as new categories are uncovered. Furthermore, pixel-by-pixel annotations are expensive and time-consuming. This paper proposes a novel framework for Weakly Incremental Learning for Semantic Segmentation, that aims at learning to segment new classes from cheap and largely available image-level labels. As opposed to existing approaches, that need to generate pseudolabels offline, we use a localizes, trained with image-level labels and regularized by the segmentation model, to obtain pseudo-supervision online and update the model incrementally. We cope with the inherent noise in the process by using soft-labels generated by the localizes. We demonstrate the effectiveness of our approach on the Pascal VOC and COCO datasets, outperforming offline weakly-supervised methods and obtaining results comparable with incremental learning methods with full supervision.(1)

关键词： Learning systems Location awareness Image segmentation computer vision Protocols Annotations Semantics

来源：评论

学校读者我要写书评

暂无评论

SASIC: Stereo Image Compression with Latent Shifts and Stereo Attention

SASIC: Stereo Image Compression with Latent Shifts and Stere...

引用

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

作者： Woedlinger, Matthias Kotera, Jan Xu, Jan Sablatnig, Robert TU Wien Vienna Austria Deep Render London England

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

We propose a learned method for stereo image compression that leverages the similarity of the left and right images in a stereo pair due to overlapping fields of view. The left image is compressed by a learned compression method based on an autoencoder with a hyperprior entropy model. The right image uses this information from the previously encoded left image in both the encoding and decoding stages. In particular, for the right image, we encode only the residual of its latent representation to the optimally shifted latent of the left image. On top of that, we also employ a stereo attention module to connect left and right images during decoding. The performance of the proposed method is evaluated on two benchmark stereo image datasets (Cityscapes and InStereo2K) and outperforms previous stereo image compression methods while being significantly smaller in model size.

关键词： computer vision Image coding Codes Computational modeling Bit rate Performance gain Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

V-Doc : Visual questions answers with Documents

V-Doc : Visual questions answers with Documents

引用

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

作者： Ding, Yihao Huang, Zhe Wang, Runlin Zhang, Yanhang Chen, Xianru Ma, Yuzhong Chung, Hyunsuk Han, Soyeon Caren Univ Sydney Sydney NSW Australia FortifyEdge Cambridge MA USA

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

We propose V-Doc, a question-answering tool using document images and PDF, mainly for researchers and general non-deep learning experts looking to generate, process, and understand the document visual question answering tasks. The V-Doc supports generating and using both extractive and abstractive question-answer pairs using documents images. The extractive QA selects a subset of tokens or phrases from the document contents to predict the answers, while the abstractive QA recognises the language in the content and generates the answer based on the trained model. Both aspects are crucial to understanding the documents, especially in an image format. We include a detailed scenario of question generation for the abstractive QA task. V-Doc supports a wide range of datasets and models, and is highly extensible through a declarative, framework-agnostic platform.(1)

关键词： Deep learning Visualization computer vision Computational modeling Predictive models Portable document format Question answering (information retrieval)

来源：评论

学校读者我要写书评

暂无评论

SkinningNet: Two-Stream Graph Convolutional Neural Network for Skinning Prediction of Synthetic Characters

SkinningNet: Two-Stream Graph Convolutional Neural Network f...

引用

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

作者： Mosella-Montoro, Albert Ruiz-Hidalgo, Javier Univ Politecn Cataluna Barcelona Spain

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

This work presents SkinningNet, an end-to-end Two Stream Graph Neural Network architecture that computes skinning weights from an input mesh and its associated skeleton, without making any assumptions on shape class and structure of the provided mesh. Whereas previous methods pre-compute handcrafted features that relate the mesh and the skeleton or assume a fixed topology of the skeleton, the proposed method extracts this information in an end-to-end learnable fashion by jointly learning the best relationship between mesh vertices and skeleton joints. The proposed method exploits the benefits of the novel Multi-Aggregator Graph Convolution that combines the results of different aggregators during the summarizing step of the Message-Passing scheme, helping the operation to generalize for unseen topologies. Experimental results demonstrate the effectiveness of the contributions of our novel architecture, with SkinningNet outperforming current state-of-the-art alternatives.

关键词： Shape Network topology Machine vision computer architecture Feature extraction Skeleton Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Tencent-MVSE: A Large-Scale Benchmark Dataset for Multi-Modal Video Similarity Evaluation

Tencent-MVSE: A Large-Scale Benchmark Dataset for Multi-Moda...

引用

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

作者： Zeng, Zhaoyang Luo, Yongsheng Liu, Zhenhua Rao, Fengyun Li, Dian Guo, Weidong Wen, Zhen Tencent QQ Browser Lab Shenzhen Peoples R China

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Multi-modal video similarity evaluation is important for video recommendation systems such as video deduplication, relevance matching, ranking, and diversity control. However, there still lacks a benchmark dataset that can support supervised training and accurate evaluation. In this paper, we propose the Tencent-MVSE dataset, which is the first benchmark dataset for the multi-modal video similarity evaluation task. The Tencent-MVSE dataset contains video pairs similarity annotations, and diverse metadata including Chinese title, automatic speech recognition (ASR) text, as well as human-annotated categories/tags. We provide a simple baseline with a multi-modal Transformer architecture to perform supervised multi-modal video similarity evaluation. We also explore pre-training strategies to make use of the unpaired data. The whole dataset as well as our baseline will be released to promote the development of the multi-modal video similarity evaluation. The dataset has been released in https://***/.

关键词： Training computer vision Annotations computer architecture Benchmark testing Transformers pattern recognition

来源：评论

学校读者我要写书评

暂无评论

APES: Articulated Part Extraction from Sprite Sheets

APES: Articulated Part Extraction from Sprite Sheets

引用

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

作者： Xu, Zhan Fisher, Matthew Zhou, Yang Aneja, Deepali Dudhat, Rushikesh Yi, Li Kalogerakis, Evangelos Univ Massachusetts Amherst MA 01003 USA Adobe Res San Jose CA USA Tsinghua Univ Beijing Peoples R China

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Rigged puppets are one of the most prevalent representations to create 2D character animations. Creating these puppets requires partitioning characters into independently moving parts. In this work, we present a method to automatically identify such articulated parts from a small set of character poses shown in a sprite sheet, which is an illustration of the character that artists often draw before puppet creation. Our method is trained to infer articulated parts, e.g. head, torso and limbs, that can be reassembled to best reconstruct the given poses. Our results demonstrate significantly better performance than alternatives qualitatively and quantitatively. Our project page https://***/parts/includes our code and data.

关键词： Torso computer vision Codes Animation pattern recognition Sprites (computer)

来源：评论

学校读者我要写书评

暂无评论

VISCUIT: Visual Auditor for Bias in CNN Image Classifier

VISCUIT: Visual Auditor for Bias in CNN Image Classifier

引用

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

作者： Lee, Seongmin Hoffman, Judy Wang, Zijie J. Chau, Duen Horng (Polo) Georgia Inst Technol Atlanta GA 30332 USA

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

CNN image classifiers are widely used, thanks to their efficiency and accuracy However, they can suffer from biases that impede their practical applications. Most existing bias investigation techniques are either inapplicable to general image classification tasks or require significant user efforts in perusing all data subgroups to manually specify which data attributes to inspect. We present VISCUIT, an interactive visualization system that reveals how and why a CNN classifier is biased. VISCUIT visually summarizes the subgroups on which the classifier underperforms and helps users discover and characterize the cause of the underperformances by revealing image concepts responsible for activating neurons that contribute to misclassifications. VisCUIT runs in modern browsers and is opensource, allowing people to easily access and extend the tool to other model architectures and datasets. VISCUIT is available at the following public demo link: https://***/VisCUIT. A video demo is available at https://***/eNDbSyM4R_4.

关键词： Visualization computer vision Computational modeling Neurons Data visualization computer architecture Browsers

来源：评论

学校读者我要写书评

暂无评论

On the Road to Online Adaptation for Semantic Image Segmentation

On the Road to Online Adaptation for Semantic Image Segmenta...

引用

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

作者： Volpi, Riccardo De Jorge, Pau Larlus, Diane Csurka, Gabriela NAVER LABS Europe Meylan France Univ Oxford Oxford England

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

We propose a new problem formulation and a corresponding evaluation framework to advance research on unsupervised domain adaptation for semantic image segmentation. The overall goal is fostering the development of adaptive learning systems that will continuously learn, without supervision, in ever-changing environments. Typical protocols that study adaptation algorithms for segmentation models are limited to few domains, adaptation happens offline, and human intervention is generally required, at least to annotate data for hyper-parameter tuning. We argue that such constraints are incompatible with algorithms that can continuously adapt to different real-world situations. To address this, we propose a protocol where models need to learn online, from sequences of temporally correlated images, requiring continuous, frame-by-frame adaptation. We accompany this new protocol with a variety of baselines to tackle the proposed formulation, as well as an extensive analysis of their behaviors, which can serve as a starting point for future research.

关键词： Representation learning Image segmentation Adaptation models computer vision Protocols Roads Semantics

来源：评论

学校读者我要写书评

暂无评论

CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation

CMT-DeepLab: Clustering Mask Transformers for Panoptic Segme...

引用

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

作者： Yu, Qihang Wang, Huiyu Kim, Dahun Qiao, Siyuan Collins, Maxwell Zhu, Yukun Adam, Hartwig Yuille, Alan Chen, Liang-Chieh Johns Hopkins Univ Baltimore MD 21218 USA Korea Adv Inst Sci & Technol Daejeon South Korea Google Res Mountain View CA USA Google Mountain View CA 94043 USA

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

We propose Clustering Mask Transformer (CMT-DeepLab), a transformer-based framework for panoptic segmentation designed around clustering. It rethinks the existing transformer architectures used in segmentation and detection;CMT-DeepLab considers the object queries as cluster centers, which fill the role of grouping the pixels when applied to segmentation. The clustering is computed with an alternating procedure, by first assigning pixels to the clusters by their feature affinity, and then updating the cluster centers and pixel features. Together, these operations comprise the Clustering Mask Transformer (CMT) layer, which produces cross-attention that is denser and more consistent with the final segmentation task. CMT-DeepLab improves the performance over prior art significantly by 4.4% PQ, achieving a new state-of-the-art of 55.7% PQ on the COCO test-dev set.

关键词： computer vision Art computer architecture Transformers pattern recognition Task analysis

来源：评论

学校读者我要写书评

暂无评论

Enhancing Classifier Conservativeness and Robustness by Polynomiality

Enhancing Classifier Conservativeness and Robustness by Poly...

引用

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

作者： Wang, Ziqi Loog, Marco Delft Univ Technol Delft Netherlands Univ Copenhagen Copenhagen Denmark

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

We illustrate the detrimental effect, such as overconfident decisions, that exponential behavior can have in methods like classical LDA and logistic regression. We then show how polynomiality can remedy the situation. This, among others, leads purposefully to random-level performance in the tails, away from the bulk of the training data. A directly related, simple, yet important technical novelty we subsequently present is softRmax: a reasoned alternative to the standard softmax function employed in contemporary (deep) neural networks. It is derived through linking the standard softmax to Gaussian class-conditional models, as employed in LDA, and replacing those by a polynomial alternative. We show that two aspects of softRmax, conservativeness and inherent gradient regularization, lead to robustness against adversarial attacks without gradient obfuscation.

关键词： Deep learning computer vision Computational modeling Neural networks Training data Tail Robustness

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 << < 3 4 5 6 7 8 9 10 11 12 > >>

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：