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

19,438 篇 会议
46 篇 期刊文献
5 册 图书

馆藏范围

19,488 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

12,440 篇 工学
- 10,282 篇 计算机科学与技术...
- 2,395 篇 机械工程
- 2,007 篇 软件工程
- 813 篇 光学工程
- 531 篇 电气工程
- 419 篇 控制科学与工程
- 322 篇 信息与通信工程
- 210 篇 测绘科学与技术
- 80 篇 生物医学工程（可授...
- 73 篇 电子科学与技术（可...
- 70 篇 生物工程
- 60 篇 仪器科学与技术
- 38 篇 建筑学
- 36 篇 土木工程
- 33 篇 力学（可授工学、理...
- 31 篇 航空宇航科学与技...
- 26 篇 安全科学与工程
- 20 篇 材料科学与工程（可...
- 20 篇 交通运输工程
3,409 篇 医学
- 3,408 篇 临床医学
1,980 篇 理学
- 1,006 篇 数学
- 973 篇 物理学
- 359 篇 统计学（可授理学、...
- 336 篇 生物学
- 231 篇 系统科学
- 24 篇 化学
258 篇 管理学
- 138 篇 管理科学与工程(可...
- 122 篇 图书情报与档案管...
- 27 篇 工商管理
19 篇 法学
- 19 篇 社会学
14 篇 农学
8 篇 教育学
7 篇 经济学
3 篇 军事学
3 篇 艺术学

主题

7,893 篇 computer vision
2,727 篇 training
2,680 篇 pattern recognit...
1,760 篇 computational mo...
1,644 篇 visualization
1,410 篇 cameras
1,372 篇 three-dimensiona...
1,327 篇 shape
1,213 篇 face recognition
1,207 篇 image segmentati...
1,164 篇 feature extracti...
1,109 篇 robustness
1,087 篇 semantics
983 篇 layout
959 篇 object detection
949 篇 computer archite...
942 篇 benchmark testin...
931 篇 codes
902 篇 computer science
859 篇 deep learning

机构

174 篇 univ sci & techn...
161 篇 carnegie mellon ...
148 篇 univ chinese aca...
144 篇 chinese univ hon...
110 篇 microsoft resear...
106 篇 tsinghua univ pe...
103 篇 zhejiang univ pe...
99 篇 swiss fed inst t...
92 篇 tsinghua univers...
89 篇 microsoft res as...
88 篇 shanghai ai lab ...
81 篇 zhejiang univers...
76 篇 alibaba grp peop...
73 篇 university of sc...
73 篇 hong kong univ s...
72 篇 peking univ peop...
72 篇 university of ch...
68 篇 shanghai jiao to...
66 篇 univ oxford oxfo...
66 篇 shanghai jiao to...

作者

79 篇 van gool luc
70 篇 zhang lei
59 篇 timofte radu
48 篇 yang yi
47 篇 xiaoou tang
45 篇 luc van gool
43 篇 darrell trevor
43 篇 tian qi
42 篇 loy chen change
42 篇 sun jian
42 篇 li fei-fei
40 篇 qi tian
38 篇 li stan z.
36 篇 chen xilin
36 篇 torralba antonio
35 篇 vasconcelos nuno
35 篇 shan shiguang
35 篇 liu yang
34 篇 liu xiaoming
34 篇 tao dacheng

语言

19,484 篇 英文
2 篇 日文
2 篇 中文
1 篇 其他

检索条件"任意字段=IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2000"

共 19489 条记录，以下是4561-4570 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：

ID-Unet: Iterative Soft and Hard Deformation for View Synthesis

ID-Unet: Iterative Soft and Hard Deformation for View Synthe...

引用

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

作者： Yin, Mingyu Sun, Li Li, Qingli East China Normal Univ Shanghai Key Lab Multidimens Informat Proc Shanghai 200241 Peoples R China East China Normal Univ Key Lab Adv Theory & Applicat Stat & Data Sci Shanghai 200241 Peoples R China

ISBN: (纸本)9781665445092

View synthesis is usually done by an autoencoder, in which the encoder maps a source view image into a latent content code, and the decoder transforms it into a target view image according to the condition. However, the source contents are often not well kept in this setting, which leads to unnecessary changes during the view translation. Although adding skipped connections, like Unet, alleviates the problem, but it often causes the failure on the view conformity. This paper proposes a new architecture by performing the source-to-target deformation in an iterative way. Instead of simply incorporating the features from multiple layers of the encoder, we design soft and hard deformation modules, which warp the encoder features to the target view at different resolutions, and give results to the decoder to complement the details. Particularly, the current warping flow is not only used to align the feature of the same resolution, but also as an approximation to coarsely deform the high resolution feature. Then the residual flow is estimated and applied in the high resolution, so that the deformation is built up in the coarse-to-fine fashion. To better constrain the model, we synthesize a rough target view image based on the intermediate flows and their warped features. The extensive ablation studies and the final results on two different data sets show the effectiveness of the proposed model. https://***/Mingyuy/Iterative-view-synthesis.

关键词： Deformable models computer vision Image resolution Computational modeling Transforms Data models Decoding

来源：评论

学校读者我要写书评

暂无评论

Self Texture Transfer Networks for Low Bitrate Image Compression

Self Texture Transfer Networks for Low Bitrate Image Compres...

引用

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

作者： Iwai, Shoma Miyazaki, Tomo Sugaya, Yoshihiro Omachi, Shinichiro Tohoku Univ Grad Sch Engn Dept Commun Sendai Miyagi Japan

ISBN: (纸本)9781665448994

Lossy image compression causes a loss of texture, especially at low bitrate. To mitigate this problem, we propose a novel image compression method that utilizes a reference-based image super-resolution model. We use two image compression models and a self texture transfer model. The image compression models encode and decode a whole input image and selected reference patches. The reference patches are small but compressed with high quality. The self texture transfer model transfers the texture of reference patches into similar regions in the compressed image. The experimental results show that our method can reconstruct accurate texture by transferring the texture of reference patches.

关键词： computer vision Image coding conferences Bit rate Superresolution pattern recognition Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Adaptive Cross-Modal Prototypes for Cross-Domain Visual-Language Retrieval

Adaptive Cross-Modal Prototypes for Cross-Domain Visual-Lang...

引用

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

作者： Liu, Yang Chen, Qingchao Albanie, Samuel Peking Univ Wangxuan Inst Comp Technol Beijing Peoples R China Peking Univ Natl Inst Hlth Data Sci Beijing Peoples R China Univ Oxford Visual Geometry Grp Oxford England Univ Oxford Dept Engn Sci Oxford England

ISBN: (纸本)9781665445092

In this paper, we study the task of visual-text retrieval in the highly practical setting in which labelled visual data with paired text descriptions are available in one domain (the "source"), but only unlabelled visual data (without text descriptions) are available in the domain of interest (the "target"). We propose the ADAPTIVE CROSS-MODAL PROTOTYPES framework which seeks to enable target domain retrieval by learning cross-modal visual-text representations while minimising both uni-modal and cross-modal distribution shift across the source and target domains. Our approach is built upon two key ideas: first, we encode the inductive bias that the learned cross-modal representations should be compositional with respect to concepts in each modality-this is achieved through clustering pretrained uni-modal features across each domain and designing a careful regularisation scheme to preserve the resulting structure. Second, we employ mutual information maximisation between cross-modal representations in the source and target domains during learning-this provides a mechanism that preserves commonalities between the domains while discarding signal in each that cannot be inferred from the other. We showcase our approach for the task of cross-domain visual-text retrieval, outperforming existing approaches for both images and videos.

关键词： Visualization computer vision Prototypes pattern recognition Task analysis Mutual information Videos

来源：评论

学校读者我要写书评

暂无评论

BCNN: A Binary CNNWith All Matrix Ops Quantized To 1 Bit Precision

BCNN: A Binary CNNWith All Matrix Ops Quantized To 1 Bit Pre...

引用

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

作者： Redfern, Arthur J. Zhu, Lijun Newquist, Molly K. Texas Instruments Inc 12500 TI Blvd Dallas TX 75243 USA Georgia Inst Technol North Ave NW Atlanta GA 30332 USA

ISBN: (纸本)9781665448994

This paper describes a CNN where all CNN style 2D convolution operations that lower to matrix matrix multiplication are fully binary. The network is derived from a common building block structure that is consistent with a constructive proof outline showing that binary neural networks are universal function approximators. 71.24% top 1 accuracy on the 2012 ImageNet validation set was achieved with a 2 step training procedure and implementation strategies optimized for binary operands are provided.

关键词： Training computer vision Convolution conferences Neural networks Memory management Decoding

来源：评论

学校读者我要写书评

暂无评论

Video Prediction Recalling Long-term Motion Context via Memory Alignment Learning

Video Prediction Recalling Long-term Motion Context via Memo...

引用

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

作者： Lee, Sangmin Kim, Hak Gu Choi, Dae Hwi Kim, Hyung-Il Ro, Yong Man Korea Adv Inst Sci & Technol Image & Video Syst Lab Daejeon South Korea Ecole Polytech Fed Lausanne Lausanne Switzerland ETRI Daejeon South Korea

ISBN: (纸本)9781665445092

Our work addresses long-term motion context issues for predicting future frames. To predict the future precisely, it is required to capture which long-term motion context (e.g., walking or running) the input motion (e.g., leg movement) belongs to. The bottlenecks arising when dealing with the long-term motion context are: (i) how to predict the long-term motion context naturally matching input sequences with limited dynamics, (ii) how to predict the long-term motion context with high-dimensionality (e.g., complex motion). To address the issues, we propose novel motion context-aware video prediction. To solve the bottleneck (i), we introduce a long-term motion context memory (LMC-Memory) with memory alignment learning. The proposed memory alignment learning enables to store long-term motion contexts into the memory and to match them with sequences including limited dynamics. As a result, the long-term context can be recalled from the limited input sequence. In addition, to resolve the bottleneck (ii), we propose memory query decomposition to store local motion context (i.e., low-dimensional dynamics) and recall the suitable local context for each local part of the input individually. It enables to boost the alignment effects of the memory. Experimental results show that the proposed method outperforms other sophisticated RNN-based methods, especially in long-term condition. Further, we validate the effectiveness of the proposed network designs by conducting ablation studies and memory feature analysis. The source code of this work is available(dagger).

关键词： Legged locomotion computer vision Codes Impedance matching Dynamics Training data pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Rectification-based Knowledge Retention for Continual Learning

Rectification-based Knowledge Retention for Continual Learni...

引用

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

作者： Singh, Pravendra Mazumder, Pratik Rai, Piyush Namboodiri, Vinay P. IIT Kanpur Kanpur Uttar Pradesh India Univ Bath Bath Avon England

ISBN: (纸本)9781665445092

Deep learning models suffer from catastrophic forgetting when trained in an incremental learning setting. In this work, we propose a novel approach to address the task incremental learning problem, which involves training a model on new tasks that arrive in an incremental manner. The task incremental learning problem becomes even more challenging when the test set contains classes that are not part of the train set, i.e., a task incremental generalized zero-shot learning problem. Our approach can be used in both the zero-shot and non zero-shot task incremental learning settings. Our proposed method uses weight rectifications and affine transformations in order to adapt the model to different tasks that arrive sequentially. Specifically, we adapt the network weights to work for new tasks by "rectifying" the weights learned from the previous task. We learn these weight rectifications using very few parameters. We additionally learn affine transformations on the outputs generated by the network in order to better adapt them for the new task. We perform experiments on several datasets in both zero-shot and non zero-shot task incremental learning settings and empirically show that our approach achieves state-of-the-art results. Specifically, our approach outperforms the state-of-the-art non zero-shot task incremental learning method by over 5% on the CIFAR-100 dataset. Our approach also significantly outperforms the state-of-the-art task incremental generalized zero-shot learning method by absolute margins of 6.91% and 6.33% for the AWA1 and CUB datasets, respectively. We validate our approach using various ablation studies.

关键词： Learning systems Training Deep learning computer vision Adaptation models pattern recognition Task analysis

来源：评论

学校读者我要写书评

暂无评论

Embracing Uncertainty: Decoupling and De-bias for Robust Temporal Grounding

Embracing Uncertainty: Decoupling and De-bias for Robust Tem...

引用

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

作者： Zhou, Hao Zhang, Chongyang Luo, Yan Chen, Yanjun Hu, Chuanping Shanghai Jiao Tong Univ Sch Elect Informat & Elect Engn Shanghai Peoples R China Shanghai Jiao Tong Univ AI Inst MoE Key Lab Artificial Intelligence Shanghai Peoples R China Zhengzhou Univ Zhengzhou Peoples R China

ISBN: (纸本)9781665445092

Temporal grounding aims to localize temporal boundaries within untrimmed videos by language queries, but it faces the challenge of two types of inevitable human uncertainties: query uncertainty and label uncertainty. The two uncertainties stem from human subjectivity, leading to limited generalization ability of temporal grounding. In this work, we propose a novel DeNet (Decoupling and Debias) to embrace human uncertainty: Decoupling - We explicitly disentangle each query into a relation feature and a modified feature. The relation feature, which is mainly based on skeleton-like words (including nouns and verbs), aims to extract basic and consistent information in the presence of query uncertainty. Meanwhile, modified feature assigned with style-like words (including adjectives, adverbs, etc) represents the subjective information, and thus brings personalized predictions;De-bias - We propose a de-bias mechanism to generate diverse predictions, aim to alleviate the bias caused by single-style annotations in the presence of label uncertainty. Moreover, we put forward new multi-label metrics to diversify the performance evaluation. Extensive experiments show that our approach is more effective and robust than state-of-the-arts on Charades-STA and ActivityNet Captions datasets.

关键词： Performance evaluation computer vision Uncertainty Grounding Annotations Feature extraction Robustness

来源：评论

学校读者我要写书评

暂无评论

StEP: Style-based Encoder Pre-training for Multi-modal Image Synthesis

StEP: Style-based Encoder Pre-training for Multi-modal Image...

引用

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

作者： Meshry, Moustafa Ren, Yixuan Davis, Larry S. Shrivastava, Abhinav Univ Maryland College Pk MD 20742 USA

ISBN: (纸本)9781665445092

We propose a novel approach for multi-modal Image-to-image (I2I) translation. To tackle the one-to-many relationship between input and output domains, previous works use complex training objectives to learn a latent embedding, jointly with the generator, that models the variability of the output domain. In contrast, we directly model the style variability of images, independent of the image synthesis task. Specifically, we pre-train a generic style encoder using a novel proxy task to learn an embedding of images, from arbitrary domains, into a low-dimensional style latent space. The learned latent space introduces several advantages over previous traditional approaches to multi-modal I2I translation. First, it is not dependent on the target dataset, and generalizes well across multiple domains. Second, it learns a more powerful and expressive latent space, which improves the fidelity of style capture and transfer. The proposed style pre-training also simplifies the training objective and speeds up the training significantly. Furthermore, we provide a detailed study of the contribution of different loss terms to the task of multi-modal I2I translation, and propose a simple alternative to VAEs to enable sampling from unconstrained latent spaces. Finally, we achieve state-of-the-art results on six challenging benchmarks with a simple training objective that includes only a GAN loss and a reconstruction loss.

关键词： Training computer vision Codes Image synthesis Benchmark testing Generative adversarial networks Generators

来源：评论

学校读者我要写书评

暂无评论

Roses are Red, Violets are Blue... But Should VQA expect Them To?

Roses are Red, Violets are Blue... But Should VQA expect The...

引用

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

作者： Kervadec, Corentin Antipov, Grigory Baccouche, Moez Wolf, Christian Cesson Seyigne Orange France INSA Lyon LIRIS UMR CNRS 5205 Lyon France

ISBN: (纸本)9781665445092

Models for Visual Question Answering (VQA) are notorious for their tendency to rely on dataset biases, as the large and unbalanced diversity of questions and concepts involved and tends to prevent models from learning to "reason", leading them to perform "educated guesses" instead. In this paper, we claim that the standard evaluation metric, which consists in measuring the overall in-domain accuracy, is misleading. Since questions and concepts are unbalanced, this tends to favor models which exploit subtle training set statistics. Alternatively, naively introducing artificial distribution shifts between train and test splits is also not completely satisfying. First, the shifts do not reflect real-world tendencies, resulting in unsuitable models;second, since the shifts are handcrafted, trained models are specifically designed for this particular setting, and do not generalize to other configurations. We propose the GQAOOD benchmark designed to overcome these concerns: we measure and compare accuracy over both rare and frequent question-answer pairs, and argue that the former is better suited to the evaluation of reasoning abilities, which we experimentally validate with models trained to more or less exploit biases. In a large-scale study involving 7 VQA models and 3 bias reduction techniques, we also experimentally demonstrate that these models fail to address questions involving infrequent concepts and provide recommendations for future directions of research.

关键词： Training Measurement Visualization computer vision Computational modeling Benchmark testing Knowledge discovery

来源：评论

学校读者我要写书评

暂无评论

Neural Reprojection Error: Merging Feature Learning and Camera Pose Estimation

Neural Reprojection Error: Merging Feature Learning and Came...

引用

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

作者： Germain, Hugo Lepetit, Vincent Bourmaud, Guillaume Univ Gustave Eiffel Ecole Ponts LIGM CNRS Marne La Vallee France Univ Bordeaux IMS Bordeaux INP CNRS Bordeaux France

ISBN: (纸本)9781665445092

Absolute camera pose estimation is usually addressed by sequentially solving two distinct subproblems: First a feature matching problem that seeks to establish putative 2D-3D correspondences, and then a Perspective-n-Point problem that minimizes, w.r.t. the camera pose, the sum of so-called Reprojection Errors (RE). We argue that generating putative 2D-3D correspondences 1) leads to an important loss of information that needs to be compensated as far as possible, within RE, through the choice of a robust loss and the tuning of its hyperparameters and 2) may lead to an RE that conveys erroneous data to the pose estimator. In this paper, we introduce the Neural Reprojection Error (NRE) as a substitute for RE. NRE allows to rethink the camera pose estimation problem by merging it with the feature learning problem, hence leveraging richer information than 2D-3D correspondences and eliminating the need for choosing a robust loss and its hyperparameters. Thus NRE can be used as training loss to learn image descriptors tailored for pose estimation. We also propose a coarse-to-fine optimization method able to very efficiently minimize a sum of NRE terms w.r.t. the camera pose. We experimentally demonstrate that NRE is a good substitute for RE as it significantly improves both the robustness and the accuracy of the camera pose estimate while being computationally and memory highly efficient. From a broader point of view, we believe this new way of merging deep learning and 3D geometry may be useful in other computer vision applications.

关键词： Geometry Deep learning computer vision Three-dimensional displays Pose estimation Merging Memory management

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 << < 453 454 455 456 457 458 459 460 461 462 > >>

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：