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4911-4920 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：

LiBRe: A Practical Bayesian Approach to Adversarial Detection

LiBRe: A Practical Bayesian Approach to Adversarial Detectio...

引用

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

作者： Deng, Zhijie Yang, Xiao Xu, Shizhen Su, Hang Zhu, Jun Tsinghua Univ Dept Comp Sci & Tech BNRist Ctr Inst AITsinghua Bosch Joint ML CtrTHBI Lab Beijing 100084 Peoples R China RealAI Beijing Peoples R China

ISBN: (纸本)9781665445092

Despite their appealing flexibility, deep neural networks (DNNs) are vulnerable against adversarial examples. Various adversarial defense strategies have been proposed to resolve this problem, but they typically demonstrate restricted practicability owing to unsurmountable compromise on universality, effectiveness, or efficiency. In this work, we propose a more practical approach, Lightweight Bayesian Refinement (LiBRe), in the spirit of leveraging Bayesian neural networks (BNNs) for adversarial detection. Empowered by the task and attack agnostic modeling under Bayes principle, LiBRe can endow a variety of pre-trained task-dependent DNNs with the ability of defending heterogeneous adversarial attacks at a low cost. We develop and integrate advanced learning techniques to make LiBRe appropriate for adversarial detection. Concretely, we build the few-layer deep ensemble variational and adopt the pre-training & fine-tuning workflow to boost the effectiveness and efficiency of LiBRe. We further provide a novel insight to realise adversarial detection-oriented uncertainty quantification without inefficiently crafting adversarial examples during training. Extensive empirical studies covering a wide range of scenarios verify the practicability of LiBRe. We also conduct thorough ablation studies to evidence the superiority of our modeling and learning strategies.(1)

关键词： Training Deep learning Costs Uncertainty Neural networks Bayes methods pattern recognition

来源：评论

学校读者我要写书评

暂无评论

DSC-PoseNet: Learning 6DoF Object Pose Estimation via Dual-scale Consistency

DSC-PoseNet: Learning 6DoF Object Pose Estimation via Dual-s...

引用

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

作者： Yang, Zongxin Yu, Xin Yang, Yi Baidu Res Beijing Peoples R China Univ Technol Sydney ReLER Sydney NSW Australia

ISBN: (纸本)9781665445092

Compared to 2D object bounding-box labeling, it is very difficult for humans to annotate 3D object poses, especially when depth images of scenes are unavailable. This paper investigates whether we can estimate the object poses effectively when only RGB images and 2D object annotations are given. To this end, we present a two-step pose estimation framework to attain 6DoF object poses from 2D object bounding-boxes. In the first step, the framework learns to segment objects from real and synthetic data in a weakly-supervised fashion, and the segmentation masks will act as a prior for pose estimation. In the second step, we design a dual-scale pose estimation network, namely DSC-PoseNet, to predict object poses by employing a differential renderer. To be specific, our DSC-PoseNet firstly predicts object poses in the original image scale by comparing the segmentation masks and the rendered visible object masks. Then, we resize object regions to a fixed scale to estimate poses once again. In this fashion, we eliminate large scale variations and focus on rotation estimation, thus facilitating pose estimation. Moreover, we exploit the initial pose estimation to generate pseudo ground-truth to train our DSC-PoseNet in a self-supervised manner. The estimation results in these two scales are ensembled as our final pose estimation. Extensive experiments on widely-used benchmarks demonstrate that our method outperforms state-of-the-art models trained on synthetic data by a large margin and even is on par with several fully-supervised methods.

关键词： Training Image segmentation computer vision Three-dimensional displays Annotations Pose estimation Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Look Before You Leap: Learning Landmark Features for One-Stage Visual Grounding

Look Before You Leap: Learning Landmark Features for One-Sta...

引用

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

作者： Huang, Binbin Lian, Dongze Luo, Weixin Gao, Shenghua ShanghaiTech Univ Shanghai Peoples R China Shanghai Engn Res Ctr Intelligent Vis & Imaging Shanghai Peoples R China

ISBN: (纸本)9781665445092

An LBYL ('Look Before You Leap') Network is proposed for end-to-end trainable one-stage visual grounding. The idea behind LBYL-Net is intuitive and straightforward: we follow a language's description to localize the target object based on its relative spatial relation to 'Landmarks', which is characterized by some spatial positional words and some descriptive words about the object. The core of our LBYL-Net is a landmark feature convolution module that transmits the visual features with the guidance of linguistic description along with different directions. Consequently, such a module encodes the relative spatial positional relations between the current object and its context. Then we combine the contextual information from the landmark feature convolution module with the target's visual features for grounding. To make this landmark feature convolution light-weight, we introduce a dynamic programming algorithm (termed dynamic max pooling) with low complexity to extract the landmark feature. Thanks to the landmark feature convolution module, we mimic the human behavior of 'Look Before You Leap' to design an LBYL-Net, which takes full consideration of contextual information. Extensive experiments show our method's effectiveness in four grounding datasets. Specifically, our LBYL-Net outperforms all state-of-the-art two-stage and one-stage methods on ReferitGame. On RefCOCO and RefCOCO+, Our LBYL-Net also achieves comparable results or even better results than existing one-stage methods.

关键词： Visualization computer vision Grounding Convolution Heuristic algorithms Computational modeling Linguistics

来源：评论

学校读者我要写书评

暂无评论

Improving Image recognition by Retrieving from Web-Scale Image-Text Data

Improving Image Recognition by Retrieving from Web-Scale Ima...

引用

conference on computer vision and pattern recognition (cvpr)

作者： Ahmet Iscen Alireza Fathi Cordelia Schmid Google Research

Retrieval augmented models are becoming increasingly popular for computer vision tasks after their recent success in NLP problems. The goal is to enhance the recognition capabilities of the model by retrieving similar examples for the visual input from an external memory set. In this work, we introduce an attention-based memory module, which learns the importance of each retrieved example from the memory. Compared to existing approaches, our method removes the influence of the irrelevant retrieved examples, and retains those that are beneficial to the input query. We also thoroughly study various ways of constructing the memory dataset. Our experiments show the benefit of using a massive-scale memory dataset of 1B image-text pairs, and demonstrate the performance of different memory representations. We evaluate our method in three different classification tasks, namely long-tailed recognition, learning with noisy labels, and fine-grained classification, and show that it achieves state-of-the-art accuracies in ImageNet-LT, Places-LT and Webvision datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Farewell to Mutual Information: Variational Distillation for Cross-Modal Person Re-Identification

Farewell to Mutual Information: Variational Distillation for...

引用

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

作者： Tian, Xudong Zhang, Zhizhong Lin, Shaohui Qu, Yanyun Xie, Yuan Ma, Lizhuang East China Normal Univ Shanghai Peoples R China Xiamen Univ Xiamen Peoples R China Shanghai Jiao Tong Univ Shanghai Peoples R China

ISBN: (纸本)9781665445092

The Information Bottleneck (IB) provides an information theoretic principle for representation learning, by retaining all information relevant for predicting label while minimizing the redundancy. Though IB principle has been applied to a wide range of applications, its optimization remains a challenging problem which heavily relies on the accurate estimation of mutual information. In this paper, we present a new strategy, Variational Self-Distillation (VSD), which provides a scalable, flexible and analytic solution to essentially fitting the mutual information but without explicitly estimating it. Under rigorously theoretical guarantee, VSD enables the IB to grasp the intrinsic correlation between representation and label for supervised training. Furthermore, by extending VSD to multi-view learning, we introduce two other strategies, Variational Cross-Distillation (VCD) and Variational Mutual-Learning (VML), which significantly improve the robustness of representation to viewchanges by eliminating view-specific and task-irrelevant information. To verify our theoretically grounded strategies, we apply our approaches to cross-modal person Re-ID, and conduct extensive experiments, where the superior performance against state-of-the-art methods are demonstrated. Our intriguing findings highlight the need to rethink the way to estimate mutual information.

关键词： Training Correlation Fitting Redundancy Estimation Robustness pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Interventional Video Grounding with Dual Contrastive Learning

Interventional Video Grounding with Dual Contrastive Learnin...

引用

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

作者： Nan, Guoshun Qiao, Rui Xiao, Yao Liu, Jun Leng, Sicong Zhang, Hao Lu, Wei Singapore Univ Technol & Design StatNLP Res Grp Singapore Singapore Shanghai Jiao Tong Univ Shanghai Peoples R China Singapore Univ Technol & Design Informat Syst Technol & Design Singapore Singapore Nanyang Technol Univ Sch Comp Sci & Engn Singapore Singapore ASTAR Inst High Performance Comp Singapore Singapore

ISBN: (纸本)9781665445092

Video grounding aims to localize a moment from an untrimmed video for a given textual query. Existing approaches focus more on the alignment of visual and language stimuli with various likelihood-based matching or regression strategies, i.e., P(Y vertical bar X). Consequently, these models may suffer from spurious correlations between the language and video features due to the selection bias of the dataset. 1) To uncover the causality behind the model and data, we first propose a novel paradigm from the perspective of the causal inference, i.e., interventional video grounding (IVG) that leverages backdoor adjustment to deconfound the selection bias based on structured causal model (SCM) and do-calculus P(Y vertical bar do(X)). Then, we present a simple yet effective method to approximate the unobserved confounder as it cannot be directly sampled from the dataset. 2) Meanwhile, we introduce a dual contrastive learning approach (DCL) to better align the text and video by maximizing the mutual information (MI) between query and video clips, and the MI between start/end frames of a target moment and the others within a video to learn more informative visual representations. Experiments on three standard benchmarks show the effectiveness of our approaches.

关键词： Visualization Correlation Grounding Benchmark testing Knowledge discovery Data models pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Recognizing Rigid patterns of Unlabeled Point Clouds by Complete and Continuous Isometry Invariants with no False Negatives and no False Positives

Recognizing Rigid Patterns of Unlabeled Point Clouds by Comp...

引用

conference on computer vision and pattern recognition (cvpr)

作者： Daniel Widdowson Vitaliy Kurlin Computer Science department University of Liverpool UK

Rigid structures such as cars or any other solid objects are often represented by finite clouds of unlabeled points. The most natural equivalence on these point clouds is rigid motion or isometry maintaining all inter-point distances. Rigid patterns of point clouds can be reliably compared only by complete isometry invariants that can also be called equivariant descriptors without false negatives (isometric clouds having different descriptions) and without false positives (non-isometric clouds with the same description). Noise and motion in data motivate a search for invariants that are continuous under perturbations of points in a suitable metric. We propose the first continuous and complete invariant of unlabeled clouds in any Euclidean space. For a fixed dimension, the new metric for this invariant is computable in a polynomial time in the number of points.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Not just Compete, but Collaborate: Local Image-to-Image Translation via Cooperative Mask Prediction

Not just Compete, but Collaborate: Local Image-to-Image Tran...

引用

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

作者： Kim, Daejin Khan, Mohammad Azam Choo, Jaegul Korea Adv Inst Sci & Technol Daejeon South Korea Dhaka Power Distribut Co Ltd Dhaka Bangladesh

ISBN: (纸本)9781665445092

Facial attribute editing aims to manipulate the image with the desired attribute while preserving the other details. Recently, generative adversarial networks along with the encoder-decoder architecture have been utilized for this task owing to their ability to create realistic images. However, the existing methods for the unpaired dataset cannot still preserve the attribute-irrelevant regions properly due to the absence of the ground truth image. This work proposes a novel, intuitive loss function called the CAM-consistency loss, which improves the consistency of an input image in image translation. While the existing cycle-consistency loss ensures that the image can be translated back, our approach makes the model further preserve the attribute-irrelevant regions even in a single translation to another domain by using the Grad-CAM output computed from the discriminator. Our CAM-consistency loss directly optimizes such a Grad-CAM output from the discriminator during training, in order to properly capture which local regions the generator should change while keeping the other regions unchanged. In this manner, our approach allows the generator and the discriminator to collaborate with each other to improve the image translation quality. In our experiments, we validate the effectiveness and versatility of our proposed CAM-consistency loss by applying it to several representative models for facial image editing, such as StarGAN, AttGAN, and STGAN.

关键词： Training computer vision Computational modeling computer architecture Predictive models Generative adversarial networks Generators

来源：评论

学校读者我要写书评

暂无评论

How and What to Learn: Taxonomizing Self-Supervised Learning for 3D Action recognition 22

How and What to Learn: Taxonomizing Self-Supervised Learning...

引用

22nd ieee/cvf Winter conference on Applications of computer vision (WACV)

作者： Ben Tanfous, Amor Zerroug, Aimen Linsley, Drew Serre, Thomas Toulouse Univ Artificial & Nat Intelligence Toulouse Inst Toulouse France Brown Univ Carney Inst Brain Sci Dept Cognit Linguist Psychol Sci Providence RI 02912 USA

ISBN: (纸本)9781665409155

There are two competing standards for self-supervised learning in action recognition from 3D skeletons. Su et al., 2020 [31] used an auto-encoder architecture and an image reconstruction objective function to achieve state-of-the-art performance on the NTU60 C-View benchmark. Rao et al., 2020 [23] used Contrastive learning in the latent space to achieve state-of-the-art performance on the NTU60 C-Sub benchmark. Here, we reconcile these disparate approaches by developing a taxonomy of self-supervised learning for action recognition. We observe that leading approaches generally use one of two types of objective functions: those that seek to reconstruct the input from a latent representation ("Attractive" learning) versus those that also try to maximize the representations distinctiveness ("Contrastive" learning). Independently, leading approaches also differ in how they implement these objective functions: there are those that optimize representations in the decoder output space and those which optimize representations in the network's latent space (encoder output). We find that combining these approaches leads to larger gains in performance and tolerance to transformation than is achievable by any individual method, leading to state-of-the-art performance on three standard action recognition datasets. We include links to our code and data.

关键词： Visualization Three-dimensional displays Systematics Taxonomy Supervised learning Benchmark testing Linear programming

来源：评论

学校读者我要写书评

暂无评论

Prototype Augmentation and Self-Supervision for Incremental Learning

Prototype Augmentation and Self-Supervision for Incremental ...

引用

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

作者： Zhu, Fei Zhang, Xu-Yao Wang, Chuang Yin, Fei Liu, Cheng-Lin Chinese Acad Sci Inst Automat NLPR Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China CAS Ctr Excellence Brain Sci & Intelligence Techn Beijing 100190 Peoples R China

ISBN: (纸本)9781665445092

Despite the impressive performance in many individual tasks, deep neural networks suffer from catastrophic forgetting when learning new tasks incrementally. Recently, various incremental learning methods have been proposed, and some approaches achieved acceptable performance relying on stored data or complex generative models. However, storing data from previous tasks is limited by memory or privacy issues, and generative models are usually unstable and inefficient in training. In this paper, we propose a simple non-exemplar based method named PASS, to address the catastrophic forgetting problem in incremental learning. On the one hand, we propose to memorize one class-representative prototype for each old class and adopt prototype augmentation (protoAug) in the deep feature space to maintain the decision boundary of previous tasks. On the other hand, we employ self:supervised learning (SSL) to learn more generalizable and transferable features for other tasks, which demonstrates the effectiveness of SSL in incremental learning. Experimental results on benchmark datasets show that our approach significantly outperforms non-exemplar based methods, and achieves comparable performance compared to exemplar based approaches.

关键词： Training Learning systems Deep learning Data privacy computer vision Computational modeling Prototypes

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 << < 488 489 490 491 492 493 494 495 496 497 > >>

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：