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

6,639 篇 会议
34 篇 期刊文献
5 册 图书

馆藏范围

6,677 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

3,950 篇 工学
- 3,725 篇 计算机科学与技术...
- 1,476 篇 软件工程
- 807 篇 光学工程
- 323 篇 信息与通信工程
- 240 篇 控制科学与工程
- 206 篇 机械工程
- 169 篇 电气工程
- 85 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
- 65 篇 仪器科学与技术
- 38 篇 建筑学
- 36 篇 土木工程
- 34 篇 力学（可授工学、理...
- 32 篇 航空宇航科学与技...
- 29 篇 安全科学与工程
- 23 篇 化学工程与技术
- 21 篇 材料科学与工程（可...
1,498 篇 理学
- 969 篇 物理学
- 929 篇 数学
- 369 篇 统计学（可授理学、...
- 136 篇 生物学
- 40 篇 系统科学
- 26 篇 化学
210 篇 医学
- 210 篇 临床医学
- 23 篇 基础医学(可授医学...
165 篇 管理学
- 123 篇 图书情报与档案管...
- 44 篇 管理科学与工程(可...
- 29 篇 工商管理
21 篇 法学
- 21 篇 社会学
10 篇 农学
9 篇 教育学
6 篇 经济学
2 篇 军事学
1 篇 艺术学

主题

2,364 篇 computer vision
848 篇 pattern recognit...
663 篇 cameras
634 篇 computer science
592 篇 face recognition
558 篇 layout
541 篇 conferences
527 篇 image segmentati...
514 篇 shape
454 篇 object recogniti...
453 篇 robustness
394 篇 humans
339 篇 feature extracti...
324 篇 training
305 篇 object detection
263 篇 image recognitio...
260 篇 application soft...
249 篇 lighting
248 篇 computational mo...
238 篇 image reconstruc...

机构

44 篇 microsoft resear...
27 篇 department of co...
21 篇 swiss fed inst t...
21 篇 school of comput...
21 篇 carnegie mellon ...
20 篇 department of co...
19 篇 swiss fed inst t...
18 篇 department of co...
17 篇 department of in...
17 篇 the robotics ins...
17 篇 institute of com...
16 篇 univ sci & techn...
16 篇 robotics institu...
15 篇 tsinghua univ pe...
14 篇 department of el...
14 篇 center for autom...
14 篇 school of comput...
14 篇 school of comput...
13 篇 univ maryland co...
13 篇 microsoft resear...

作者

39 篇 timofte radu
28 篇 s.k. nayar
25 篇 huang thomas s.
24 篇 xiaoou tang
22 篇 t. kanade
20 篇 chellappa rama
20 篇 t.s. huang
19 篇 van gool luc
19 篇 nayar shree k.
19 篇 t. darrell
17 篇 a.k. jain
17 篇 a. zisserman
17 篇 heung-yeung shum
17 篇 jain anil k.
17 篇 zisserman andrew
16 篇 g. healey
16 篇 torralba antonio
16 篇 l. van gool
15 篇 ying wu
15 篇 m. shah

语言

6,668 篇 英文
8 篇 中文
2 篇 其他

检索条件"任意字段=2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2003"

共 6678 条记录，以下是431-440 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：

Continual Learning with Transformers for Image Classification

Continual Learning with Transformers for Image Classificatio...

引用

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

作者： Ermis, Beyza Zappella, Giovanni Wistuba, Martin Rawal, Aditya Archambeau, Cedric AWS Berlin Germany AWS Santa Clara CA USA

ISBN: (纸本)9781665487399

In many real-world scenarios, data to train machine learning models become available over time. However, neural network models struggle to continually learn new concepts without forgetting what has been learnt in the past. This phenomenon is known as catastrophic forgetting and it is often difficult to prevent due to practical constraints, such as the amount of data that can be stored or the limited computation sources that can be used. Moreover, training large neural networks, such as Transformers, from scratch is very costly and requires a vast amount of training data, which might not be available in the application domain of interest. A recent trend indicates that dynamic architectures based on an expansion of the parameters can reduce catastrophic forgetting efficiently in continual learning, but this needs complex tuning to balance the growing number of parameters and barely share any information across tasks. As a result, they struggle to scale to a large number of tasks without significant overhead. In this paper, we validate in the computer vision domain a recent solution called Adaptive Distillation of Adapters (ADA), which is developed to perform continual learning using pre-trained Transformers and Adapters on text classification tasks. We empirically demonstrate on different classification tasks that this method maintains a good predictive performance without retraining the model or increasing the number of model parameters over the time. Besides it is significantly faster at inference time compared to the state-of-the-art methods.

关键词： Training computer vision Adaptation models Computational modeling Neural networks Training data Predictive models

来源：评论

学校读者我要写书评

暂无评论

Exploring Robustness Connection between Artificial and Natural Adversarial Examples

Exploring Robustness Connection between Artificial and Natur...

引用

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

作者： Agarwal, Akshay Ratha, Nalini Vatsa, Mayank Singh, Richa Buffalo Buffalo NY 14260 USA IIT Jodhpur Jodhpur Rajasthan India

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Although recent deep neural network algorithm has shown tremendous success in several computer vision tasks, their vulnerability against minute adversarial perturbations has raised a serious concern. In the early days of crafting these adversarial examples, artificial noises are optimized through the network and added in the images to decrease the confidence of the classifiers against the true class. However, recent efforts are showcasing the presence of natural adversarial examples which can also be effectively used to fool the deep neural networks with high confidence. In this paper, for the first time, we have raised the question that whether there is any robustness connection between artificial and natural adversarial examples. The possible robustness connection between natural and artificial adversarial examples is studied in the form that whether an adversarial example detector trained on artificial examples can detect the natural adversarial examples. We have analyzed several deep neural networks for the possible detection of artificial and natural adversarial examples in seen and unseen settings to set up a robust connection. The extensive experimental results reveal several interesting insights to defend the deep classifiers whether vulnerable against natural or artificially perturbed examples. We believe these findings can pave a way for the development of unified resiliency because defense against one attack is not sufficient for real-world use cases.

关键词： Deep learning computer vision Neural networks Semantics Transformers Robustness Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Doppelganger Saliency: Towards More Ethical Person Re-Identification

Doppelganger Saliency: Towards More Ethical Person Re-Identi...

引用

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

作者： RichardWebster, Brandon Hu, Brian Fieldhouse, Keith Hoogs, Anthony Kitware Inc 1712 Route 9Suite 300 Clifton Pk NY 12065 USA

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Modern surveillance systems have become increasingly dependent on artificial intelligence to provide actionable information for real-time decision making. A critical question relates to how these systems handle difficult ethical dilemmas, such as the re-identification of similar looking individuals. Potential misidentification of individuals can have severe negative consequences, as evidenced by recent headlines of individuals who were wrongly targeted for crimes they did not commit based on false matches. A computer vision-based saliency algorithm is proposed to help identify pixel-level differences in pairs of images containing visually similar individuals, which we term "doppelgangers." The computed saliency maps can alert human users of the presence of doppelg angers and provide important visual evidence to reduce the potential of false matches in these high-stakes situations. We show both qualitative and quantitative saliency results on doppelg angers found in a video-based person re-identification dataset (MARS) using three different state-of-the-art models. Our results suggest that this novel use of visual saliency can improve overall outcomes by helping human users in the person re-identification setting, while assuring the ethical and trusted operation of surveillance systems.

关键词： Ethics Visualization computer vision Surveillance conferences Computational modeling Decision making

来源：评论

学校读者我要写书评

暂无评论

Adaptive Differential Filters for Fast and Communication-Efficient Federated Learning

Adaptive Differential Filters for Fast and Communication-Eff...

引用

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

作者： Becking, Daniel Kirchhoffer, Heiner Tech, Gerhard Haase, Paul Mueller, Karsten Schwarz, Heiko Samek, Wojciech Fraunhofer Heinrich Hertz Inst HHI Berlin Germany

ISBN: (纸本)9781665487399

Federated learning (FL) scenarios inherently generate a large communication overhead by frequently transmitting neural network updates between clients and server. To minimize the communication cost, introducing sparsity in conjunction with differential updates is a commonly used technique. However, sparse model updates can slow down convergence speed or unintentionally skip certain update aspects, e.g., learned features, if error accumulation is not properly addressed. In this work, we propose a new scaling method operating at the granularity of convolutional filters which 1) compensates for highly sparse updates in FL processes, 2) adapts the local models to new data domains by enhancing some features in the filter space while diminishing others and 3) motivates extra sparsity in updates and thus achieves higher compression ratios, i.e., savings in the overall data transfer. Compared to unscaled updates and previous work, experimental results on different computer vision tasks (Pascal VOC, CIFAR10, Chest X-Ray) and neural networks (ResNets, MobileNets, VGGs) in uni-, bidirectional and partial update FL settings show that the proposed method improves the performance of the central server model while converging faster and reducing the total amount of transmitted data by up to 377x.

关键词： computer vision Adaptation models Computational modeling Pipelines Neural networks Collaborative work Data models

来源：评论

学校读者我要写书评

暂无评论

Self-supervised Learning for Sonar Image Classification

Self-supervised Learning for Sonar Image Classification

引用

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

作者： Preciado-Grijalva, Alan Wehbe, Bilal Firvida, Miguel Bande Valdenegro-Toro, Matias German Res Ctr Artificial Intelligence D-28359 Bremen Germany Bonn Rhein Sieg Univ Appl Sci D-53757 St Augustin Germany Univ Groningen Dept AI NL-9747 AG Groningen Netherlands

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Self-supervised learning has proved to be a powerful approach to learn image representations without the need of large labeled datasets. For underwater robotics, it is of great interest to design computer vision algorithms to improve perception capabilities such as sonar image classification. Due to the confidential nature of sonar imaging and the difficulty to interpret sonar images, it is challenging to create public large labeled sonar datasets to train supervised learning algorithms. In this work, we investigate the potential of three self-supervised learning methods (RotNet, Denoising Autoencoders, and Jigsaw) to learn high-quality sonar image representation without the need of human labels. We present pre-training and transfer learning results on real-life sonar image datasets. Our results indicate that self-supervised pre-training yields classification performance comparable to supervised pre-training in a few-shot transfer learning setup across all three methods. Code and self-supervised pre-trained models are be available at agrija9/ssl-sonar-images.

关键词： computer vision Transfer learning Supervised learning Noise reduction Sonar Self-supervised learning Image representation

来源：评论

学校读者我要写书评

暂无评论

Doubling down: sparse grounding with an additional, almost-matching caption for detection-oriented multimodal pretraining

Doubling down: sparse grounding with an additional, almost-m...

引用

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

作者： Nebbia, Giacomo Kovashka, Adriana Univ Pittsburgh Pittsburgh PA 15260 USA

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

A common paradigm in deep learning applications for computer vision is self-supervised pretraining followed by supervised fine-tuning on a target task. In the self-supervision step, a model is trained in a supervised fashion, but the source of supervision needs to be implicitly defined by the data. Image-caption alignment is often used as such a source of implicit supervision in multimodal pretraining, and grounding (i.e., matching word tokens with visual tokens) is one way to exploit it. We introduce a strategy to take advantage of an underexplored structure in image-caption datasets: the relationship between captions matched with different images but mentioning the same objects. Given an image-caption pair, we find an additional caption that mentions one of the objects the first caption mentions, and we impose a sparse grounding between the image and the second caption so that only a few word tokens are grounded in the image. Our goal is to learn a better feature representation for the objects mentioned by both captions, encouraging grounding between the additional caption and the image to focus on the common objects only. We report superior grounding performance when comparing our approach with a previously-published pretraining strategy, and we show the benefit of our proposed double-caption grounding on two downstream detection tasks: supervised detection and open-vocabulary detection.

关键词： Deep learning computer vision Visualization Grounding conferences Computational modeling Data models

来源：评论

学校读者我要写书评

暂无评论

On the Exploitation of Deepfake Model recognition

On the Exploitation of Deepfake Model Recognition

引用

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

作者： Guarnera, Luca Giudice, Oliver Niessner, Matthias Battiato, Sebastiano Univ Catania Dept Math & Comp Sci Catania Italy Banca Italia IT Dept Appl Res Team Rome Italy Tech Univ Munich Munich Germany

ISBN: (纸本)9781665487399

Despite recent advances in Generative Adversarial Networks (GANs), with special focus to the Deepfake phenomenon there is no a clear understanding neither in terms of explainability nor of recognition of the involved models. In particular, the recognition of a specific GAN model that generated the deepfake image compared to many other possible models created by the same generative architecture (e.g. StyleGAN) is a task not yet completely addressed in the state-of-the-art. In this work, a robust processing pipeline to evaluate the possibility to point-out analytic fingerprints for Deepfake model recognition is presented. After exploiting the latent space of 50 slightly different models through an in-depth analysis on the generated images, a proper encoder was trained to discriminate among these models obtaining a classification accuracy of over 96%. Once demonstrated the possibility to discriminate extremely similar images, a dedicated metric exploiting the insights discovered in the latent space was introduced. By achieving a final accuracy of more than 94% for the Model recognition task on images generated by models not employed in the training phase, this study takes an important step in countering the Deepfake phenomenon introducing a sort of signature in some sense similar to those employed in the multimedia forensics field (e.g. for camera source identification task, image ballistics task, etc).

关键词： Training Measurement Deepfakes Analytical models Image recognition Forensics Pipelines

来源：评论

学校读者我要写书评

暂无评论

Remote Estimation of Continuous Blood Pressure by a Convolutional Neural Network Trained on Spatial patterns of Facial Pulse Waves

Remote Estimation of Continuous Blood Pressure by a Convolut...

引用

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

作者： Iuchi, Kaito Miyazaki, Ryogo Cardoso, George C. Ogawa-Ochiai, Keiko Tsumura, Norimichi Chiba Univ Grad Sch Sci & Engn Dept Imaging Sci Chiba Japan Univ Sao Paulo Phys Dept FFCLRP Sao Paulo Brazil Hiroshima Univ Hosp Dept Gen Med Hiroshima Japan

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

We propose a remote method to estimate continuous blood pressure based on spatial information of a pulse wave at a single point in time. By setting regions of interest to cover a face in a mutually exclusive and collectively exhaustive manner, RGB facial video is converted into a spatial pulse wave signal. The spatial pulse wave signal is converted into spatial signals of contours of each segmented pulse beat and relationships of each segmented pulse beat. The spatial signal is represented as a time-continuous value based on a representation of a pulse contour in a time axis and a phase axis and an interpolation along with the time axis. A relationship between the spatial signals and blood pressure is modeled by a convolutional neural network. A dataset was built to demonstrate the effectiveness of the proposed method. The dataset consists of continuous blood pressure and facial RGB videos of ten healthy volunteers. A comparison of conventional methods with the proposed method shows superior error for the latter. The results show an adequate estimation of the performance of the proposed method, when compared to the ground truth in mean blood pressure, in both the correlation coefficient (0.85) and mean absolute error (5.4 mmHg).

关键词： Correlation coefficient Interpolation computer vision Face recognition conferences Estimation Blood pressure

来源：评论

学校读者我要写书评

暂无评论

Efficient Image Super-Resolution with Collapsible Linear Blocks

Efficient Image Super-Resolution with Collapsible Linear Blo...

引用

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

作者： Wang, Li Li, Dong Tian, Lu Shan, Yi Adv Micro Devices Inc Beijing Peoples R China

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

In this paper, we propose a simple but effective architecture for fast and accurate single image super-resolution. Unlike other compact image super-resolution methods based on hand-crafted designs, we first apply coarse-grained pruning for network acceleration, and then introduce collapsible linear blocks to recover the representative ability of the pruned network. Specifically, each collapsible linear block has a multi-branch topology during training, and can be equivalently replaced with a single convolution in the inference stage. Such decoupling of the training-time and inference-time architecture is implemented via a structural re-parameterization technique, leading to improved representation without introducing extra computation costs. Additionally, we adopt a two-stage training mechanism with progressively larger patch sizes to facilitate the optimization procedure. We evaluate the proposed method on the NTIRE 2022 Efficient Image Super-Resolution Challenge and achieve a good trade-off between latency and accuracy. Particularly, under the condition of limited inference time (<= 49.42ms) and parameter amount (<= 0.894M), our solution obtains the best fidelity results in terms of PSNR, i.e., 29.05dB and 28.75dB on the DIV2K validation and test sets, respectively.

关键词： Training Costs Network topology Convolution conferences Superresolution computer architecture

来源：评论

学校读者我要写书评

暂无评论

Multi-modal Aerial View Object Classification Challenge Results - PBVS 2022

Multi-modal Aerial View Object Classification Challenge Resu...

引用

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

作者： Low, Spencer Nina, Oliver Sappa, Angel D. Blasch, Erik Brigham Young Univ Provo UT 84602 USA Air Force Res Lab Dayton OH USA ESPOL Polytech Univ Ecuador Comp Vision Ctr Guayaquil Ecuador Air Force Off Sci Res Arlington VA USA

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

This paper details the results and main findings of the second iteration of the Multi-modal Aerial View Object Classification (MAVOC) challenge. The primary goal of both MAVOC challenges is to inspire research into methods for building recognition models that utilize both synthetic aperture radar (SAR) and electro-optical (EO) imagery. Teams are encouraged to develop multi-modal approaches that incorporate complementary information from both domains. While the 2021 challenge showed a proof of concept that both modalities could be used together, the 2022 challenge focuses on the detailed multi-modal methods. The 2022 challenge uses the same UNIfied COincident Optical and Radar for recognition (UNICORN) dataset and competition format that was used in 2021. Specifically, the challenge focuses on two tasks, (1) SAR classification and (2) SAR + EO classification. The bulk of this document is dedicated to discussing the top performing methods and describing their performance on our blind test set. Notably, all of the top ten teams outperform a Resnet-18 baseline. For SAR classification, the top team showed a 129% improvement over baseline and an 8% average improvement from the 2021 winner. The top team for SAR + EO classification shows a 165% improvement with a 32% average improvement over 2021.

关键词： Training Laser radar Image recognition Radar imaging Optical imaging pattern recognition Task analysis

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 << < 40 41 42 43 44 45 46 47 48 49 > >>

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：