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

3,915 篇 会议
2 篇 期刊文献

馆藏范围

3,917 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

3,011 篇 工学
- 2,919 篇 计算机科学与技术...
- 216 篇 软件工程
- 141 篇 机械工程
- 133 篇 光学工程
- 42 篇 生物工程
- 28 篇 信息与通信工程
- 25 篇 电气工程
- 17 篇 控制科学与工程
- 9 篇 电子科学与技术（可...
- 9 篇 化学工程与技术
- 9 篇 交通运输工程
- 8 篇 生物医学工程（可授...
- 7 篇 安全科学与工程
- 4 篇 材料科学与工程（可...
- 4 篇 建筑学
- 3 篇 土木工程
- 3 篇 农业工程
1,559 篇 医学
- 1,558 篇 临床医学
- 3 篇 基础医学(可授医学...
174 篇 理学
- 136 篇 物理学
- 43 篇 生物学
- 29 篇 数学
- 16 篇 统计学（可授理学、...
- 10 篇 化学
14 篇 管理学
- 7 篇 管理科学与工程(可...
- 7 篇 图书情报与档案管...
- 3 篇 工商管理
5 篇 法学
- 3 篇 社会学
- 2 篇 法学
2 篇 教育学
- 2 篇 教育学
2 篇 农学
1 篇 经济学

主题

2,408 篇 computer vision
1,085 篇 training
1,043 篇 pattern recognit...
805 篇 conferences
709 篇 computational mo...
543 篇 visualization
491 篇 computer archite...
446 篇 three-dimensiona...
410 篇 semantics
409 篇 benchmark testin...
383 篇 codes
331 篇 transformers
290 篇 deep learning
277 篇 feature extracti...
260 篇 neural networks
256 篇 task analysis
238 篇 shape
216 篇 image segmentati...
204 篇 measurement
202 篇 object detection

机构

72 篇 tsinghua univ pe...
59 篇 univ sci & techn...
55 篇 zhejiang univ pe...
55 篇 chinese univ hon...
51 篇 carnegie mellon ...
51 篇 peng cheng lab p...
49 篇 swiss fed inst t...
47 篇 sensetime res pe...
46 篇 shanghai ai lab ...
42 篇 univ hong kong p...
38 篇 huawei noahs ark...
35 篇 univ chinese aca...
35 篇 shanghai jiao to...
33 篇 alibaba grp peop...
32 篇 tech univ munich...
31 篇 stanford univ st...
30 篇 peking univ peop...
30 篇 swiss fed inst t...
29 篇 adobe res san jo...
29 篇 google res mount...

作者

63 篇 timofte radu
30 篇 van gool luc
19 篇 yang yi
19 篇 qiao yu
18 篇 loy chen change
16 篇 zhang lei
16 篇 radu timofte
15 篇 sun jian
14 篇 liu yang
14 篇 liu shuaicheng
14 篇 tao dacheng
13 篇 li xin
13 篇 fan haoqiang
13 篇 chen wei-ting
12 篇 luo ping
12 篇 chen dongdong
12 篇 wang kai
12 篇 wang xinchao
12 篇 torralba antonio
12 篇 ghanem bernard

语言

3,916 篇 英文
1 篇 其他

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

共 3917 条记录，以下是3841-3850 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：

Generating Accurate Pseudo Examples for Continual Learning

Generating Accurate Pseudo Examples for Continual Learning

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Daniel L. Silver Sazia Mahfuz Jodrey School of Computer Science Acadia University School of Computing Queens Uninversity

ISBN: (数字)9781728193601

ISBN: (纸本)9781728193618

Continual learning (CL) is concerned with the persistent and cumulative nature of learning. This requires a method of successfully consolidating new knowledge into long-term memory without the loss of prior knowledge. Prior research has addressed this CL retention problem through the efficient rehearsal of prior examples while learning the examples of a new task within a long-term Multiple Task Learning (MTL) network. The approach maintains or improves prior knowledge while allowing its representation to remain plastic for the integration of new task examples. Preferably, rehearsal is done using pseudo examples synthesized by the MTL network; eliminating the need to retain prior task training examples or a generate them with an additional model. Previous work has shown that to properly retain knowledge the pseudo examples must adhere to the input probability distribution of those original examples. Two approaches are investigated for creating appropriate pseudo examples from a Restricted Boltzmann Machine (RBM) autoencoder, which can reside in the lowest layers of the long-term MTL Deep Belief network. We show that appropriate pseudo examples can be reconstructed by passing uniform random examples to a generative RBM model and selecting only those with reconstruction error less than the mean training error. These pseudo examples are shown to adhere to the probability distribution of the input variables of the original training examples and retain prior task knowledge during rehearsal as well as those examples. As part of the research, we develop and test a new metric called the Autoencoder Divergence Measure for comparing the probability distributions of two datasets given to a generative RBM network based on their reconstruction mean squared error.

关键词： Task analysis Training Probability distribution Knowledge engineering Input variables Generative adversarial networks Neural networks

来源：评论

学校读者我要写书评

暂无评论

How Suboptimal is Training rPPG Models with Videos and Targets from Different Body Sites?

How Suboptimal is Training rPPG Models with Videos and Targe...

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Björn Braun Daniel McDuff Christian Holz Department of Computer Science ETH Zürich Switzerland Paul G. Allen School of Computer Science University of Washington

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Remote camera measurement of the blood volume pulse via photoplethysmography (rPPG) is a compelling technology for scalable, low-cost, and accessible assessment of cardiovascular information. Neural networks currently provide the state-of-the-art for this task and supervised training or fine-tuning is an important step in creating these models. However, most current models are trained on facial videos using contact PPG measurements from the fingertip as targets/labels. One of the reasons for this is that few public datasets to date have incorporated contact PPG measurements from the face. Yet there is copious evidence that the PPG signals at different sites on the body have very different morphological features. Is training a facial video rPPG model using contact measurements from another site on the body suboptimal? Using a recently released unique dataset with synchronized contact PPG and video measurements from both the hand and face, we can provide precise and quantitative answers to this question. We obtain up to 40% lower mean squared errors between the waveforms of the predicted and the ground truth PPG signals using state-of-the-art neural models when using PPG signals from the forehead compared to using PPG signals from the fingertip. We also show qualitatively that the neural models learn to predict the morphology of the ground truth PPG signal better when trained on the forehead PPG signals. However, while models trained from the forehead PPG produce a more faithful waveform, models trained from a finger PPG do still learn the dominant frequency (i.e., the heart rate) well.

关键词： Training Wrist Forehead Current measurement Volume measurement Estimation Predictive models

来源：评论

学校读者我要写书评

暂无评论

PointOfView: A Multi-modal Network for Few-shot 3D Point Cloud Classification Fusing Point and Multi-view Image Features

PointOfView: A Multi-modal Network for Few-shot 3D Point Clo...

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Huantao Ren Jiyang Wang Minmin Yang Senem Velipasalar Electrical Engineering and Computer Science Dept Syracuse University Syracuse NY USA

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Most existing 3D point cloud analysis approaches employ traditional supervised methods, which require large amounts of labeled data, and data annotation is labor-intensive, and costly. On the other hand, although many existing works use either raw 3D point clouds or multiple 2D depth images, their joint use is relatively under-explored. To address these issues, we propose PointOfView, a novel, multi-modal few-shot 3D point cloud classification model, to classify never-before-seen classes with only a few annotated samples. A 2D multi-view learning branch is proposed for processing multiple projection images, and it contains two sub-branches to extract information at individual image level as well as among all six depth images. In addition, we propose a multi-scale 2D pooling layer, which employs various 2D max-pooling and 2D average pooling operations, with different pooling sizes. This allows fusing features at different scales. The second main branch processes raw 3D point clouds by first sorting them, and then using DGCNN to extract features. We perform within-dataset and cross-domain experiments on ModelNel40, ModelNet40-C and ScanobjectNN datasets, and compare with six state-of-the-art baselines. The results show that our approach outperforms all baselines in all experimental settings and achieve the state-of-the-art performance.

关键词： Point cloud compression Solid modeling computer vision Three-dimensional displays Shape Computational modeling conferences

来源：评论

学校读者我要写书评

暂无评论

Vulnerability of Person Re-Identification Models to Metric Adversarial Attacks

Vulnerability of Person Re-Identification Models to Metric A...

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Quentin Bouniot Romaric Audigier Angélique Loesch CEA LIST Vision and Learning Lab for Scene Analysis Gif-sur-Yvette France

ISBN: (数字)9781728193601

ISBN: (纸本)9781728193618

Person re-identification (re-ID) is a key problem in smart supervision of camera networks. Over the past years, models using deep learning have become state of the art. However, it has been shown that deep neural networks are flawed with adversarial examples, i.e. human-imperceptible perturbations. Extensively studied for the task of image closed- set classification, this problem can also appear in the case of open-set retrieval tasks. Indeed, recent work has shown that we can also generate adversarial examples for metric learning systems such as re-ID ones. These models remain vulnerable: when faced with adversarial examples, they fail to correctly recognize a person, which represents a security breach. These attacks are all the more dangerous as they are impossible to detect for a human operator. Attacking a metric consists in altering the distances between the feature of an attacked image and those of reference images, i.e. guides. In this article, we investigate different possible attacks depending on the number and type of guides available. From this metric attack family, two particularly effective attacks stand out. The first one, called Self Metric Attack, is a strong attack that does not need any image apart from the attacked image. The second one, called FurthestNegative Attack, makes full use of a set of images. Attacks are evaluated on commonly used datasets: Market1501 and DukeMTMC. Finally, we propose an efficient extension of adversarial training protocol adapted to metric learning as a defense that increases the robustness of re-ID models. 1

关键词： Measurement Training Task analysis Protocols Testing Robustness Perturbation methods

来源：评论

学校读者我要写书评

暂无评论

Data-free Defense of Black Box Models Against Adversarial Attacks

Data-free Defense of Black Box Models Against Adversarial At...

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Gaurav Kumar Nayak Inder Khatri Ruchit Rawal Anirban Chakraborty University of Central Florida Orlando Florida USA New York University New York USA Indian Institute of Science Bangalore India

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Several companies often safeguard their trained deep models (i.e. details of architecture, learnt weights, training details etc.) from third-party users by exposing them only as ‘black boxes' through APIs. Moreover, they may not even provide access to the training data due to proprietary reasons or sensitivity concerns. In this work, we propose a novel defense mechanism for black box models against adversarial attacks in a data-free set up. We construct synthetic data via a generative model and train surrogate network using model stealing techniques. To minimize adversarial contamination on perturbed samples, we propose ‘wavelet noise remover' (WNR) that performs discrete wavelet decomposition on input images and carefully select only a few important coefficients determined by our ‘wavelet coefficient selection module' (WCSM). To recover the high-frequency content of the image after noise removal via WNR, we further train a ‘regenerator' network with an objective to retrieve the coefficients such that the reconstructed image yields similar to original predictions on the surrogate model. At test time, WNR combined with trained regenerator network is prepended to the black box network, resulting in a high boost in adversarial accuracy. Our method improves the adversarial accuracy on CIFAR-10 by 38.98% and 32.01% against the state-of-the-art Auto Attack compared to baseline, even when the attacker uses surrogate architecture (Alexnet-half and Alexnet) similar to the black box architecture (Alexnet) with same model stealing strategy as defender.

关键词： Training Accuracy Sensitivity Noise Training data computer architecture Predictive models

来源：评论

学校读者我要写书评

暂无评论

Dynamic Representations Toward Efficient Inference on Deep Neural Networks by Decision Gates

Dynamic Representations Toward Efficient Inference on Deep N...

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Mohammad Saeed Shafiee Mohammad Javad Shafiee Alexander Wong Faculty of Electrical Engineering Shahid Rajee University Tehran Iran Vision & Image Processing Research Group Waterloo AI Institute University of Waterloo DarwinAI Corp. Waterloo Canada

ISBN: (数字)9781728125060

ISBN: (纸本)9781728125077

While deep neural networks extract rich features from the input data, the current trade-off between depth and computational cost makes it difficult to adopt deep neural networks for many industrial applications, especially when computing power is limited. Here, we are inspired by the idea that, while deeper embeddings are needed to discriminate difficult samples (i.e., fine-grained discrimination), a large number of samples can be well discriminated via much shallower embeddings (i.e., coarse-grained discrimination). In this study, we introduce the simple yet effective concept of decision gates (d-gate), modules trained to decide whether a sample needs to be projected into a deeper embedding or if an early prediction can be made at the d-gate, thus enabling the computation of dynamic representations at different depths. The proposed d-gate modules can be integrated with any deep neural network and reduces the average computational cost of the deep neural networks while maintaining modeling accuracy. The proposed d-gate framework is examined via different network architectures and datasets, with experimental results showing that leveraging the proposed d-gate modules led to a ~43% speed-up and 44% FLOPs reduction on ResNet-101 and 55% speed-up and 39% FLOPs reduction on DenseNet-201 trained on the CIFAR10 dataset with only ~2% drop in accuracy. Furthermore, experiments where d-gate modules are integrated into ResNet-101 trained on the ImageNet dataset demonstrate that it is possible to reduce the computational cost of the network by 1.5 GFLOPs without any drop in the modeling accuracy.

关键词： Neural networks computer architecture Computational efficiency Feature extraction Computational modeling Visualization Logic gates

来源：评论

学校读者我要写书评

暂无评论

DepthVoting: A Few-Shot Point Cloud Classification Model Incorporating a Projection-Based Voting Mechanism

DepthVoting: A Few-Shot Point Cloud Classification Model Inc...

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Yunhui Zhu Jiajing Chen Senem Velipasalar Electrical Engineering and Computer Science Dept. Syracuse University Syracuse NY USA

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Despite the significant progress in few-shot 2D image classification, few-shot 3D point cloud classification remains relatively under-explored, particularly in addressing the challenges posed by missing points in 3D point clouds. Most existing methods for few-shot 3D point cloud classification are point-based, and thus, highly sensitive to missing points. Despite recent attempts, such as ViewNet, which introduce projection-based backbones to increase robustness against missing points, the reliance on max pooling, to extract information from multiple images simultaneously, makes them prone to information loss. To address these limitations, we introduce DepthVoting, a novel projection-based approach, for few-shot 3D point cloud classification. Instead of extracting features from multiple projection images simultaneously, DepthVoting captures features from pairs of projection images (obtained from opposite view angles) separately, enhancing the extraction of more comprehensive information. These features are sent to multiple few-shot heads, which share parameters. To further refine predictions, DepthVoting incorporates a voting mechanism, allowing contribution and incorporating information from different pairs. We conduct extensive experiments on three datasets, namely ModelNet40, ModelNet40-C, and ScanObjectNN, along with cross-validation. Our proposed method consistently outperforms the state-of-the-art baselines on all datasets in terms of average accuracy with even higher margins on the challenging ScanObjectNN dataset.

关键词： Point cloud compression Solid modeling Three-dimensional displays Head Accuracy Feature extraction Data augmentation

来源：评论

学校读者我要写书评

暂无评论

Motorcyclist Helmet Violation Detection Framework by Leveraging Robust Ensemble and Augmentation Methods

Motorcyclist Helmet Violation Detection Framework by Leverag...

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Thien Van Luong Huu Si Phuc Nguyen Duy Khanh Dinh Viet Hung Duong Duy Hong Sam Vo Huan Vu Minh Tuan Hoang Tien Cuong Nguyen Faculty of Computer Science Phenikaa University Hanoi Vietnam VNPT Group VNPT AI Hanoi Vietnam University of Transport and Communications Hanoi Vietnam

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Traffic Monitoring Systems play a crucial role in real-life scenarios by improving traffic flow and reducing violations. Among these violations, helmet non-compliance is particularly common in countries where motorcycles are the primary mode of transportation. However, deploying an automatic violation capturing for helmet non-compliance in the real world presents challenges due to diverse traffic situations, environmental conditions, varying object sizes, and severely imbalanced datasets. In order to address these challenges, we propose a novel deep learning framework for helmet violation detection, which consists of four different modules, namely, object detection, object association, post-processing for tracking, and score correction. In particular, we develop a robust ensemble method to take advantage of various state-of-the-art object detection models such as YOLOv7, YOLOv8, Co-DETR, and EfficientDet. Furthermore, to address the issue of data imbalance, we propose two copy and paste data augmentation techniques for enriching data samples of rare classes. As a result, our approach yields a substantial 7.43% mAP enhancement over the baseline Co-DETR model, achieving a final score of 0.4792 in the 2024 AI City Challenge Track 5 test set and ranking 3rd among the competing teams.

关键词： Deep learning Head Urban areas Transportation Motorcycles Object detection Data augmentation

来源：评论

学校读者我要写书评

暂无评论

A Hybrid ANN-SNN Architecture for Low-Power and Low-Latency Visual Perception

A Hybrid ANN-SNN Architecture for Low-Power and Low-Latency ...

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Asude Aydin Mathias Gehrig Daniel Gehrig Davide Scaramuzza Robotics and Perception Group University of Zurich Switzerland

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Spiking Neural Networks (SNNs) are a class of bio-inspired neural networks that promise to bring low-power and low-latency inference to edge-devices through the use of asynchronous and sparse processing. However, being temporal models, SNNs depend heavily on expressive states to generate predictions on par with classical artificial neural networks (ANNs). These states converge only after long transient time periods, and quickly decay in the absence of input data, leading to higher latency, power consumption, and lower accuracy. In this work, we address this issue by initializing the state with an auxiliary ANN running at a low rate. The SNN then uses the state to generate predictions with high temporal resolution until the next initialization phase. Our hybrid ANN-SNN model thus combines the best of both worlds: It does not suffer from long state transients and state decay thanks to the ANN, and can generate predictions with high temporal resolution, low latency, and low power thanks to the SNN. We show for the task of event-based 2D and 3D human pose estimation that our method consumes 88% less power with only a 4% decrease in performance compared to its fully ANN counterparts when run at the same inference rate. Moreover, when compared to SNNs, our method achieves a 74% lower error. This research thus provides a new understanding of how ANNs and SNNs can be used to maximize their respective benefits. Code: https://***/uzh-rpg/hybrid_ann_snn

关键词： Accuracy Three-dimensional displays Pose estimation computer architecture Spiking neural networks Predictive models Low latency communication

来源：评论

学校读者我要写书评

暂无评论

FGCN: Deep Feature-based Graph Convolutional Network for Semantic Segmentation of Urban 3D Point Clouds

FGCN: Deep Feature-based Graph Convolutional Network for Sem...

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Saqib Ali Khan Yilei Shi Muhammad Shahzad Xiao Xiang Zhu School of Electrical Engineering and Computer Science (SEECS) National University of Sciences and Technology (NUST) Islamabad Pakistan Chair of Remote Sensing Technology (LMF) Technical University of Munich (TUM) Munich Germany Signal Processing in Earth Observation (SiPEO) Technical University of Munich (TUM) Munich Germany

ISBN: (数字)9781728193601

ISBN: (纸本)9781728193618

Directly processing 3D point clouds using convolutional neural networks (CNNs) is a highly challenging task primarily due to the lack of explicit neighborhood relation-ship between points in 3D space. Several researchers have tried to cope with this problem using a preprocessing step of voxelization. Although, this allows to translate the existing CNN architectures to process 3D point clouds but, in addition to computational and memory constraints, it poses quantization artifacts which limits the accurate inference of the underlying object's structure in the illuminated scene. In this paper, we have introduced a more stable and effective end-to-end architecture to classify raw 3D point clouds from indoor and outdoor scenes. In the proposed methodology, we encode the spatial arrangement of neighbouring 3D points inside an undirected symmetrical graph, which is passed along with features extracted from a 2D CNN to a Graph Convolutional Network (GCN) that contains three layers of localized graph convolutions to generate a complete segmentation map. The proposed network achieves on par or even better than state-of-the-art results on tasks like semantic scene parsing, part segmentation and urban classification on three standard benchmark datasets.

关键词： Three-dimensional displays Feature extraction Convolution computer architecture Two dimensional displays Semantics Machine learning

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392页 << < 381 382 383 384 385 386 387 388 389 390 > >>

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：