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

383 篇 会议

馆藏范围

383 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

383 篇 工学
- 383 篇 计算机科学与技术...
2 篇 医学
- 2 篇 临床医学

主题

383 篇 recognition: det...
382 篇 categorization
380 篇 retrieval
200 篇 deep learning
81 篇 representation l...
38 篇 vision applicati...
35 篇 segmentation
35 篇 scene analysis a...
27 篇 grouping and sha...
24 篇 gesture
24 篇 face
23 篇 and body pose
23 篇 datasets and eva...
20 篇 3d from multivie...
19 篇 video analytics
17 篇 statistical lear...
17 篇 vision + languag...
16 篇 optimization met...
13 篇 robotics + drivi...
13 篇 others

机构

16 篇 univ chinese aca...
15 篇 chinese univ hon...
11 篇 sun yat sen univ...
11 篇 sensetime res pe...
11 篇 peng cheng lab p...
9 篇 huawei noahs ark...
9 篇 carnegie mellon ...
8 篇 univ sci & techn...
8 篇 tsinghua univ pe...
8 篇 johns hopkins un...
7 篇 facebook ai res ...
7 篇 sun yat sen univ...
7 篇 minist educ key ...
7 篇 nanyang technol ...
6 篇 cas ctr excellen...
6 篇 hong kong univ s...
6 篇 tencent youtu la...
6 篇 tech univ munich...
6 篇 univ calif berke...
6 篇 univ texas austi...

作者

7 篇 zheng wei-shi
7 篇 wang xiaogang
7 篇 lin dahua
6 篇 ji rongrong
6 篇 yan junjie
5 篇 grauman kristen
5 篇 lin liang
5 篇 doermann david
5 篇 shao ling
5 篇 liang xiaodan
4 篇 shan shiguang
4 篇 zhang baochang
4 篇 girshick ross
4 篇 loy chen change
4 篇 chen xilin
4 篇 rastegari mohamm...
4 篇 tian qi
4 篇 lu cewu
4 篇 ouyang wanli
4 篇 schiele bernt

语言

383 篇 英文

检索条件"主题词=Recognition: Detection"

共 383 条记录，以下是131-140 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：

Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks 32

Evading Defenses to Transferable Adversarial Examples by Tra...

引用

32nd IEEE/CVF Conference on Computer Vision and Pattern recognition (CVPR)

作者： Dong, Yinpeng Pang, Tianyu Su, Hang Zhu, Jun Tsinghua Univ Dept Comp Sci & Tech BNRist Ctr State Key Lab Intell Tech & SysInst AITHBI Lab Beijing 100084 Peoples R China

ISBN: (纸本)9781728132938

Deep neural networks are vulnerable to adversarial examples, which can mislead classifiers by adding imperceptible perturbations. An intriguing property of adversarial examples is their good transferability, making black-box attacks feasible in real-world applications. Due to the threat of adversarial attacks, many methods have been proposed to improve the robustness. Several state-of-the-art defenses are shown to be robust against transferable adversarial examples. In this paper, we propose a translation-invariant attack method to generate more transferable adversarial examples against the defense models. By optimizing a perturbation over an ensemble of translated images, the generated adversarial example is less sensitive to the white-box model being attacked and has better transferability. To improve the efficiency of attacks, we further show that our method can be implemented by convolving the gradient at the untranslated image with a pre-defined kernel. Our method is generally applicable to any gradient-based attack method. Extensive experiments on the ImageNet dataset validate the effectiveness of the proposed method. Our best attack fools eight state-of-the-art defenses at an 82% success rate on average based only on the transferability, demonstrating the insecurity of the current defense techniques.

关键词： Categorization Deep Learning recognition: detection Retrieval

来源：评论

学校读者我要写书评

暂无评论

Hybrid Scene Compression for Visual Localization 32

Hybrid Scene Compression for Visual Localization

引用

32nd IEEE/CVF Conference on Computer Vision and Pattern recognition (CVPR)

作者： Camposeco, Federico Cohen, Andrea Pollefeys, Marc Sattler, Torsten Swiss Fed Inst Technol Dept Comp Sci Zurich Switzerland Microsoft Zurich Switzerland Chalmers Univ Technol Gothenburg Sweden

ISBN: (纸本)9781728132938

Localizing an image w.r.t. a 3D scene model represents a core task for many computer vision applications. An increasing number of real-world applications of visual localization on mobile devices, e.g., Augmented Reality or autonomous robots such as drones or self-driving cars, demand localization approaches to minimize storage and bandwidth requirements. Compressing the 3D models used for localization thus becomes a practical necessity. In this work, we introduce a new hybrid compression algorithm that uses a given memory limit in a more effective way. Rather than treating all 3D points equally, it represents a small set of points with full appearance information and an additional, larger set of points with compressed information. This enables our approach to obtain a more complete scene representation without increasing the memory requirements,leading to a superior performance compared to previous compression schemes. As part of our contribution, we show how to handle ambiguous matches arising from point compression during RANSAC. Besides outperforming previous compression techniques in terms of pose accuracy under the same memory constraints,our compression scheme itself is also more efficient. Furthermore,the localization rates and accuracy obtained with our approach are comparable to state-of-the-art feature-based methods, while using a small fraction of the memory.

关键词： 3D from Multiview and Sensors Categorization recognition: detection Retrieval Robotics + Driving

来源：评论

学校读者我要写书评

暂无评论

Deep Multimodal Clustering for Unsupervised Audiovisual Learning 32

Deep Multimodal Clustering for Unsupervised Audiovisual Lear...

引用

32nd IEEE/CVF Conference on Computer Vision and Pattern recognition (CVPR)

作者： Hu, Di Nie, Feiping Li, Xuelong Northwestern Polytech Univ Sch Comp Sci Xian 710072 Peoples R China Northwestern Polytech Univ Ctr OPT IMagery Anal & Learning OPTIMAL Xian 710072 Peoples R China

ISBN: (纸本)9781728132938

The seen birds twitter, the running cars accompany with noise, etc. These naturally audiovisual correspondences provide the possibilities to explore and understand the outside world. However, the mixed multiple objects and sounds make it intractable to perform efficient matching in the unconstrained environment. To settle this problem, we propose to adequately excavate audio and visual components and perform elaborate correspondence learning among them. Concretely, a novel unsupervised audiovisual learning model is proposed, named as Deep Multimodal Clustering (DMC), that synchronously performs sets of clustering with multimodal vectors of convolutional maps in different shared spaces for capturing multiple audiovisual correspondences. And such integrated multimodal clustering network can be effectively trained with max-margin loss in the end-to-end fashion. Amounts of experiments in feature evaluation and audiovisual tasks are performed. The results demonstrate that DMC can learn effective unimodal representation, with which the classifier can even outperform human performance. Further;DMC shows noticeable performance in sound localization, multisource detection, and audiovisual understanding.

关键词： Big Data Categorization Large Scale Methods Others recognition: detection Representation Learning Retrieval Scene Analysis and Understanding V

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Domain Adaptation using Feature-Whitening and Consensus Loss 32

Unsupervised Domain Adaptation using Feature-Whitening and C...

引用

32nd IEEE/CVF Conference on Computer Vision and Pattern recognition (CVPR)

作者： Roy, Subhankar Siarohin, Aliaksandr Sangineto, Enver Bulo, Samuel Rota Sebe, Nicu Ricci, Elisa Univ Trento DISI Trento TN Italy Fdn Bruno Kessler Trento Italy Mapillary Res Malmo Sweden

ISBN: (纸本)9781728132938

A classifier trained on a dataset seldom works on other datasets obtained under different conditions due to domain shift. This problem is commonly addressed by domain adaptation methods. In this work we introduce a novel deep learning framework which unifies different paradigms in unsupervised domain adaptation. Specifically, we propose domain alignment layers which implement feature whitening for the purpose of matching source and target feature distributions. Additionally, we leverage the unlabeled target data by proposing the Min-Entropy Consensus loss, which regularizes training while avoiding the adoption of many user-defined hyper-parameters. We report results on publicly available datasets, considering both digit classification and object recognition tasks. We show that, in most of our experiments, our approach improves upon previous methods, setting new state-of-the-art performances.

关键词： Categorization Deep Learning recognition: detection Retrieval

来源：评论

学校读者我要写书评

暂无评论

You Look Twice: GaterNet for Dynamic Filter Selection in CNNs 32

You Look Twice: GaterNet for Dynamic Filter Selection in CNN...

引用

32nd IEEE/CVF Conference on Computer Vision and Pattern recognition (CVPR)

作者： Chen, Zhourong Li, Yang Bengio, Samy Si, Si Google Res Mountain View CA 94043 USA Hong Kong Univ Sci & Technol Hong Kong Peoples R China Google Mountain View CA 94043 USA

ISBN: (纸本)9781728132938

The concept of conditional computation for deep nets has been proposed previously to improve model performance by selectively using only parts of the model conditioned on the sample it is processing. In this paper, we investigate input-dependent dynamic filter selection in deep convolutional neural networks (CNNs). The problem is interesting because the idea of forcing different parts of the model to learn from different types of samples may help us acquire better filters in CNNs, improve the model generalization performance and potentially increase the interpretability of model behavior. We propose a novel yet simple framework called GaterNet, which involves a backbone and a gater network. The backbone network is a regular CNN that performs the major computation needed for making a prediction, while a global gater network is introduced to generate binary gates for selectively activating filters in the backbone network based on each input. Extensive experiments on CIFAR and ImageNet datasets show that our models consistently outperform the original models with a large margin. On CIFAR-10, our model also improves upon state-of-the-art results.

关键词： Categorization Deep Learning recognition: detection Retrieval

来源：评论

学校读者我要写书评

暂无评论

Knockoff Nets: Stealing Functionality of Black-Box Models 32

Knockoff Nets: Stealing Functionality of Black-Box Models

引用

32nd IEEE/CVF Conference on Computer Vision and Pattern recognition (CVPR)

作者： Orekondy, Tribhuvanesh Schiele, Bernt Fritz, Mario Max Planck Inst Informat Saarbrucken Germany CISPA Helmholtz Ctr Informat Secur Saarland Informat Campus Saarbrucken Germany

ISBN: (纸本)9781728132938

Machine Learning (ML) models are increasingly deployed in the wild to perform a wide range of tasks. In this work, we ask to what extent can an adversary steal functionality of such "victim'' models based solely on blackbox interactions: image in, predictions out. In contrast to prior work, we study complex victim blackbox models, and an adversary lacking knowledge of train/test data used by the model, its internals, and semantics over model outputs. We formulate model functionality stealing as a two-step approach: (i) querying a set of input images to the blackbox model to obtain predictions;and (ii) training a "knockoff'' with queried image-prediction pairs. We make multiple remarkable observations: (a) querying random images from a different distribution than that of the blackbox training data results in a well-performing knockoff;(b) this is possible even when the knockoff is represented using a different architecture;and (c) our reinforcement learning approach additionally improves query sample efficiency in certain settings and provides performance gains. We validate model functionality stealing on a range of datasets and tasks, as well as show that a reasonable knockoff of an image analysis API could be created for as little as $30.

关键词： Categorization Deep Learning recognition: detection Retrieval Vision Applications and Systems

来源：评论

学校读者我要写书评

暂无评论

Divide and Conquer the Embedding Space for Metric Learning 32

Divide and Conquer the Embedding Space for Metric Learning

引用

32nd IEEE/CVF Conference on Computer Vision and Pattern recognition (CVPR)

作者： Sanakoyeu, Artsiom Tschernezki, Vadim Buechler, Uta Ommer, Bjoern Heidelberg Univ IWR Heidelberg Collaboratory Image Proc Heidelberg Germany

ISBN: (纸本)9781728132938

Learning the embedding space, where semantically similar objects are located close together and dissimilar objects far apart, is a cornerstone of many computer vision applications. Existing approaches usually learn a single metric in the embedding space for all available data points, which may have a very complex non-uniform distribution with different notions of similarity between objects, e.g. appearance, shape, color or semantic meaning. Approaches for learning a single distance metric often struggle to encode all different types of relationships and do not generalize well. In this work, we propose a novel easy-to-implement divide and conquer approach for deep metric learning, which significantly improves the state-of-the-art performance of metric learning. Our approach utilizes the embedding space more efficiently by jointly splitting the embedding space and data into K smaller sub-problems. It divides both, the data and the embedding space into K subsets and learns K separate distance metrics in the non-overlapping subspaces of the embedding space, defined by groups of neurons in the embedding layer of the neural network. The proposed approach increases the convergence speed and improves generalization since the complexity of each sub-problem is reduced compared to the original one. We show that our approach outperforms the state-of-the-art by a large margin in retrieval, clustering and re-identification tasks on CUB200-2011, CARS196, Stanford Online Products, Inshop Clothes and PKU VehicleID datasets.

关键词： Categorization Deep Learning recognition: detection Representation Learning Retrieval

来源：评论

学校读者我要写书评

暂无评论

Locating Objects Without Bounding Boxes 32

Locating Objects Without Bounding Boxes

引用

32nd IEEE/CVF Conference on Computer Vision and Pattern recognition (CVPR)

作者： Ribera, Javier Guera, David Chen, Yuhao Delp, Edward J. Purdue Univ Video & Image Proc Lab VIPER W Lafayette IN 47907 USA

ISBN: (纸本)9781728132938

Recent advances in convolutional neural networks (CNN) have achieved remarkable results in locating objects in images. In these networks, the training procedure usually requires providing bounding boxes or the maximum number of expected objects. In this paper, we address the task of estimating object locations without annotated bounding boxes which are typically hand-drawn and time consuming to label. We propose a loss function that can be used in any fully convolutional network (FCN) to estimate object locations. This loss function is a modification of the average Hausdorff distance between two unordered sets of points. The proposed method has no notion of bounding boxes, region proposals, or sliding windows. We evaluate our method with three datasets designed to locate people's heads, pupil centers and plant centers. We outperform state-of-the-art generic object detectors and methods fine-tuned for pupil tracking.

关键词： Categorization recognition: detection Retrieval

来源：评论

学校读者我要写书评

暂无评论

Stochastic Class-based Hard Example Mining for Deep Metric Learning 32

Stochastic Class-based Hard Example Mining for Deep Metric L...

引用

32nd IEEE/CVF Conference on Computer Vision and Pattern recognition (CVPR)

作者： Suh, Yumin Han, Bohyung Kim, Wonsik Lee, Kyoung Mu Seoul Natl Univ ECE Seoul South Korea Seoul Natl Univ ASRI Seoul South Korea Samsung Res Samsung Elect Seoul South Korea

ISBN: (纸本)9781728132938

Performance of deep metric learning depends heavily on the capability of mining hard negative examples during training. However many metric learning algorithms often require intractable computational cost due to frequent feature computations and nearest neighbor searches in a large-scale *** a result, existing approaches often suffer from trade-off between training speed and prediction accuracy. To alleviate this limitation, we propose a stochastic hard negative mining method. Our key idea is to adopt class signatures that keep track of feature embedding online with minor additional cost during training,and identify hard negative example candidates using the signatures. Given an anchor instance, our algorithm first selects a few hard negative classes based on the class-to-sample distances and then performs a refined search in an instance-level only from the selected classes. As most of the classes are discarded at the first step, it is much more efficient than exhaustive search while effectively mining a large number of hard examples. Our experiment shows that the proposed technique improves image retrieval accuracy substantially;it achieves the state-of-the-art performance on the several standard benchmark datasets.

关键词： Categorization Deep Learning recognition: detection Retrieval

来源：评论

学校读者我要写书评

暂无评论

Polynomial Representation for Persistence Diagram 32

Polynomial Representation for Persistence Diagram

引用

32nd IEEE/CVF Conference on Computer Vision and Pattern recognition (CVPR)

作者： Wang, Zhichao Li, Qian Li, Gang Xu, Guandong Univ New South Wales Sch Elect Engn & Telecommun Sydney NSW Australia Univ Technol Sydney Adv Analyt Inst Sydney NSW Australia Deakin Univ Sch Informat Technol Geelong Vic 3216 Australia

ISBN: (纸本)9781728132938

Persistence diagram (PD) has been considered as a compact descriptor for topological data analysis (TDA). Unfortunately, PD cannot be directly used in machine learning methods since it is a multiset of points. Recent efforts have been devoted to transforming PDs into vectors to accommodate machine learning methods. However, they share one common shortcoming: the mapping of PDs to a feature representation depends on a pre-defined polynomial. To address this limitation, this paper proposes an algebraic representation for PDs, i.e., polynomial representation. In this work, we discover a set of general polynomials that vanish on vectorized PDs and extract the task-adapted feature representation from these polynomials. We also prove two attractive properties of the proposed polynomial representation, L e., stability and linear separability. Experiments also show that our method compares favorably with state-of-the-art TDA methods.

关键词： Biological and Cell Microscopy Categorizat Computer Vision Theory Medical recognition: detection Representation 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39页 << < 10 11 12 13 14 15 16 17 18 19 > >>

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：