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

141 篇 会议
40 篇 期刊文献
3 册 图书

馆藏范围

184 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

101 篇 工学
- 47 篇 计算机科学与技术...
- 44 篇 软件工程
- 22 篇 机械工程
- 22 篇 光学工程
- 19 篇 信息与通信工程
- 15 篇 生物医学工程（可授...
- 15 篇 生物工程
- 14 篇 控制科学与工程
- 7 篇 仪器科学与技术
- 7 篇 电气工程
- 7 篇 土木工程
- 6 篇 电子科学与技术（可...
- 6 篇 建筑学
- 5 篇 化学工程与技术
- 3 篇 安全科学与工程
- 2 篇 力学（可授工学、理...
52 篇 理学
- 18 篇 数学
- 17 篇 物理学
- 17 篇 生物学
- 5 篇 系统科学
- 4 篇 化学
- 3 篇 地球物理学
- 3 篇 统计学（可授理学、...
18 篇 管理学
- 11 篇 图书情报与档案管...
- 6 篇 管理科学与工程(可...
- 2 篇 工商管理
6 篇 医学
- 6 篇 临床医学
- 5 篇 基础医学(可授医学...
- 4 篇 药学(可授医学、理...
5 篇 法学
- 5 篇 社会学
1 篇 农学
1 篇 艺术学

主题

24 篇 feature extracti...
20 篇 training
17 篇 cameras
12 篇 computer vision
10 篇 histograms
10 篇 robustness
9 篇 support vector m...
9 篇 vectors
9 篇 visualization
9 篇 kernel
8 篇 pipelines
8 篇 clustering algor...
7 篇 hidden markov mo...
7 篇 three-dimensiona...
7 篇 computational mo...
7 篇 pattern recognit...
7 篇 measurement
6 篇 deep learning
6 篇 lighting
6 篇 estimation

机构

30 篇 pattern analysis...
19 篇 pattern analysis...
14 篇 pattern analysis...
12 篇 pattern analysis...
12 篇 neuroinformatics...
9 篇 department of co...
9 篇 department of co...
8 篇 pattern analysis...
7 篇 pattern analysis...
7 篇 textual and visu...
6 篇 university of ge...
6 篇 university of ve...
4 篇 huawei technolog...
3 篇 school of automa...
3 篇 diten university...
3 篇 adobe research
3 篇 pattern analysis...
3 篇 istituto italian...
3 篇 computer vision ...
3 篇 university of tr...

作者

54 篇 vittorio murino
30 篇 alessio del bue
28 篇 murino vittorio
15 篇 pietro morerio
13 篇 morerio pietro
12 篇 del bue alessio
10 篇 diego sona
10 篇 marco cristani
8 篇 marco crocco
8 篇 sona diego
8 篇 alessandro perin...
7 篇 v. murino
7 篇 ryad chellali
7 篇 beyan cigdem
7 篇 loris bazzani
6 篇 florent perronni...
6 篇 cristani marco
6 篇 samuele martelli
5 篇 andrea trucco
5 篇 moin nabi

语言

181 篇 英文
3 篇 其他

检索条件"机构=Pattern Analysis and Computer Vision"

共 184 条记录，以下是51-60 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：

Leveraging Acoustic Images for Effective Self-supervised Audio Representation Learning 1

引用

16th European Conference on computer vision, ECCV 2020

作者： Sanguineti, Valentina Morerio, Pietro Pozzetti, Niccolò Greco, Danilo Cristani, Marco Murino, Vittorio Pattern Analysis and Computer Vision Istituto Italiano di Tecnologia Genoa Italy University of Genova Genoa Italy Huawei Technologies Ltd. Ireland Research Center Dublin Ireland University of Verona Verona Italy

ISBN: (数字)9783030585426

ISBN: (纸本)9783030585419

In this paper, we propose the use of a new modality characterized by a richer information content, namely acoustic images, for the sake of audio-visual scene understanding. Each pixel in such images is characterized by a spectral signature, associated to a specific direction in space and obtained by processing the audio signals coming from an array of microphones. By coupling such array with a video camera, we obtain spatio-temporal alignment of acoustic images and video frames. This constitutes a powerful source of self-supervision, which can be exploited in the learning pipeline we are proposing, without resorting to expensive data annotations. However, since 2D planar arrays are cumbersome and not as widespread as ordinary microphones, we propose that the richer information content of acoustic images can be distilled, through a self-supervised learning scheme, into more powerful audio and visual feature representations. The learnt feature representations can then be employed for downstream tasks such as classification and cross-modal retrieval, without the need of a microphone array. To prove that, we introduce a novel multimodal dataset consisting in RGB videos, raw audio signals and acoustic images, aligned in space and synchronized in time. Experimental results demonstrate the validity of our hypothesis and the effectiveness of the proposed pipeline, also when tested for tasks and datasets different from those used for training. © 2020, Springer Nature Switzerland AG.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Temporal Poselets for Collective Activity Detection and Recognition

Temporal Poselets for Collective Activity Detection and Reco...

引用

International Conference on computer vision Workshops (ICCV Workshops)

作者： Moin Nabi Alessio Del Bue Vittorio Murino Pattern Analysis and Computer Vision (PAVIS) Istituto Italiano di Tecnologia (IIT) Genova Italy

Detection and recognition of collective human activities are important modules of any system devoted to high level social behavior analysis. In this paper, we present a novel semantic-based spatio-temporal descriptor which can cope with several interacting people at different scales and multiple activities in a video. Our descriptor is suitable for modelling the human motion interaction in crowded environments - the scenario most difficult to analyse because of occlusions. In particular, we extend the Pose let detector approach by defining a descriptor based on Pose let activation patterns over time, named TPOS. We will show that this descriptor can effectively tackle complex real scenarios allowing to detect humans in the scene, to localize (in space-time) human activities, and perform collective group activity recognition in a joint manner, reaching state-of-the-art results.

关键词： Detectors Feature extraction Video sequences Vectors Context Semantics Torso

来源：评论

学校读者我要写书评

暂无评论

Violence detection in crowded scenes using substantial derivative

Violence detection in crowded scenes using substantial deriv...

引用

IEEE Conference on Advanced Video and Signal Based Surveillance (AVSS)

作者： Sadegh Mohammadi Hamed Kiani Alessandro Perina Vittorio Murino Pattern Analysis and Computer Vision Department (PAVIS) Istituto Italiano di Tecnologia Genova Italy

This paper presents a novel video descriptor based on substantial derivative, an important concept in fluid mechanics, that captures the rate of change of a fluid property as it travels through a velocity field. Unlike standard approaches that only use temporal motion information, our descriptor exploits the spatio-temporal characteristic of substantial derivative. In particular, the spatial and temporal motion patterns are captured by respectively the convective and local accelerations. After estimating the convective and local field from the optic flow, we followed the standard bag-of-word procedure for each motion pattern separately, and we concatenated the two resulting histograms to form the final descriptor. We extensively evaluated the effectiveness of the proposed method on five benchmarks, including three standard datasets (Violence in Movies, Violence In Crowd, and BEHAVE), and two new video-survelliance sequences downloaded from Youtube. Our experiments show how the proposed approach sets the new state-of-the-art on all benchmarks and how the structural information captured by convective acceleration is essential to detect violent episodes in crowded scenarios.

关键词： Force Acceleration Standards Motion pictures Video sequences Trajectory Dynamics

来源：评论

学校读者我要写书评

暂无评论

PRAGO: Differentiable Multi-View Pose Optimization From Objectness Detections*

PRAGO: Differentiable Multi-View Pose Optimization From Obje...

引用

International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission (3DIMPVT)

作者： Matteo Taiana Matteo Toso Stuart James Alessio Del Bue Pattern Analysis and Computer Vision (PAVIS) Istituto Italiano di Tecnologia (IIT) Genoa Italy

ISBN: (数字)9798350362459

ISBN: (纸本)9798350362466

Robustly estimating camera poses from a set of images is a fundamental task which remains challenging for differentiable methods, especially in the case of small and sparse camera pose graphs. To overcome this challenge, we propose Pose-refined Rotation Averaging Graph Optimization (PRAGO). From a set of objectness detections on unordered images, our method reconstructs the rotational pose, and in turn, the absolute pose, in a differentiable manner benefiting from the optimization of a sequence of geometrical tasks. We show how our objectness pose-refinement module in PRAGO is able to refine the inherent ambiguities in pairwise relative pose estimation without removing edges and avoiding making early decisions on the viability of graph edges. PRAGO then refines the absolute rotations through iterative graph construction, reweighting the graph edges to compute the final rotational pose, which can be converted into absolute poses using translation averaging. We show that PRAGO is able to outperform non-differentiable solvers on small and sparse scenes extracted from 7-Scenes achieving a relative improvement of 21% for rotations while achieving similar translation estimates.

关键词： Three-dimensional displays Image edge detection Pose estimation Focusing Cameras Iterative methods Task analysis

来源：评论

学校读者我要写书评

暂无评论

Learning unbiased classifiers from biased data with meta-learning

Learning unbiased classifiers from biased data with meta-lea...

引用

IEEE computer Society Conference on computer vision and pattern Recognition Workshops (CVPRW)

作者： Ruggero Ragonesi Pietro Morerio Vittorio Murino Pattern Analysis and Computer Vision (PAVIS) - Istituto Italiano di Tecnologia Department of Computer Science University of Verona

It is well known that large deep architectures are powerful models when adequately trained, but may exhibit undesirable behavior leading to confident incorrect predictions, even when evaluated on slightly different test examples. Test data characterized by distribution shifts (from training data distribution), outliers, and adversarial samples are among the types of data affected by this problem. This situation worsens whenever data are biased, meaning that predictions are mostly based on spurious correlations present in the data. Unfortunately, since such correlations occur in the most of data, a model is prevented from correctly generalizing the considered classes. In this work, we tackle this problem from a meta-learning perspective. Considering the dataset as composed of unknown biased and unbiased samples, we first identify these two subsets by a pseudo-labeling algorithm, even if coarsely. Subsequently, we apply a bi-level optimization algorithm in which, in the inner loop, we look for the best parameters guiding the training of the two subsets, while in the outer loop, we train the final model taking benefit from augmented data generated using Mixup. Properly tuning the contributions of biased and unbiased data, together with the regularization introduced by the mixed data has proved to be an effective training strategy to learn unbiased models, showing superior generalization capabilities. Experimental results on synthetically and realistically biased datasets surpass state-of-the-art performance, as compared to existing methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning with Dataset Bias in Latent Subcategory Models

Learning with Dataset Bias in Latent Subcategory Models

引用

IEEE Conference on computer vision and pattern Recognition

作者： Dimitris Stamos Andrew McDonald Samuele Martelli Vittorio Murino Moin Nabi Massimiliano Pontil Department of Computer Science University College London Pattern Analysis & Computer Vision Istituto Italiano di Tecnologia

ISBN: (纸本)9781467369657

Latent subcategory models (LSMs) offer significant improvements over training linear support vector machines (SVMs). Training LSMs is a challenging task due to the potentially large number of local optima in the objective function and the increased model complexity which requires large training set sizes. Often, larger datasets are available as a collection of heterogeneous datasets. However, previous work has highlighted the possible danger of simply training a model from the combined datasets, due to the presence of bias. In this paper, we present a model which jointly learns an LSM for each dataset as well as a compound LSM. The method provides a means to borrow statistical strength from the datasets while reducing their inherent bias. In experiments we demonstrate that the compound LSM, when tested on PASCAL, LabelMe, Caltech101 and SUN09 in a leave-one-dataset-out fashion, achieves an average improvement of over 6.5% over a previous SVM-based undoing bias approach and an average improvement of over 8.5% over a standard LSM trained on the concatenation of the datasets.

关键词： Dataset Linux Security Module Bias Bias Bias Statistical Biases bias(electronics) Functional training Support Vector Network Objective function Learning train stock

来源：评论

学校读者我要写书评

暂无评论

A comparison of crowd commotion measures from generative models

A comparison of crowd commotion measures from generative mod...

引用

IEEE computer Society Conference on computer vision and pattern Recognition Workshops (CVPRW)

作者： Sadegh Mohammadi Hamed Kiani Alessandro Perina Vittorio Murino Pattern Analysis and Computer Vision Department (PAVIS) Istituto Italiano di Tecnologia Genova Italy

Detecting abnormal events in video sequences is a challenging task that has been broadly investigated over the last decade. The main challenges come from the lack of a clear definition of abnormality and from the scarcity, often absence, of abnormal training samples. To address these two shortages, the computer vision community made use of generative models to learn normal behavioral patterns in videos. Then, for each test observation, a (crowd) commotion measure is computed quantifying the deviation from the normal model. In this paper, we evaluated two different families of generative models, namely topic models, representing the standard choice, and the most recent Counting Grids which have never been considered for this task. Moreover, we also extended the 2D Counting Grid, introduced for the analysis of images, to three dimensions, making the model able to capture the spatial-temporal relationships of the videos. In the experimental section, we compared all the approaches on five challenging sequences showing the superiority of the 3-D counting grid.

关键词： Computational modeling Cameras Feature extraction Histograms Surveillance Context Video sequences

来源：评论

学校读者我要写书评

暂无评论

Low-level multimodal integration on Riemannian manifolds for automatic pedestrian detection

Low-level multimodal integration on Riemannian manifolds for...

引用

International Conference on Information Fusion

作者： Marco San-Biagio Marco Crocco Marco Cristani Samuele Martelli Vittorio Murino Pattern Analysis & Computer Vision (PAVIS) Istituto Italiano di Tecnologia (lIT) Genova Italy

In computer vision, automated pedestrian detection is surely one of the hottest topics, with important applications in surveillance and security. To this end, information integration from different imaging modalities, such as thermal infrared and visible spectrum, can significantly improve the detection rate with respect to monomodal strategies. A common scheme consists of extracting two sets of features, from thermal and visible images of the same scene respectively, and stacking them together into a single feature set, ignoring possible and meaningful inter-media dependencies. Here we propose a fusion scheme which acts at the feature-level, taking standard pixel characteristics (such as first/second order spatial derivatives or Local Binary pattern) and designing a composite descriptor that, at the same time, encodes the information coming from the separate modalities, as well as the cross-modal mutual relationships in the form of covariances. The descriptor, which lies on a Riemannian manifold, is projected onto a Euclidean tangent space and then fed into a Support Vector Machine classifier. Experiments performed on the OTCBVS dataset [1], and validated statistically, demonstrate that our method outperforms significantly the single modality policies as well as different fusion schemes at the pixel, feature and decision level.

关键词： Feature extraction Covariance matrix Imaging Vectors Standards Training Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Latent subcategory models for pedestrian detection with partial occlusion handling

Latent subcategory models for pedestrian detection with part...

引用

IEEE Conference on Advanced Video and Signal Based Surveillance (AVSS)

作者： Samuele Martelli Marco San Biagio Vittorio Murino Pattern Analysis & Computer Vision (PAVIS) Istituto Italiano di Tecnologia Genova Italy Pattern Analysis & Computer Vision (PAVIS) Istituto Italiano di Tecnologia Genova Liguria IT Universita degli Studi di Verona Verona Italy

Pedestrian detection is one of the most important tasks in computer vision, especially in automotive and security applications. One of the most common problems in real scenarios is related to the detection of occluded pedestrians. In this paper, we propose a novel multi-cue pedestrian detection approach able to deal with non homogeneous object samples by learning latent subcategory models trained on both visual and depth-based features. We also propose a novel self-similarity based feature, namely SST D , to encode the homogeneity in appearance of pedestrians characterized by similar occlusion patterns. Experiments are performed on the Daimler Pedestrian Detection Benchmark Dataset showing the robustness of our approach in actual scenarios.

关键词： Support vector machines Training Histograms Feature extraction Standards Computational modeling Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Visualization of High Dimensional Data using an Automated 3D Star Co-ordinate System

Visualization of High Dimensional Data using an Automated 3D...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： J.S. Shaik M. Yeasin Computer Vision Pattern and Image Analysis Laboratory Electrical and Computer Engineering University of Memphis Memphis TN USA

This paper presents a 3D star coordinate-based visualization technique for exploratory data analysis. To improve the data visualization and reveal the hidden patterns in complex high dimensional data sets, first the 2D star coordinate system is extended to the 3D star coordinate system. An autonomous procedure is defined to find the best configuration for the 3D star coordinate system based on cluster validation measures. To illustrate the efficacy of the proposed techniques, empirical analysis were conducted on a number of synthetic (Five dimensional Gaussian distribution with three classes) and real (Fisher's IRIS, Leukemia, Gastric cancer and Petroleum datasets) databases. Empirical analyses shows that automated 3D star coordinate system helps in better visualization of the complex high dimensional data when compared to 2D star coordinate system and also other projection-based visualization techniques. Also the automated configuration for 3D star coordinate system reveals the hidden patterns in the complex datasets without human intervention.

关键词： Data visualization Data analysis Data mining Visual databases Humans computer vision Image analysis Laboratories Coordinate measuring machines Gaussian distribution

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19页 << < 2 3 4 5 6 7 8 9 10 11 > >>

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：