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

196 篇 会议
63 篇 期刊文献
1 册 图书

馆藏范围

260 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

152 篇 工学
- 73 篇 计算机科学与技术...
- 65 篇 软件工程
- 45 篇 机械工程
- 25 篇 控制科学与工程
- 21 篇 光学工程
- 20 篇 信息与通信工程
- 16 篇 仪器科学与技术
- 11 篇 生物工程
- 9 篇 电子科学与技术（可...
- 9 篇 交通运输工程
- 6 篇 电气工程
- 5 篇 公安技术
- 4 篇 化学工程与技术
- 3 篇 力学（可授工学、理...
- 2 篇 材料科学与工程（可...
- 2 篇 船舶与海洋工程
- 2 篇 林业工程
- 2 篇 安全科学与工程
61 篇 理学
- 30 篇 物理学
- 20 篇 数学
- 11 篇 生物学
- 8 篇 系统科学
- 4 篇 化学
- 4 篇 统计学（可授理学、...
- 2 篇 海洋科学
13 篇 管理学
- 10 篇 管理科学与工程(可...
- 2 篇 图书情报与档案管...
3 篇 法学
- 2 篇 社会学
- 1 篇 民族学
2 篇 文学
1 篇 教育学
- 1 篇 心理学(可授教育学...
1 篇 农学
1 篇 医学
1 篇 艺术学

主题

19 篇 training
17 篇 feature extracti...
11 篇 cameras
10 篇 visualization
9 篇 object detection
9 篇 trajectory
9 篇 vehicles
8 篇 task analysis
8 篇 computer vision
8 篇 data models
7 篇 image segmentati...
7 篇 planning
7 篇 predictive model...
6 篇 optimization
6 篇 semantics
6 篇 machine learning
6 篇 shape
6 篇 robustness
5 篇 legged locomotio...
5 篇 semantic segment...

机构

27 篇 key lab of machi...
12 篇 key laboratory o...
11 篇 peng cheng labor...
10 篇 key laboratory o...
10 篇 school of mathem...
10 篇 key lab. of mach...
9 篇 huawei noah's ar...
9 篇 zhejiang lab
8 篇 sensetime resear...
8 篇 state key lab of...
8 篇 noah's ark lab h...
7 篇 key laboratory o...
7 篇 engineering lab ...
7 篇 key lab. of mach...
7 篇 institute of cir...
7 篇 s-lab nanyang te...
6 篇 key lab. of mach...
6 篇 key lab of machi...
6 篇 key laboratory o...
5 篇 school of comput...

作者

30 篇 hong liu
26 篇 hongbin zha
24 篇 zhouchen lin
20 篇 huijing zhao
18 篇 yisen wang
14 篇 chao xu
13 篇 yunhe wang
13 篇 dingsheng luo
13 篇 chang xu
13 篇 xihong wu
13 篇 liu hong
10 篇 zha hongbin
10 篇 boxin shi
10 篇 jinshi cui
10 篇 lin zhouchen
9 篇 donghao xu
8 篇 li xiangtai
8 篇 chunjing xu
7 篇 li xia
7 篇 franck guillemar...

语言

254 篇 英文
5 篇 中文
1 篇 其他

检索条件"机构=Key Lab of Machine Perception"

共 260 条记录，以下是71-80 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：

Homogeneous Architecture Augmentation for Neural Predictor

Homogeneous Architecture Augmentation for Neural Predictor

引用

International Conference on Computer Vision (ICCV)

作者： Yuqiao Liu Yehui Tang Yanan Sun College of Computer Science Sichuan University Key Lab of Machine Perception (MOE) Peking University

ISBN: (纸本)9781665428132

Neural Architecture Search (NAS) can automatically design well-performed architectures of Deep Neural Networks (DNNs) for the tasks at hand. However, one bottleneck of NAS is the prohibitively computational cost largely due to the expensive performance evaluation. The neural predictors can directly estimate the performance without any training of the DNNs to be evaluated, thus have drawn increasing attention from researchers. Despite their popularity, they also suffer a severe limitation: the shortage of annotated DNN architectures for effectively training the neural predictors. In this paper, we proposed Homogeneous Architecture Augmentation for Neural Predictor (HAAP) of DNN architectures to address the issue aforementioned. Specifically, a homogeneous architecture augmentation algorithm is proposed in HAAP to generate sufficient training data taking the use of homogeneous representation. Furthermore, the one-hot encoding strategy is introduced into HAAP to make the representation of DNN architectures more effective. The experiments have been conducted on both NAS-Benchmark-101 and NAS-Bench-201 dataset. The experimental results demonstrate that the proposed HAAP algorithm outperforms the state of the arts compared, yet with much less training data. In addition, the ablation studies on both benchmark datasets have also shown the universality of the homogeneous architecture augmentation. Our code has been made available at https://***/lyq998/HAAP.

关键词： Training Performance evaluation Deep learning Neural networks Training data Computer architecture Transforms

来源：评论

学校读者我要写书评

暂无评论

TWO-LEVEL MULTI-TASK METRIC LEARNING WITH APPLICATION TO MULTI-CLASSIFICATION

TWO-LEVEL MULTI-TASK METRIC LEARNING WITH APPLICATION TO MUL...

引用

IEEE International Conference on Image Processing

作者： Hong Liu Xuewu Zhang Pingping Wu Key Laboratory of Machine Perception (Ministry of Education) Engineering Lab on Intelligent Perception for Internet of Things (ELIP) Shenzhen Graduate School Peking University

ISBN: (纸本)9781479983407

Many metric learning approaches neglect that the real world multi-class problems share strong visual similarities, which can be exploited by learning discriminative models. In this paper, a Two-level Multi-task Metric Learning (TMTL) method is presented to learn a distance measure from equivalence constraints. Multiple features are adopted to represent the image information and learn the distance matrices in the first level. Then the task-specific learning paradigm and multi-task voting mechanism make full use of pairwise equivalence labels, which induces knowledge from anonymous pairs to multi-classification. Experiments are conducted on two challenging benchmarks PubFig and OuluVS for face identification and lipreading respectively. The results demonstrate that our method outperforms the recent multi-task learning approaches and multi-class support vector machine.

关键词： Metric Learning Multi-task Learning Face Identification Lipreading

来源：评论

学校读者我要写书评

暂无评论

Driver Identification through Multi-state Car Following Modeling

Driver Identification through Multi-state Car Following Mode...

引用

International Conference on Intelligent Transportation

作者： Zhezhang Ding Donghao Xu Huijing Zhao Mathieu Moze François Aioun Franck Guillemard Key Lab of Machine Perception (MOE) Peking University Beijing China Groupe PSA Velizy France

ISBN: (纸本)9781538670255

Driver profiling and characterization is one of the key issues that models heterogeneities inter- and/or intradrivers' behaviors, which forms the basis of many applications such as driver identification, abnormal driving state awareness, personalized driving assistance, etc. This research proposes a driver identification method through multi-state car following modeling, where a GMM (Gaussian Mixture Model) is used to model the internal stochasticity of an individual driver using a mixture of Gaussian kernels, a driver profile is defined to describe the probabilities of a car following behavior being operated by each registered driver, a projection matrix is learned to project a feature vector to a lower dimensional space that has the best discriminative nature for GMM modeling, driver profiling and ID prediction. Experiments are conducted using the naturalistic driving data that are collected on the motorways in Beijing, where a dataset of eight-drivers' car-following data is generated. Promising results are demonstrated and the performance of driver identification on different aspects are examined.

关键词： Automobiles Acceleration Feature extraction Predictive models Kernel Manganese

来源：评论

学校读者我要写书评

暂无评论

SDM-BSM: A FUSING DEPTH SCHEME FOR HUMAN ACTION RECOGNITION

SDM-BSM: A FUSING DEPTH SCHEME FOR HUMAN ACTION RECOGNITION

引用

IEEE International Conference on Image Processing

作者： Hong Liu Lu Tian Mengyuan Liu Hao Tang Engineering Lab on Intelligent Perception for Internet of Things (ELIP) Shenzhen Graduate School Key Laboratory of Machine Perception (Ministry of Education) Peking University

ISBN: (纸本)9781479983407

Depth map has shown promising capability in human action recognition, however it always be auxiliary of RGB features in previous work. As to sufficiently exploring depth map, we propose an innovative descriptor for human action recognition using solo depth data. First, Salient Depth Map (SDM) is calculated between two consecutive depth frames, which is superior for action description as it is located on salient moving objects. Moreover, Binary Shape Map (BSM) is proposed to depict the silhouettes induced by the lateral component of the scene action parallel to the image plane. Then, for implementation, a new framework as Bag-of-Map-Words is employed after concatenating SDM and BSM feature vectors. Experiments on NHA database demonstrate the superiority and high efficiency of the proposed method. We also give detailed comparisons with other features and analysis for parameters as a guidance of further applications.

关键词： Human action recognition Bag of Words Salient feature Solo depth information Facial Recognition MAPPING(MATHEMATICAL) maps BSM space division multiplexing image plane red-green-blue colour model biological control

来源：评论

学校读者我要写书评

暂无评论

SPONTANEOUS VERSUS POSED SMILE RECOGNITION USING DISCRIMINATIVE LOCAL SPATIAL-TEMPORAL DESCRIPTORS

SPONTANEOUS VERSUS POSED SMILE RECOGNITION USING DISCRIMINAT...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Pingping Wu Hong Liu Xuewu Zhang Engineering Lab on Intelligent Perception for Internet of Things (ELIP) Key Laboratory of Machine Perception and Intelligence Shenzhen Graduate School Peking University China

ISBN: (纸本)9781479928941

Automatic recognition of spontaneous versus posed (SVP) facial expressions has received widespread attention in recent years for its potential applications in friendly human machine interface. Most existing works of SVP facial expression recognition extract geometry-based features which heavily rely on accurate detection and tracking of facial feature points. In this paper, a novel approach is proposed to distinguish between spontaneous and posed smiles using discriminative completed LBP from three orthogonal planes, which is an appearance-based local spatial-temporal descriptor. The descriptor devotes to extracting most robust and discriminative patterns of interest. In addition, flexible facial subregion cropping, a spatial division method, is proposed taking into account different facial organ size of different people and filtering of redundant information. Besides, in the temporal domain, a new division method is also applied, which divides the smile process according to smile dynamics. Experiments on three benchmark databases and comparisons to the state-of-the-art methods validate the advantages of our approach, obtaining an accuracy rate of 91.40%.

关键词： Feature extraction Power capacitors Databases Face recognition Face Conferences Robustness

来源：评论

学校读者我要写书评

暂无评论

REGRESSION BASED LANDMARK ESTIMATION AND MULTI-FEATURE FUSION FOR VISUAL SPEECH RECOGNITION

REGRESSION BASED LANDMARK ESTIMATION AND MULTI-FEATURE FUSIO...

引用

IEEE International Conference on Image Processing

ISBN: (纸本)9781479983407

Visual speech recognition also known as lipreading can improve robustness of automatic acoustic speech recognition e-specially under noisy environments. However, it remains a challenging topic considering the variety of speaking characteristics and confusion between visual speech features. In this paper, we propose an automatic lipreading method by using a new lip tracking method and multiple visual information fusion to tackle the problem. First, a method of face landmark estimation based on regression is employed for lip detection, based on which a geometric-based shape invariant feature (SIF) is put forward. Moreover, it can also be applied to the removal of the non-speaking utterance. Then the motion interchange patterns and spatial-temporal descriptors are also adopted to describe the lip information, where the Bayes combination strategy is applied. The proposed method is explored on three benchmark data sets: Avletters2, OuluVS and PKUVS. Experimental results demonstrate promising results and show effectiveness of the proposed approach.

关键词： Visual Speech Recognition Shape Invariant Features Motion Interchange Patterns Bayes Combination Speech recognition Lipreading Visualization Fusion reactions FUSION fusion (melting) Fusion, biological lip Confusion Noisy environment Information fusion

来源：评论

学校读者我要写书评

暂无评论

ACTION CLASSIFICATION BY EXPLORING DIRECTIONAL CO-OCCURRENCE OF WEIGHTED STIPS

ACTION CLASSIFICATION BY EXPLORING DIRECTIONAL CO-OCCURRENCE...

引用

IEEE International Conference on Image Processing

作者： Mengyuan Liu Hong Liu Qianru Sun Engineering Lab on Intelligent Perception for Internet of Things (ELIP) Shenzhen Graduate School Key Laboratory of Machine Perception (Ministry of Education) Peking University

ISBN: (纸本)9781479957521

Human action recognition is challenging mainly due to intro-variety, inter-ambiguity and clutter backgrounds in real videos. Bag-of-visual words model utilizes spatio-temporal interest points (STIPs), and represents action by the distribution of points which ignores visual context among points. To add more contextual information, we propose a method by encoding spatio-temporal distribution of weighted pairwise points. First, STIPs are extracted from an action sequence and clustered into visual words. Then, each word is weighted in both temporal and spatial domains to capture the relation-ships with other words. Finally, the directional relationships between co-occurrence pairwise words are used to encode visual contexts. We report state-of-the-art results on Rochester and UT-Interaction datasets to validate that our method can classify human actions with high accuracies.

关键词： Spatio-temporal interest point Bag-of-visual words Co-occurrence

来源：评论

学校读者我要写书评

暂无评论

A Human-like Trajectory Planning Method by Learning from Naturalistic Driving Data

A Human-like Trajectory Planning Method by Learning from Nat...

引用

IEEE Symposium on Intelligent Vehicle

作者： Xu He Donghao Xu Huijing Zhao Mathieu Moze François Aioun Franck Guillemard Key Lab of Machine Perception (MOE) Peking University Beijing China Groupe PSA Velizy France

Trajectory planning has generally been framed as finding the lowest cost one from a set of trajectory candidates, where the cost function has been hand-crafted with carefully tuned parameters by experts. Such methods have technological feasibility of achieving vehicle autonomy, while the resultant behaviors could be much different with those of human drivers. This research proposes a humanlike trajectory planning method by learning from naturalistic driving data. A cost function is formulated by incorporating not only the components on comfort, efficiency and safety, but also lane incentive by referring to a human driver's lane change decisions. Coefficients of the cost components are learnt by correlating the probability of a trajectory being selected with its distance (i.e. similarity) to the human driven one at the same driving situation. A data set is developed by using the naturalistic data of human drivers on the motorways in Beijing, containing samples of lane changes to the left and right lanes, and car followings. Experiments are conducted on three aspects: 1) lane change trajectory planning to a given target lane; 2) lane change trajectory planning with simultaneous decision of a target lane; and 3) trajectory planning with simultaneous decision of maneuver. Promising results are presented.

关键词： Trajectory Planning Cost function Autonomous vehicles Safety Automobiles

来源：评论

学校读者我要写书评

暂无评论

Vision based algorithm for automatic recognition of cutting line of clothes label tapes

Vision based algorithm for automatic recognition of cutting ...

引用

Proceedings of 2002 International Conference on machine Learning and Cybernetics

作者： Yu, Mei Jiang, Gang-Yi He, Sai-Long Yang, Ming Yu, Bo-Kang Institute of Circuits and Systems Ningbo University Ningbo 315211 China Natl. Key Lab. of Machine Perception Peking University Beijing 100871 China Hangzhou Inst. of Electronic Eng. Hangzhou 310037 China

ISBN: (纸本)0780375084

In this paper, an algorithm of recognizing cutting line of clothes labels tape is proposed, which applies vertical edge detection and distance filter to remove noise and locate the cutting line in image. The proposed algorithm is able to calculate the parameters of the cutting line accurately, and can be used in automatic system for clothes labels cutting, so that the manufacture efficiency is improved while the operating cost is decreased compared with handiwork.

关键词： Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Video object segmentation and disparity estimation in stereoscopic coding

Video object segmentation and disparity estimation in stereo...

引用

IEEE TENCON 2004 - 2004 IEEE Region 10 Conference: Analog and Digital Techniques in Electrical Engineering

作者： Jiang, Gangyi Ye, Xien Yu, Mei Kim, Yong-Deak Choi, Tae-Young Institute of Circuits and Systems Ningbo University Ningbo 315211 China Division of Electronics Engineering Ajou University Suwon 442-749 Korea Republic of National Key Lab. of Machine Perception Peking University Beijing 100871 China

In this paper, a new method of video object segmentation and disparity estimation is proposed for stereoscopic videoconference. The object in left view is first extracted by motion detection combined with spatial segmentation based on improved watershed algorithm, while the corresponding object in right view is extracted by contour correspondence from the left one. After that, precise disparity estimation is implemented for some significant pixels of the object, while disparities of other pixels of the object are interpolated with the precise ones. Compared with traditional block-based algorithms, more precise and smooth disparity field can be finally acquired by the proposed method. ©2004IEEE.

关键词： Image segmentation

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26页 << < 4 5 6 7 8 9 10 11 12 13 > >>

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：