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

1,585 篇 会议
83 册 图书
16 篇 期刊文献

馆藏范围

1,684 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,044 篇 工学
- 875 篇 计算机科学与技术...
- 468 篇 软件工程
- 226 篇 信息与通信工程
- 186 篇 电气工程
- 100 篇 生物工程
- 98 篇 生物医学工程（可授...
- 84 篇 控制科学与工程
- 62 篇 光学工程
- 35 篇 机械工程
- 35 篇 电子科学与技术（可...
- 24 篇 仪器科学与技术
- 23 篇 化学工程与技术
- 21 篇 建筑学
- 21 篇 土木工程
- 20 篇 材料科学与工程（可...
- 20 篇 安全科学与工程
- 19 篇 交通运输工程
352 篇 理学
- 175 篇 数学
- 114 篇 生物学
- 88 篇 物理学
- 52 篇 统计学（可授理学、...
- 35 篇 系统科学
- 21 篇 化学
176 篇 管理学
- 92 篇 图书情报与档案管...
- 89 篇 管理科学与工程(可...
- 45 篇 工商管理
113 篇 医学
- 91 篇 临床医学
- 61 篇 基础医学(可授医学...
- 34 篇 药学(可授医学、理...
33 篇 法学
- 26 篇 社会学
17 篇 教育学
12 篇 经济学
8 篇 农学
3 篇 军事学
3 篇 艺术学
2 篇 文学

主题

238 篇 pattern recognit...
79 篇 cloud computing
74 篇 artificial intel...
71 篇 training
57 篇 feature extracti...
55 篇 neural networks
52 篇 machine learning
49 篇 deep learning
40 篇 computer archite...
36 篇 data mining
34 篇 computer imaging...
33 篇 pattern matching
33 篇 computer vision
32 篇 semantics
29 篇 image segmentati...
28 篇 computational mo...
28 篇 image recognitio...
28 篇 image processing...
27 篇 information syst...
26 篇 edge computing

机构

15 篇 school of comput...
15 篇 university of ch...
9 篇 school of comput...
8 篇 inria nancy gran...
8 篇 national center ...
8 篇 icube université...
8 篇 fujian key labor...
8 篇 erasmus mc - uni...
8 篇 tencent jarvis l...
8 篇 university of ba...
7 篇 college of intel...
6 篇 univ chinese aca...
6 篇 institute of ima...
6 篇 department of co...
6 篇 the 54th researc...
6 篇 school of artifi...
6 篇 dipartimento di ...
6 篇 dipartimento di ...
6 篇 computational sc...
6 篇 institute of com...

作者

13 篇 tan chew lim
12 篇 wang da-han
11 篇 yang jie
8 篇 stéphane cotin
8 篇 yefeng zheng
8 篇 chew lim tan
8 篇 philippe c. catt...
8 篇 marleen de bruij...
8 篇 stefanie speidel
8 篇 caroline essert
8 篇 nicolas padoy
7 篇 maier andreas
7 篇 yang yang
7 篇 hancock edwin r.
7 篇 rita cucchiara
7 篇 alberto del bimb...
6 篇 hugo jair escala...
6 篇 tao mei
6 篇 lu shijian
6 篇 marco bertini

语言

1,664 篇 英文
18 篇 其他
3 篇 中文

检索条件"任意字段=2021 10th International Conference on Computing and Pattern Recognition"

共 1684 条记录，以下是821-830 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：

MA-LSTM: A Multi-Attention Based LSTM for Complex pattern Extraction

MA-LSTM: A Multi-Attention Based LSTM for Complex Pattern Ex...

引用

international conference on pattern recognition

作者： Jingjie Guo Kelang Tian Kejiang Ye Cheng-Zhong Xu Sun Yat-sen University Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences State Key Lab of IoTSC Faculty of Science and Technology University of Macau

With the improvement of data volume, computing power and algorithms, deep learning has achieved rapid development and showing excellent performance. Recently, many deep learning models are proposed to solve the problems in different areas. A recurrent neural network (RNN) is a class of artificial neural networks where connections between nodes form a directed graph along a temporal sequence. this allows it to exhibit temporal dynamic behavior, which makes it applicable to tasks such as handwriting recognition or speech recognition. However, the RNN relies heavily on the automatic learning ability to update parameters that concentrate on the data flow but seldom considers the feature extraction capability of the gate mechanism. In this paper, we propose a novel architecture to build the forget gate which is generated by multiple bases. Instead of using the traditional single-layer fully-connected network, we use a Multiple Attention (MA) based network to generate the forget gate which refines the optimization space of gate function and improve the granularity of the recurrent neural network to approximate the map in the ground truth. Due to the benefit of MA structure on the gate mechanism, the proposed MA-LSTM model achieves better feature extraction capability than other known models.

关键词： Deep learning Handwriting recognition Recurrent neural networks Computer architecture Speech recognition Logic gates Predictive models

来源：评论

学校读者我要写书评

暂无评论

A BERT-based named entity recognition in chinese electronic medical record 9

A BERT-based named entity recognition in chinese electronic ...

引用

9th international conference on computing and pattern recognition, ICCPR 2020

作者： Wang, Qingchuan Haihong, E. School of Computer Science Beijing University of Posts and Telecommunications Beijing100876 China No.10 Xitucheng Road Haidian District Beijing China

ISBN: (纸本)9781450387835

Named entity recognition, aiming at identifying and classifying named entity mentioned in the structured or unstructured text, is a fundamental subtask for information extraction in natural language processing (NLP). With the development of electronic medical records, obtaining the key and effective information in electronic document through named entity identification has become an increasingly popular research direction. In this article, we adapt a recently introduced pre-trained language model BERT for named entity recognition in electronic medical records to solve the problem of missing context information and we add an extra mechanism to capture the relationship between words. Based on this, (1) the entities can be represented by sentence-level vector, with the forward as well as backward information of the sentence, which can be directly used by downstream tasks;(2) the model acquires the representation of word in context and learn the potential relation between words to decrease the influence of inconsistent entity markup problem of a text. We conduct experiments an electronic medical record dataset proposed by China conference on Knowledge Graph and Semantic computing in 2019. the experimental result shows that our proposed method has an improvement compared with the traditional methods. © 2020 ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

More Correlations Better Performance: Fully Associative Networks for Multi-label Image Classification

More Correlations Better Performance: Fully Associative Netw...

引用

international conference on pattern recognition

作者： Yaning Li Liu Yang College of Intelligence and Computing Tianjin University Tianjin

Recent researches demonstrate that correlation modeling plays a key role in high-performance multi-label classification methods. However, existing methods do not take full advantage of correlation information, especially correlations in feature and label spaces of each image, which limits the performance of correlation-based multi-label classification methods. With more correlations considered, in this study, a Fully Associative Network (FAN) is proposed for fully exploiting correlation information, which involves both visual feature and label correlations. Specifically, FAN introduces a robust covariance pooling to summarize convolution features as global image representation for capturing feature correlation in the multi-label task. Moreover, it constructs an effective label correlation matrix based on a re-weighted scheme, which is fed into a graph convolution network for capturing label correlation. then, correlation between covariance representations (i.e., feature correlation) and the outputs of GCN (i.e., label correlation) are modeled for final prediction. Experimental results on two datasets illustrate the effectiveness and efficiency of our proposed FAN compared with state-of-the-art methods.

关键词： Fans Visualization Correlation Image recognition Convolution Predictive models Image representation

来源：评论

学校读者我要写书评

暂无评论

the DeepHealth Toolkit: A Unified Framework to Boost Biomedical Applications

The DeepHealth Toolkit: A Unified Framework to Boost Biomedi...

引用

international conference on pattern recognition

作者： Michele Cancilla Laura Canalini Federico Bolelli Stefano Allegretti Salvador Carrión Roberto Paredes Jon A. Gómez Simone Leo Marco Enrico Piras Luca Pireddu Asaf Badouh Santiago Marco-Sola Lluc Alvarez Miquel Moreto Costantino Grana Università degli Studi di Modena e Reggio Emilia Italy PRHLT Research Center Universitat Politècnica de València Spain Data-intensive Computing Group CRS4 Italy Barcelona Supercomputing Center Spain Universitat Autònoma de Barcelona Spain Universitat Politècnica de Catalunya Spain

Given the overwhelming impact of machine learning on the last decade, several libraries and frameworks have been developed in recent years to simplify the design and training of neural networks, providing array-based programming, automatic differentiation and user-friendly access to hardware accelerators. None of those tools, however, was designed with native and transparent support for Cloud computing or heterogeneous High-Performance computing (HPC). the DeepHealth Toolkit is an open source Deep Learning toolkit aimed at boosting productivity of data scientists operating in the medical field by providing a unified framework for the distributed training of neural networks, which is able to leverage hybrid HPC and cloud environments in a transparent way for the user. the toolkit is composed of a Computer Vision library, a Deep Learning library, and a front-end for non-expert users; all of the components are focused on the medical domain, but they are general purpose and can be applied to any other field. In this paper, the principles driving the design of the DeepHealth libraries are described, along with details about the implementation and the interaction between the different elements composing the toolkit. Finally, experiments on common benchmarks prove the efficiency of each separate component and of the DeepHealth Toolkit overall.

关键词： Deep learning Training Computer vision Cloud computing Pipelines Neural networks Writing

来源：评论

学校读者我要写书评

暂无评论

Generative Latent Implicit Conditional Optimization when Learning from Small Sample

Generative Latent Implicit Conditional Optimization when Lea...

引用

international conference on pattern recognition

作者： Idan Azuri Daphna Weinshall School of Computer Science and Engineering The Hebrew University Jerusalem Israel

We revisit the long-standing problem of learning from small sample, to which end we propose a novel method called GLICO (Generative Latent Implicit Conditional Optimization). GLICO learns a mapping from the training examples to a latent space, and a generator that generates images from vectors in the latent space. Unlike most recent works, which rely on access to large amounts of unlabeled data, GLICO does not require access to any additional data other than the small set of labeled points. In fact, GLICO learns to synthesize completely new samples for every class using as little as 5 or 10 examples per class, with as few as 10 such classes without imposing any prior. GLICO is then used to augment the small training set while training a classifier on the small sample. To this end our proposed method samples the learned latent space using spherical interpolation, and generates new examples using the trained generator. Empirical results show that the new sampled set is diverse enough, leading to improvement in image classification in comparison with the state of the art, when trained on small samples obtained from CIFAR-10, CIFAR-100, and CUB-200.

关键词： Training Interpolation Generators pattern recognition Optimization Image classification

来源：评论

学校读者我要写书评

暂无评论

Differential sets of cortical muscle synergy signatures during adult locomotion

Differential sets of cortical muscle synergy signatures duri...

引用

international IEEE/EMBS conference on Neural Engineering, CNE

作者： Coen S. Zandvoort Andreas Daffertshofer Nadia Dominici Faculty of Behavioural and Movement Sciences Amsterdam Movement Sciences & Institute of Brain and Behavior Amsterdam Vrije Universiteit Amsterdam Netherlands

Muscle synergy assessments are often employed to evaluate the modular organization of the spinal cord during a locomotion task. While they provide valuable insights into the pattern formation of the a-motoneurons at the spinal cord, by construction they cannot capture control from supra-spinal layers. We examined how locomotor muscle synergies are represented in the sensorimotor cortex, with particular focus on the cortico-synergy coherence as a measure of coupling along the cortico-spinal tract. Non-negative matrix factorization served to decompose multivariate electromyographic signals into muscle synergies. their representations were localized in the cortex using coherence-based beamforming. Overall, the cortico-synergy coherence was maximal in sensorimotor areas especially in the beta-frequency band. However, only for the synergies timed to heel strike, that are related to the double support phases, the coherence was significant. these coherences were closely related to the timing of the activation patterns of the synergies, suggesting sensorimotor cortex to be strongly involved in emergence and control of these synergies.

关键词： Couplings Technological innovation pattern formation Spinal cord Europe Coherence Organizations

来源：评论

学校读者我要写书评

暂无评论

High Resolution Localization and Vertical Angle Scattering Spectrum Reconstruction of Targets in Shallow Water Waveguide

High Resolution Localization and Vertical Angle Scattering S...

引用

10th IEEE international conference on Signal Processing, Communications and computing (IEEE ICSPCC)

作者： Fan, Xiaomeng Zhang, Ting Jiang, Jingning Zhejiang Univ Coll Informat Sci & Elect Engn Hangzhou Peoples R China Zhejiang Univ Coll Informat Sci & Elect Engn Zhejiang Prov Key Lab Informat Proc Informat Proc Commun & Networking IPCN Hangzhou Peoples R China

ISBN: (纸本)9781728172019

In complex ocean environment, reconstructing low-frequency scattering pattern (frequency-angle spectrum) of underwater targets can provide further powerful support for target classification. this paper describes the reconstruction of target scattering pattern with unknown position, from received data on a vertical line array (VLA) in shallow water waveguide. the point spread function (PSF) in conventional matching field processing (CMFP) does not have global strict shift invariance. this paper proves that with the same effective mode number, the PSF retains the shift invariant property and can thus be deconvolved from CMFP by Richardson-Lucy (R-L) algorithm. the proposed deconvolved matched field processing (DMFP) can achieve high resolution along both range and depth direction and low side lobes. By using the estimated target range and depth, and the estimated mode amplitude at each frequency by mode decomposition, the broadband target scattering spectrum with respect to vertical angle is accurately reconstructed with moderate number of modes.

关键词： deconvolved matched field processing mode decomposition scattering pattern reconstruction

来源：评论

学校读者我要写书评

暂无评论

Trajectory-User Link with Attention Recurrent Networks

Trajectory-User Link with Attention Recurrent Networks

引用

international conference on pattern recognition

作者： Tao Sun Yongjun Xu Fei Wang Lin Wu Tangwen Qian Zezhi Shao University of Chinese Academy of Sciences Beijing China Institute of Computing Technology Chinese Academy of Sciences Beijing China

the prevalent adoptions of GPS-enabled devices have witnessed an explosion of various location-based services which produces a huge amount of trajectories monitoring the individuals' movements. In this paper, we tackle Trajectory-User Link (TUL) problem, which identifies humans' movement patterns and links trajectories to the users who generated them. Existing solutions on TUL problem employ recurrent neural networks and variational autoencoder methods, which face the bottlenecks in the case of excessively long trajectories and fragmentary users' movements. However, these are common characteristics of trajectory data in reality, leading to performance degradation of the existing models. In this paper, we propose an end-to-end attention recurrent neural learning framework, called TULAR (Trajectory-User Link with Attention Recurrent Networks), which focus on selected parts of the source trajectories when linking. TULAR introduce the Trajectory Semantic Vector (TSV) via unsupervised location representation learning and recurrent neural networks, by which to reckon the weight of parts of source trajectory. Further, we employ three attention scores for the weight measurements. Experiments are conducted on two real world datasets and compared with several existing methods, and the results show that TULAR yields a new state-of-the-art performance. Source code is public available at Github: https://***/taos123/TULAR.

关键词： Weight measurement Training Recurrent neural networks Semantics Graphics processing units Trajectory pattern recognition

来源：评论

学校读者我要写书评

暂无评论

VSB2-Net: Visual-Semantic Bi-Branch Network for Zero-Shot Hashing

VSB2-Net: Visual-Semantic Bi-Branch Network for Zero-Shot Ha...

引用

international conference on pattern recognition

作者： Xin Li Xiangfeng Wang Bo Jin Wenjie Zhang Jun Wang Hongyuan Zha School of Computer Science and Technology East China Normal University Shanghai China Tencent Shenzhen China College of Computing Georgia Institute of Technology Atlanta GA USA

Zero-shot hashing aims at learning hashing model from seen classes and the obtained model is capable of generalizing to unseen classes for image retrieval. Inspired by zero-shot learning, existing zero-shot hashing methods usually transfer the supervised knowledge from seen to unseen classes, by embedding the hamming space to a shared semantic space. However, this makes instances difficult to distinguish due to limited hashing bit numbers, especially for semantically similar unseen classes. We propose a novel inductive zero-shot hashing framework, i.e., VSB²-Net, where both semantic space and visual feature space are embedded to the same hamming space instead. the reconstructive semantic relationships are established in the hamming space, preserving local similarity relationships and explicitly enlarging the discrepancy between semantic hamming vectors. A two-task architecture, comprising of classification module and visual feature reconstruction module, is employed to enhance the generalization and transfer abilities. Extensive evaluation results on several benchmark datasets demonstrate the superiority of our proposed method compared to several state-of-the-art baselines.

关键词： Visualization Semantics Image retrieval Benchmark testing pattern recognition Acceleration Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Learning Defects in Old Movies from Manually Assisted Restoration

Learning Defects in Old Movies from Manually Assisted Restor...

引用

international conference on pattern recognition

作者： Arthur Renaudeau Travis Seng Axel Carlier Fabien Pierre François Lauze Jean-François Aujol Jean-Denis Durou IRIT UMR CNRS 5505 Université de Toulouse France Université de Lorraine CNRS Inria LORIA Nancy France DIKU University of Copenhagen Denmark Université de Bordeaux Bordeaux INP CNRS IMB UMR 5251 Talence France

ISBN: (纸本)9781728188089;9781728188096

We propose to detect defects in old movies, as the first step of a larger framework of old movies restoration by inpainting techniques. the specificity of our work is to learn a film restorer's expertise from a pair of sequences, composed of a movie with defects, and the same movie which was semiautomatically restored with the help of a specialized software. In order to detect those defects with minimal human interaction and further reduce the time spent for a restoration, we feed a U-Net with consecutive defective frames as input to detect the unexpected variations of pixel intensity over space and time. Since the output of the network is a mask of defect location, we first have to create the dataset of mask frames on the basis of restored frames from the software used by the film restorer, instead of classical synthetic ground truth, which is not available. these masks are estimated by computing the absolute difference between restored frames and defectuous frames, combined with thresholding and morphological closing. Our network succeeds in automatically detecting real defects with more precision than the manual selection with an all-encompassing shape, including some the expert restorer could have missed for lack of time.

关键词： Shape Manuals Motion pictures Software pattern recognition Feeds

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169页 << < 79 80 81 82 83 84 85 86 87 88 > >>

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：