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

91 篇 会议
13 册 图书
2 篇 期刊文献

馆藏范围

106 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

77 篇 工学
- 71 篇 计算机科学与技术...
- 41 篇 电气工程
- 19 篇 软件工程
- 5 篇 信息与通信工程
- 4 篇 仪器科学与技术
- 2 篇 动力工程及工程热...
- 2 篇 控制科学与工程
- 2 篇 化学工程与技术
- 2 篇 生物医学工程（可授...
- 1 篇 机械工程
- 1 篇 光学工程
- 1 篇 生物工程
39 篇 医学
- 39 篇 临床医学
19 篇 理学
- 14 篇 数学
- 5 篇 统计学（可授理学、...
- 3 篇 系统科学
- 2 篇 物理学
- 2 篇 化学
- 1 篇 生物学
10 篇 管理学
- 10 篇 图书情报与档案管...
1 篇 经济学
- 1 篇 应用经济学
1 篇 法学
- 1 篇 社会学
1 篇 艺术学
- 1 篇 设计学（可授艺术学...

主题

23 篇 machine learning
21 篇 pattern recognit...
12 篇 data mining
11 篇 training
10 篇 data models
9 篇 feature extracti...
9 篇 artificial intel...
7 篇 deep learning
7 篇 benchmark testin...
6 篇 support vector m...
6 篇 neural networks
6 篇 data mining and ...
6 篇 visualization
6 篇 semantics
5 篇 learning systems
5 篇 information syst...
5 篇 computer vision
4 篇 image segmentati...
4 篇 federated learni...
4 篇 measurement

机构

2 篇 univ elect sci &...
2 篇 chengdu univ tec...
2 篇 univ kaiserslaut...
2 篇 iee sa bissen lu...
1 篇 iit jodhpur jodh...
1 篇 kazan federal un...
1 篇 department of co...
1 篇 institute of inf...
1 篇 department of ch...
1 篇 department of fo...
1 篇 technische unive...
1 篇 key laboratory o...
1 篇 inst sci & techn...
1 篇 lg display
1 篇 faculty of elect...
1 篇 univ bonn bonn
1 篇 national laborat...
1 篇 sun yat sen univ...
1 篇 univ grenoble al...
1 篇 ufr mim universi...

作者

3 篇 li fan
3 篇 hu xiaonan
3 篇 liu qihe
2 篇 pudi vikram
2 篇 de-shuang huang
2 篇 duoqian miao
2 篇 hepu deng
2 篇 ye mao
2 篇 stricker didier
2 篇 fu lee wang
2 篇 da cruz steve di...
2 篇 shuigeng zhou
2 篇 cheng xianqiong
2 篇 songmao zhang
2 篇 george karypis
2 篇 stifter thomas
2 篇 jingsheng lei
2 篇 taetz bertram
1 篇 wil m. p. van de...
1 篇 seyed tabatabaei...

语言

104 篇 英文
1 篇 其他
1 篇 中文

检索条件"任意字段=8th International Conference on Machine Learning and Data Mining in Pattern Recognition, MLDM 2012"

共 106 条记录，以下是21-30 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：

BAFL: Federated learning with Base Ablation for Cost Effective Communication 26

BAFL: Federated Learning with Base Ablation for Cost Effecti...

引用

26th international conference on pattern recognition / 8th international Workshop on Image mining - theory and Applications (IMTA)

作者： Kundalwal, Mayank Kumar Saraswat, Anurag Mishra, Ishan Mishra, Deepak IIT Jodhpur Jodhpur Rajasthan India

ISBN: (数字)9781665490627

ISBN: (纸本)9781665490627

Federated learning is a distributed machine learning setting in which clients train a global model on their local data and share their knowledge with the server in form of the trained model while maintaining privacy of the data. the server aggregates clients' knowledge to create a generalized global model. Two major challenges faced in this process are data heterogeneity and high communication cost. We target the latter and propose a simple approach, BAFL (Federated learning for Base Ablation) for cost effective communication in federated learning. In contrast to the common practice of employing model compression techniques to reduce the total communication cost, we propose a fine-tuning approach to leverage the feature extraction ability of layers at different depths of deep neural networks. We use a model pretrained on general-purpose large scale data as a global model. this helps in better weight initialization and reduces the total communication cost required for obtaining the generalized model. We achieve further cost reduction by focusing only on the layers responsible for semantic features (data specific information). the clients fine tune only top layers on their local data. Base layers are ablated while transferring the model and clients communicate parameters corresponding to the remaining layers. this results in reduction of communication cost per round without compromising the accuracy. We evaluate the proposed approach using VGG-16 and ResNet-50 models on datasets including WBC, FOOD-101, and CIFAR-10 and obtain up to two orders of reduction in total communication cost as compared to the conventional federated learning. We perform experiments in both IID and Non-IID settings and observe consistent improvements.

关键词： Costs Federated learning Semantics Neural networks Distributed databases Focusing Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Efficient and Flexible Sublabel-Accurate Energy Minimization 26

Efficient and Flexible Sublabel-Accurate Energy Minimization

引用

26th international conference on pattern recognition / 8th international Workshop on Image mining - theory and Applications (IMTA)

作者： Nurlanov, Zhakshylyk Cremers, Daniel Bernard, Florian Univ Bonn Bonn Germany Tech Univ Munich Munich Germany

ISBN: (数字)9781665490627

ISBN: (纸本)9781665490627

We address the problem of minimizing a class of energy functions consisting of data and smoothness terms that commonly occur in machine learning, computer vision, and pattern recognition. While discrete optimization methods are able to give theoretical optimality guarantees, they can only handle a finite number of labels and therefore suffer from label discretization bias. Existing continuous optimization methods can find sublabel-accurate solutions, but they are not efficient for large label spaces. In this work, we propose an efficient sublabel-accurate method that utilizes the best properties of both continuous and discrete models. We separate the problem into two sequential steps: (i) global discrete optimization for selecting the label range, and (ii) efficient continuous sublabel-accurate local refinement of a convex approximation of the energy function in the chosen range. Doing so allows us to achieve a boost in time and memory efficiency while practically keeping the accuracy at the same level as continuous convex relaxation methods, and in addition, providing theoretical optimality guarantees at the level of discrete methods. Finally, we show the flexibility of the proposed approach to general pairwise smoothness terms, so that it is applicable to a wide range of regularizations. Experiments on the illustrating example of the image denoising problem demonstrate the properties of the proposed method. the code reproducing experiments is available on https://***/nurlanov-zh/sublabel-accurate-alpha-expansion.

关键词： Computer vision Codes Memory management Optimization methods machine learning Minimization Relaxation methods

来源：评论

学校读者我要写书评

暂无评论

引用

26th international conference on pattern recognition / 8th international Workshop on Image mining - theory and Applications (IMTA)

作者： Song, Danming Gao, Yipeng Yan, Junkai Sun, Wei Zheng, Wei-Shi Sun Yat Sen Univ Sch Comp Sci & Engn Guangzhou Peoples R China Sun Yat Sen Univ Sch Elect & Informat Technol Guangzhou Peoples R China Minist Educ Key Lab Machine Intelligence & Adv Comp Guangzhou Peoples R China

ISBN: (数字)9781665490627

ISBN: (纸本)9781665490627

Self-supervised contrastive learning methods have shown promising transferability in pretraining by maximizing the mutual information between two cropped regions as views from the same image. In order to effectively extract mutual information between views, the cropped regions need to be the same instance as prior hypothesis. However, the data collected in general scenes usually have multiple instances, so the two cropped regions probably contain different instances which will mislead the contrastive learning process. In this paper, we make the first attempt to exploit the spatial position relationships of the two cropped regions in self-supervised contrastive learning with images that include multiple instances. then, we propose an effective method called Space-correlated Contrastive learning (SpaceCL). Specifically, given two randomly cropped regions as contrastive pairs from the same image, we implement self-supervised contrastive learning by optimizing a space correspondence contrastive similarity loss. As a result, our method achieves state-of-the-art performance and remarkably outperforms other counterparts when pretrained on the COCO dataset of which images contain multiple instances. Experiments show our method outperforms ReSim with 2.6%AP on PASCAL VOC object detection, 0.8%AP(bb) and 0.6%AP(mk) on COCO object detection and instance segmentation, 1.3%AP(mk) on Cityscapes instance segmentation.

关键词： learning systems Representation learning Image segmentation Semantics Object detection data mining Task analysis

来源：评论

学校读者我要写书评

暂无评论

Minimal Solvers for Point Cloud Matching with Statistical Deformations 26

Minimal Solvers for Point Cloud Matching with Statistical De...

引用

26th international conference on pattern recognition / 8th international Workshop on Image mining - theory and Applications (IMTA)

作者： Flood, Gabrielle Tegler, Erik Gillsjö, David Heyden, Anders Aström, Kalle Lund Univ Ctr Math Sci Lund Sweden

ISBN: (数字)9781665490627

ISBN: (纸本)9781665490627

An important issue in simultaneous localisation and mapping is how to match and merge individual local maps into one global map. this is addressed within the field of robotics and is crucial for multi-robot SLAM. there are a number of different ways to solve this task depending on the representation of the map. To take advantage of matching and merging methods that allow for deformations of the local maps it is important to find feature matches that capture such deformations. In this paper we present minimal solvers for point cloud matching using statistical deformations. the solvers use either three or four point matches. these solve for either rigid or similarity transformation as well as shape deformation in the direction of the most important modes of variation. Given an initial set of tentative matches based on, for example, feature descriptors or machine learning we use these solvers in a RANSAC loop to remove outliers among the tentative matches. We evaluate the methods on both synthetic and real data and compare them to RANSAC methods based on Procrustes and demonstrate that the proposed methods improve on the current state-of-the-art.

关键词： Point cloud compression three-dimensional displays Simultaneous localization and mapping Shape Merging machine learning Task analysis

来源：评论

学校读者我要写书评

暂无评论

Understanding Autism Using machine learning: A Structural MRI Study 26

Understanding Autism Using Machine Learning: A Structural MR...

引用

26th international conference on pattern recognition / 8th international Workshop on Image mining - theory and Applications (IMTA)

作者： Ali, Mohamed T. ElNakieb, Yaser Shalaby, Ahmed Elnakib, Ahmed Mahmoud, Ali Zai, Huma Ghazal, Mohammed Barnes, Gregory El-Baz, Ayman Univ Louisville Bioengineering Dept Louisville KY 40292 USA Abu Dhabi Univ Abu Dhabi U Arab Emirates Univ Louisville Dept Neurol Louisville KY 40202 USA Univ Louisville Pediat Res Inst Louisville KY 40202 USA

ISBN: (数字)9781665490627

ISBN: (纸本)9781665490627

In this study, we propose a Computer-Aided Diagnostic (CAD) system to diagnose and understand autism spectrum disorder (ASD) using structural MRI (sMRI). Starting with identifying morphological anomalies within the cortical regions of ASD subjects. Every cortical feature receives a score corresponding to their contribution in diagnosing a subject to be ASD or typically developed (TD). Scores are determined by hyper-optimized machine learning (ML) classifiers. An early personalized diagnosis of ASD becomes possible by the proposed CAD system. the proposed framework implements multiple stages including cerebral cortex extraction from structure MRI (sMRI). Moreover, the proposed framework identify the altered brain regions. We can summarize this framework in the following procedures: i) Cerebral cortex segmentation, ii) Parcellation of the cortex to Desikan-Killiany (DK) atlas;iii) Annotating brain regions which are associated with ASD;iv) Blocking for the confounding effect of both age and sex;v) Tailoring ASD neuroatlases;vi) Classifying ASD using neural networks (NN). We utilized Autism Brain Imaging data Exchange (ABIDE I) dataset to test the proposed framework. the proposed achieved a balanced accuracy score of 97% +/- 2%. In this study, we demonstrate the ability to describe specific developmental patterns of the brain in autism using tailored neuro-atlases, as well as, developing an objective CAD system using morphological features extracted from sMRI scans.

关键词： Neuroimaging Autism Image segmentation Cerebral cortex Design automation Magnetic resonance imaging machine learning

来源：评论

学校读者我要写书评

暂无评论

Efficient Unsupervised learning for Plankton Images 26

Efficient Unsupervised Learning for Plankton Images

引用

26th international conference on pattern recognition / 8th international Workshop on Image mining - theory and Applications (IMTA)

作者： Alfano, Paolo Didier Rando, Marco Letizia, Marco Odone, Francesca Rosasco, Lorenzo Pastore, Vito Paolo Univ Genoa MaLGa DIBRIS Genoa Italy INFN Sez Genova Genoa Italy Italian Inst Technol Genoa Italy MIT CBMM 77 Massachusetts Ave Cambridge MA 02139 USA

ISBN: (数字)9781665490627

ISBN: (纸本)9781665490627

Monitoring plankton populations in situ is fundamental to preserve the aquatic ecosystem. Plankton microorganisms are in fact susceptible of minor environmental perturbations, that can reflect into consequent morphological and dynamical modifications. Nowadays, the availability of advanced automatic or semi-automatic acquisition systems has been allowing the production of an increasingly large amount of plankton image data. the adoption of machine learning algorithms to classify such data may be affected by the significant cost of manual annotation, due to both the huge quantity of acquired data and the numerosity of plankton species. To address these challenges, we propose an efficient unsupervised learning pipeline to provide accurate classification of plankton microorganisms. We build a set of image descriptors exploiting a two-step procedure. First, a Variational Autoencoder (VAE) is trained on features extracted by a pre-trained neural network. We then use the learnt latent space as image descriptor for clustering. We compare our method with state-of-the-art unsupervised approaches, where a set of pre-defined hand-crafted features is used for clustering of plankton images. the proposed pipeline outperforms the benchmark algorithms for all the plankton datasets included in our analysis, providing better image embedding properties.

关键词： Image segmentation Microorganisms Pipelines Neural networks Sociology Computer architecture Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Improving End-to-End Text Image Translation From the Auxiliary Text Translation Task 26

Improving End-to-End Text Image Translation From the Auxilia...

引用

26th international conference on pattern recognition / 8th international Workshop on Image mining - theory and Applications (IMTA)

作者： Ma, Cong Zhang, Yaping Tu, Mei Han, Xu Wu, Linghui Zhao, Yang Zhou, Yu Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Chinese Acad Sci Inst Automat Natl Lab Pattern Recognit NLPR 95 Zhongguan East Rd Beijing 100190 Peoples R China Zhongke Fanyu Technol Co Ltd Fanyu AI Lab Beijing 100190 Peoples R China Samsung Res China Beijing SRC B Beijing Peoples R China

ISBN: (数字)9781665490627

ISBN: (纸本)9781665490627

End-to-end text image translation (TIT), which aims at translating the source language embedded in images to the target language, has attracted intensive attention in recent research. However, data sparsity limits the performance of end-to-end text image translation. Multi-task learning is a non-trivial way to alleviate this problem via exploring knowledge from complementary related tasks. In this paper, we propose a novel text translation enhanced text image translation, which trains the end-to-end model with text translation as an auxiliary task. By sharing model parameters and multi-task training, our model is able to take full advantage of easily-available large-scale text parallel corpus. Extensive experimental results show our proposed method outperforms existing end-to-end methods, and the joint multi-task learning with both text translation and recognition tasks achieves better results, proving translation and recognition auxiliary tasks are complementary. (1)

关键词： Training Image recognition Text recognition Optical character recognition Multitasking Decoding machine translation

来源：评论

学校读者我要写书评

暂无评论

Efficient Dense-Graph Convolutional Network with Inductive Prior Augmentations for Unsupervised Micro-Gesture recognition 26

Efficient Dense-Graph Convolutional Network with Inductive P...

引用

26th international conference on pattern recognition / 8th international Workshop on Image mining - theory and Applications (IMTA)

作者： Shah, Atif Chen, Haoyu Shi, Henglin Zhao, Guoying Univ Oulu Ctr Machine Vis & Signal Anal CMVS Oulu Finland

ISBN: (数字)9781665490627

ISBN: (纸本)9781665490627

Skeleton-based action/gesture recognition has already witnessed excellent progress on processing large-scale, laboratory-based datasets with pre-defined skeleton joint topology. However, it's still an unsolved task when it comes to real-world scenarios with practical limitations such as small-scaled dataset sizes, few-labeled samples, and various skeleton topologies. In this paper, we work on the recognition of micro-gestures, which are subtle body gestures collected in real-world scenarios. Specifically, we utilize contrastive learning to heritage the knowledge from known large-scale datasets for enhancing the learning on fewer samples of micro-gestures. To overcome the gap caused by various domain distributions and structure topologies between the datasets, we compute skeleton representations from augmented sequences via momentum-based efficient and scalable encoders as additional inductive priors. Importantly, we propose an effective dense-graph based unsupervised architecture that resorts to a queue-based dictionary to store positive and negative keys for better contrast with queries to learn substantially efficient and discriminant patterns in the feature space. Together with cross-dataset experimental results show that our model significantly improves the accuracies on two micro-gesture datasets, SMG by 7.4% and iMiGUE by 18.41% advocating its superiority.

关键词： Dictionaries Computer architecture Skeleton Robustness data models Topology pattern recognition

来源：评论

学校读者我要写书评

暂无评论

A Multimodal Framework for Automated Teaching Quality Assessment of One-to-many Online Instruction Videos 26

A Multimodal Framework for Automated Teaching Quality Assess...

引用

26th international conference on pattern recognition / 8th international Workshop on Image mining - theory and Applications (IMTA)

作者： Pan, Yueran Wu, Jiaxin Ju, Ran Zhou, Ziang Gu, Jiayue Zeng, Songtian Yuan, Lynn Li, Ming Wuhan Univ Sch Comp Sci Wuhan Hubei Peoples R China Duke Kunshan Univ Ctr Teaching & Learning Kunshan Jiangsu Peoples R China Duke Kunshan Univ Data Sci Res Ctr Kunshan Jiangsu Peoples R China Fumi Hlth & Technol LLC Hunan Fujian Peoples R China

ISBN: (数字)9781665490627

ISBN: (纸本)9781665490627

In the post-pandemic era, online courses have been adopted universally. Manually assessing online course teaching quality requires significant time and professional pedagogy experience. To address this problem, we design an evaluation protocol and propose a multimodal machine learning framework1 for automated teaching quality assessment of one-to-many online instruction videos. Our framework evaluates online teaching quality from five aspects, namely Clarity, Classroom interaction, Technical management of online teaching, Empathy, and Time management. Our method includes mid-level behavior feature extraction, high-level interpretable feature extraction, and supervised learning prediction. Our automated multimodal teaching quality assessment system achieves comparable performance to human annotators on our one-to-many online instruction videos. For binary classification, the best average accuracy of five aspects is 0.898. For regression, the best average means square error is 0.527 on a 0-10 scale.

关键词： Teaching Quality Assessment Multimodal Behavior Coding Interptretable Feature Extraction Speaker Diarization Emotion recognition

来源：评论

学校读者我要写书评

暂无评论

Autoencoder Attractors for Uncertainty Estimation 26

Autoencoder Attractors for Uncertainty Estimation

引用

26th international conference on pattern recognition / 8th international Workshop on Image mining - theory and Applications (IMTA)

作者： Da Cruz, Steve Dias Taetz, Bertram Stifter, thomas Stricker, Didier IEE SA Bissen Luxembourg Univ Kaiserslautern Kaiserslautern Germany German Res Ctr Artificial Intelligence DFKI Darmstadt Germany

ISBN: (数字)9781665490627

ISBN: (纸本)9781665490627

the reliability assessment of a machine learning model's prediction is an important quantity for the deployment in safety critical applications. Not only can it be used to detect novel sceneries, either as out-of-distribution or anomaly sample, but it also helps to determine deficiencies in the training data distribution. A lot of promising research directions have either proposed traditional methods like Gaussian processes or extended deep learning based approaches, for example, by interpreting them from a Bayesian point of view. In this work we propose a novel approach for uncertainty estimation based on autoencoder models: the recursive application of a previously trained autoencoder model can be interpreted as a dynamical system storing training examples as attractors. While input images close to known samples will converge to the same or similar attractor, input samples containing unknown features are unstable and converge to different training samples by potentially removing or changing characteristic features. the use of dropout during training and inference leads to a family of similar dynamical systems, each one being robust on samples close to the training distribution but unstable on new features. Either the model reliably removes these features or the resulting instability can be exploited to detect problematic input samples. We evaluate our approach on several dataset combinations as well as on an industrial application for occupant classification in the vehicle interior for which we additionally release a new synthetic dataset.

关键词： Training Visualization Uncertainty Computational modeling Estimation Training data Safety

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11页 << < 1 2 3 4 5 6 7 8 9 10 > >>

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：