检索结果-内蒙古大学图书馆

dataset Bias in Deception Detection 26

26th international Conference on pattern recognition / 8th international workshop on Image mining - Theory and Applications (IMTA)

作者： Mambreyan, Ara Punskaya, Elena Gunes, Hatice Univ Cambridge Dept Engn Cambridge England Univ Cambridge Dept Comp Sci & Technol Cambridge England

ISBN: (数字)9781665490627

ISBN: (纸本)9781665490627

With the advances in machine learning, lie detection technology gained significant attention. In recent years, several multi-modal techniques achieved as high as 99% accuracy results using the Real-life Trial dataset with only 121 data points. This led to considerable media hype and research interest in lie detection with machine learning. In this paper, we analyze the effect of dataset bias in deception detection. More specifically, we train a classifier to predict the sex of the identity appearing in the video. On a test data point, we use the sex predictor to predict sex which we use as a proxy for predicting deception, predicting lie for females and truth for males. This lie predictor simulates a classifier that uses nothing but dataset bias. Nevertheless, we find that the performance of this biased classifier is comparable to those of state-of-the-art papers. More specifically, when using IDT features, our biased classifier achieves 64.6% and 59.3% AUC while a classifier trained normally on truth/lie labels achieves 57.4% accuracy and 69.3% AUC. We perform similar experiments on the Bag-of-Lies dataset and show that it too is biased with respect to sex. In addition, we apply the state-of-the-art techniques on an unbiased dataset and show that their performance is no better than chance. Our experiments strongly suggest that the results of recent deception detection techniques can be explained by the bias inherent in the datasets.

关键词： Measurement Industries Ethics machine learning algorithms Government machine learning Detectors

来源：评论

学校读者我要写书评

暂无评论

Unexpected challenges in large scale machine learning

Unexpected challenges in large scale machine learning

引用

1st international workshop on Big data, streams and Heterogeneous Source mining: Algorithms, Systems, Programming Models and Applications, BigMine-12 - Held in Conjunction with SIGKDD Conference

作者： Parker, Charles BigML Inc. 2851 NW 9th St. Corvallis OR 97330 United States

ISBN: (纸本)9781450315470

In machine learning, scale adds complexity. The most obvious consequence of scale is that data takes longer to process. At certain points, however, scale makes trivial operations costly, thus forcing us to re-evaluate algorithms in light of the complexity of those operations. Here, we will discuss one important way a general large scale machine learning setting may differ from the standard supervised classification setting and show some the results of some preliminary experiments highlighting this difference. The results suggest that there is potential for significant improvement beyond obvious solutions. Copyright © 2012 ACM.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Regularized local metric learning for person re-identification

引用

pattern recognition LETTERS 2015年 68卷 288-296页

作者： Liong, Venice Erin Lu, Jiwen Ge, Yongxin Adv Digital Sci Ctr Singapore 138632 Singapore Minist Educ Key Lab Dependable Serv Comp Cyber Phys Soc Chongqing 430044 Peoples R China Chongqing Univ Sch Software Engn Chongqing 430044 Peoples R China

In this paper, we propose a regularized local metric learning (RLML) method for person re-identification. Unlike existing metric learning based person re-identification methods which learn a single distance metric to measure the similarity of each pair of human body images, our method combines global and local metrics to represent the within-class and between-class variances. By doing so, we utilize the local distribution of the training data to avoid the overfitting problem. In addition, to address the lacking of training samples in most person re-identification systems, our method also regulates the covariance matrices in a parametric manner, so that discriminative information can be better exploited. Experimental results on four widely used datasets demonstrate the advantage of our proposed RLML over both existing metric learning and state-of-the-art person re-identification methods. (C) 2015 Elsevier B.V. All rights reserved.

关键词： Person re-identitication Metric learning Regularization

来源：评论

学校读者我要写书评

暂无评论

The 1st international workshop on Federated learning with Graph data (FedGraph) 22

The 1st International Workshop on Federated Learning with Gr...

引用

31st ACM international Conference on Information and Knowledge Management (CIKM)

作者： Yang, Carl Li, Xiaoxiao Baracaldo, Nathalie Shah, Neil He, Chaoyang Lyu, Lingjuan Sun, Lichao Avestimehr, Salman Emory Univ Atlanta GA 30322 USA Univ British Columbia Vancouver BC Canada IBM Res San Jose CA USA Snap Res Seattle WA USA FedML Inc Los Angeles CA USA Sony AI Tokyo Japan Lehigh Univ Bethlehem PA 18015 USA Univ Southern Calif Los Angeles CA 90007 USA

ISBN: (纸本)9781450392365

The field of graph data mining, one of the most important AI research areas, has been revolutionized by graph neural networks (GNNs), which benefit from training on real-world graph data with millions to billions of nodes and links. Unfortunately, the training data and process of GNNs involving graphs beyond millions of nodes are extremely costly on a centralized server, if not impossible. Moreover, due to the increasing concerns about data privacy, emerging data from realistic applications are naturally fragmented, forming distributed private graphs of multiple "data silos", among which direct transferring of data is forbidden. The nascent field of federated learning (FL), which aims to enable individual clients to jointly train their models while keeping their local data decentralized and completely private, is a promising paradigm for large-scale distributed and private training of GNNs. FedGraph2022 aims to bring together researchers from different backgrounds with a common interest in how to extend current FL algorithms to operate with graph data models such as GNNs. FL is an extremely hot topic of large commercial interest and has been intensively explored for machine learning with visual and textual data. The exploration from graph mining researchers and industrial practitioners is timely catching up just recently. There are many unexplored challenges and opportunities, which urges the establishment of an organized and open community to collaboratively advance the science behind it. The prospective participants of this workshop will include researchers and practitioners from both graph mining and federated learning communities, whose interests include, but are not limited to: graph analysis and mining, heterogeneous network modeling, complex data mining, large-scale machine learning, distributed systems, optimization, meta-learning, reinforcement learning, privacy, robustness, explainability, fairness, ethics, and trustworthiness.

关键词： graph mining distributed learning data privacy federated learning graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Proc. of the 1st international workshop on Novel data stream pattern mining Techniques, streamKDD'10, Held in Conjunction with the 16th ACM SIGKDD Conference on Knowledge Discovery and data mining

Proc. of the 1st International Workshop on Novel Data Stream...

引用

1st international workshop on Novel data stream pattern mining Techniques, streamKDD'10, Held in Conjunction with the 16th ACM SIGKDD Conference on Knowledge Discovery and data mining

ISBN: (纸本)9781450302265

The proceedings contain 8 papers. The topics discussed include: fully decentralized computation of aggregates over data streams;detecting outliers on arbitrary data streams using anytime approaches;CALDS: context-aware learning from data streams;evolutionary clustering using frequent itemsets;towards subspace clustering on dynamic data: an incremental version of PreDeCon;visual analysis of news streams with article threads;conformal prediction for distribution-independent anomaly detection in streaming vessel data;and research issues in mining multiple data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Person Re-identification based on Recurrent Feature Aggregation Network 1

Enhancing Person Re-identification based on Recurrent Featur...

引用

1st international Conference on Multimedia Analysis and pattern recognition (MAPR)

作者： Quan Nguyen Hong Thuy-Binh Nguyen Thi-Lan Le Hanoi Univ Sci & Technol Sch Elect & Commun Hanoi Vietnam Hanoi Univ Sci & Technol MICA Int Res Inst CNRS UMI2954 Grenoble INP Hanoi Vietnam Viet Hung Ind Univ Fac Informat Technol Hanoi Vietnam Univ Transport & Commun Fac Elect & Elect Engn Hanoi Vietnam

ISBN: (纸本)9781538641804

This paper proposes a method for video-based person re-identification. Motivated by the capacity of Recurrent Feature Aggregation Network (RFA-Net) that allows to aggregate the image-level features over time-steps and to yield a sequence-level feature. Our work improves the person re-identification performance by (1) proposing to use Gaussian of Gaussian (GOG) - a more powerful feature at image level instead of LBP-Color as in the original work and (2) applying metric learning techniques for person matching. To analyze the role of image feature and metric learning, we have performed extensive experiments on two public benchmark datasets including PRID 2011 and iLIDS-VID. The proposed solution obtains impressive results on the PRID 2011 dataset. The matching rate at rank 1 is increased by 16.8% compared to that of original method. For the iLIDS-VID dataset, the matching rate at rank 1 of proposed method is increased 1.1% whereas these values at the latter ranks are higher than those of the original method by approximately 4%. In additional, the mean and standard deviation of the rank where the correct matching is found of the proposed method on the PRID 2011 and the iLIDS-VID are 2.32, 4.33 and 4.61, 7.67 while those of the original work are 3.50, 5.42 and 8.03, 17.52, respectively. These obtained results emphasize the robustness of the proposed method compared to the original one.

关键词： Feature extraction Measurement Image color analysis Cameras Robustness data mining Image sequences image colour analysis image sequences Cameras Feature extraction data mining Persons Robustness image feature dataset Gauss Rank of data

来源：评论

学校读者我要写书评

暂无评论

A Method to Generate a machine-Labeled data for Biomedical Named Entity recognition with Various Sub-Domains 1

A Method to Generate a Machine-Labeled Data for Biomedical N...

引用

1st international workshop on Digital Disease Detection using Social Media, DDDSM 2017, co-located with the 8th international Joint Conference on Natural Language Processing, IJCNLP 2017

作者： Kim, Juae Kwon, Sunjae Ko, Youngjoong Seo, Jungyun Computer Science Sogang University Sinsu-dong 1 Mapo-gu Seoul Korea Republic of Computer Engineering Dong-A University 840 Hadan 2-dong Saha-gu Busan Korea Republic of

ISBN: (纸本)9781948087070

Biomedical Named Entity (NE) recognition is a core technique for various works in the biomedical domain. In previous studies, using machine learning algorithm shows better performance than dictionary-based and rule based approaches because there are too many terminological variations of biomedical NEs and new biomedical NEs are constantly generated. To achieve the high performance with a machine-learning algorithm, good-quality corpora are required. However, it is difficult to obtain the good-quality corpora because annotating a biomedical corpus for machine-learning is extremely time-consuming and costly. In addition, most previous corpora are insufficient for high-level tasks because they cannot cover various domains. Therefore, we propose a method for generating a large amount of machine-labeled data that covers various domains. To generate a large amount of machine-labeled data, firstly we generate an initial machine-labeled data by using a chunker and MetaMap. The chunker is developed to extract only biomedical NEs with manually annotated data. MetaMap is used to annotate the category of biomedical NE. Then we apply the self-training approach to bootstrap the performance of initial machine-labeled data. In our experiments, the biomedical NE recognition system that is trained with our proposed machine-labeled data achieves much high performance. As a result, our system outperforms biomedical NE recognition system that using MetaMap only with 26.03%p improvements on F1-score. © 2017 AFNLP

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Multi-valued and universal binary neurons: learning algorithms, application to image processing and recognition 1st

Multi-valued and universal binary neurons: Learning algorith...

引用

1st international workshop on machine learning and data mining in pattern recognition, MLDM 1999

作者： Aizenberg, Igor N. Aizenberg, Naum N. Krivosheev, Georgy A. Minaiskaya 28 kv. 49 Uzhgorod294015 Ukraine Paustovskogo 3 kv. 430 Moscow Russia

ISBN: (纸本)3540665994

Multi-valued and universal binary neurons (MVN and UBN) are the neural processing elements with complex-valued weights and high functionality. It is possible to implement an arbitrary mapping described by partial-defined multiple-valued function on the single MVN and an arbitrary mapping described by partial-defined or fully-defined Boolean function (which can be not threshold) on the single UBN. The fast-converged learning algorithms are existing for both types of neurons. Such features of the MVN and UBN may be used for solution of the different kinds of problems. One of the most successful applications of the MVN and UBN is their usage as basic neurons in the Cellular Neural Networks (CNN) for solution of the image processing and image analysis problems. Another effective application of the MVN is their use as the basic neurons in the neural networks oriented to the image recognition. © Springer-Verlag Berlin Heidelberg 1999.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Automatic annotation of protein functional class from sparse and imbalanced data sets

引用

1st international workshop on data mining and Bioinformatics

作者： Jung, Jaehee Thon, Michael R. Texas A&M Univ Dept Comp Sci College Stn TX 77843 USA Texas A&M Univ Dept Plant Pathol & Microbiol College Stn TX 77843 USA

ISBN: (纸本)9783540689706

In recent years, high-throughput genome sequencing and sequence analysis technologies have created the need for automated annotation and analysis of large sets of genes. The Gene Ontology (GO) provides a common controlled vocabulary for describing gene function however the process for annotating proteins with GO terms is usually through a tedious manual curation process by trained professional annotators. With the wealth of genomic data that are now available, there is a need for accurate automated annotation methods. In this paper, we propose a method for automatically predicting GO terms for proteins by applying statistical pattern recognition techniques. We employ protein functional domains as features and learn independent Support Vector machine classifiers for each GO term. This approach creates sparse data sets with highly imbalanced class distribution. We show that these problems can be overcome with standard feature and instance selection methods. We also present a meta-learning scheme that utilizes multiple SVMs trained for each GO term, resulting in improved overall performance than either SVM can achieve alone. The implementation of the tool is available at http://***/AAPFC.

关键词： gene annotation feature selection gene ontology InterPro imbalanced data

来源：评论

学校读者我要写书评

暂无评论

Collecting Retail data Using a Deep learning Identification Experience 2nd

Collecting Retail Data Using a Deep Learning Identification ...

引用

2nd international workshop on Recent Advances in Digital Security: Biometrics and Forensics, BioFor 2019, 1st international workshop on pattern recognition for Cultural Heritage, PatReCH 2019, 1st international workshop eHealth in the Big data and Deep learning Era, e-BADLE 2019, international workshop on Deep Understanding Shopper Behaviors and Interactions in Intelligent Retail Environments, DEEPRETAIL 2019 and Industrial session held at the 20th international Conference on Image Analysis and Processing, ICIAP 2019

作者： La Porta, Salvatore Marconi, Fabrizio Lazzini, Isabella JEF Srl Civitanova Marche Italy Consumer Business Group Italia Huawei Milan Italy

ISBN: (纸本)9783030307530

The aim of the paper is to present a part of an architecture realized by Huawei, that propose the first Christmas tree endowed with artificial intelligence. Its ability is to identify facial expressions from images acquired by a mobile application and then recognize the sentiment of the subject. So, basing on the prevailing sentiment the tree lights up itself with different special effects. Our task in the project was testing the performances of the neural networks employed in the mobile application for the recognition of facial emotion. We used a convolutional neural networks model-based and created a purposely dedicated dataset of images for testing the recognition performances. © 2019, Springer Nature Switzerland AG.

关键词： Emotion recognition

来源：评论

学校读者我要写书评

暂无评论

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：

请选择收藏分类：

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

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：