检索结果-内蒙古大学图书馆

17th China National Conference on Computational Linguistics, CCL 2018 and 6th International Symposium on Natural Language Processing Based on Naturally Annotated Big Data, NLP-NABD 2018

作者： Wu, Hanqian Liu, Mumu Wang, Jingjing Xie, Jue Shen, Chenlin School of Computer Science and Engineering Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration of Ministry of Education Southeast University Nanjing China NLP Lab School of Computer Science and Technology Soochow University Suzhou China Southeast University-Monash University Joint Graduate School Suzhou China

ISBN: (纸本)9783030017156

In e-commerce websites, user-generated question-answering text pairs generally contain rich aspect information of products. In this paper, we address a new task, namely Question-answering (QA) aspect classification, which aims to automatically classify the aspect category of a given QA text pair. In particular, we build a high-quality annotated corpus with specifically designed annotation guidelines for QA aspect classification. On this basis, we propose a hierarchical attention network to address the specific challenges in this new task in three stages. Specifically, we firstly segment both question text and answer text into sentences, and then construct (sentence, sentence) units for each QA text pair. Second, we leverage a QA matching attention layer to encode these (sentence, sentence) units in order to capture the aspect matching information between the sentence inside question text and the sentence inside answer text. Finally, we leverage a self-matching attention layer to capture different importance degrees of different (sentence, sentence) units in each QA text pair. Experimental results demonstrate that our proposed hierarchical attention network outperforms some strong baselines for QA aspect classification. © Springer Nature Switzerland AG 2018.

关键词： Text processing

来源：评论

学校读者我要写书评

暂无评论

lednet: A lightweight encoder-decoder network for real-time semantic segmentation

arXiv

引用

arXiv 2019年

作者： Wang, Yu Zhou, Quan Liu, Jia Xiong, Jian Gao, Guangwei Wu, Xiaofu Latecki, Longin Jan National Engineering Research Center of Communications and Networking Nanjing University of Posts & Telecommunications China Key Lab. of Broadband Wireless Communications and Sensor Network Technology Nanjing University of Posts & Telecommunications China Institute of Advanced Technology Nanjing University of Posts & Telecommunications China Department of Computer and Information Sciences Temple University Philadelphia United States

The extensive computational burden limits the usage of CNNs in mobile devices for dense estimation tasks. In this paper, we present a lightweight network to address this problem, namely LEDNet, which employs an asymmetric encoder-decoder architecture for the task of real-time semantic segmentation. More specifically, the encoder adopts a ResNet as backbone network, where two new operations, channel split and shuffle, are utilized in each residual block to greatly reduce computation cost while maintaining higher segmentation accuracy. On the other hand, an attention pyramid network (APN) is employed in the decoder to further lighten the entire network complexity. Our model has less than 1M parameters, and is able to run at over 71 FPS in a single GTX 1080Ti GPU. The comprehensive experiments demonstrate that our approach achieves state-of-the-art results in terms of speed and accuracy trade-off on CityScapes dataset. Copyright © 2019, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

network anomaly detection in critical infrastructure based on mininet network simulator 1

Network anomaly detection in critical infrastructure based o...

引用

1st Italian Conference on Cybersecurity, ITASEC 2017

作者： Bernieri, Giuseppe Pascucci, Federica Lopez, Javier Department of Engineering University Roma Tre Italy Network Information and Computer Security Lab. University of Malaga Malaga29071 Spain

In this paper, a highly-configurable network anomaly detection system for Critical Infrastructure scenarios is presented. The Mininet virtual machine environment has been used in this framework to simulate an Industrial Control System network and to replicate both physical and cyber components. Finally, a cyber-attack has been implemented for showing both the effectiveness and capability of the proposed network security system. Copyright © 2017 for this paper by its authors.

关键词： Critical infrastructures

来源：评论

学校读者我要写书评

暂无评论

Abstracts

引用

JOURNAL OF SPINAL CORD MEDICINE 2021年第SUPPL 1期44卷 S278-S324页

作者： [Anonymous] Department of Medicine Division of Physical Medicine and Rehabilitation University of Toronto Toronto ON CA KITE - Toronto Rehabilitation Institute University Health Network Toronto ON CA Institute for Health Policy Management and Evaluation University of Toronto Toronto ON CA Rehabilitation Sciences Institute University of Toronto Toronto ON CA Institute of Medical Sciences University of Toronto Toronto ON CA. Rehabilitation Sciences Institute University of Toronto ON CA KITE Research Institute-Toronto Rehab-University Health Network Toronto ON CA Physical Therapy Department University of Toronto ON CA Praxis Spinal Cord Institute Vancouver BC Université de Montréal (École de réadaptation) Montreal QC CA Institut de réadaptation Gingras-Linsay-de-Montréal Montreal QC CA Division of Physical Medicine & Rehabilitation Department of Medicine Faculty of Medicine & Dentistry University of Alberta Edmonton AB CA University of Calgary Calgary AB CA Alberta Health Services Centre for Family Medicine Kitchener ON CA McMaster University Department of Family Medicine Hamilton ON CA Dept. of Physical Therapy University of Toronto Toronto ON CA KITE-University Health Network Toronto ON CA Praxis Spinal Cord Institute Vancouver BC CA Center for Interdisciplinary Research in Rehabilitation and Social Integration (CIRRIS) Quebec City QC CA Dept. of Rehabilitation Laval University Quebec City QC CA Institute of Health Policy Management and Evaluation University of Toronto Toronto ON CA School of Rehabilitation Science University of Saskatchewan Saskatoon SK CA Ontario Neurotrauma Foundation Toronto ON CA Canadian Spinal Research Organization Toronto ON CA CIUSSS du Centre-Sud-de-l ‘Île-de-Montréal (Installation Gingras-Lindsay) Montréal QC CA École de réadaptation Université de Montréal Montréal QC CA First Steps Wellness Centre Regina SK CA Stan Cassidy Centre for Rehabilitation Horizon Health Network Fredericton NB CA Departmen

来源：评论

学校读者我要写书评

暂无评论

Optimization of charging and data collection in wireless rechargeable sensor networks 1

引用

2nd International Conference on Human Centered Computing, HCC 2016

作者： Hu, Cheng Wang, Yun Key Lab of Computer Network and Information Integration MOE Southeast University Nanjing211189 China

ISBN: (数字)9783319318547

ISBN: (纸本)9783319318530

Wireless Rechargeable Sensor networks (WRSNs) can significantly prolong the lifetime by employing a mobile charger to replenish the depleted energy of the sensor nodes. This paper considers the scenario that the mobile charger cannot maintain full operation of the WRSN. In this case, the first and foremost problem is how to allocate the insufficient energy to the sensor nodes and decide their corresponding data sensing rates. The objective is to maximize the utility of data collection, which concerns data fairness as well as data amount. To address this problem, we first formulate and simplify its optimization form. Then based on two observations, we propose the BalanceFlow scheme, which coordinates data sensing of the sensor nodes with charging of the mobile charger. Numerical results show that, the BalanceFlow scheme achieves near optimal utility compared with the optimization results. © Springer International Publishing Switzerland 2016.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Logistic boosting regression for lab.l distribution learning?

Logistic boosting regression for label distribution learning...

引用

2016 IEEE Conference on computer Vision and Pattern Recognition, CVPR 2016

作者： Xing, Chao Geng, Xin Xue, Hui Key Lab of Computer Network and Information Integration Ministry of Education School of Computer Science and Engineering Southeast University Nanjing211189 China

ISBN: (纸本)9781467388511

lab.l Distribution Learning (LDL) is a general learning framework which includes both single lab.l and multi-lab.l learning as its special cases. One of the main assumptions made in traditional LDL algorithms is the derivation of the parametric model as the maximum entropy model. While it is a reasonable assumption without additional information, there is no particular evidence supporting it in the problem of LDL. Alternatively, using a general LDL model family to approximate this parametric model can avoid the potential influence of the specific model. In order to learn this general model family, this paper uses a method called Logistic Boosting Regression (LogitBoost) which can be seen as an additive weighted function regression from the statistical viewpoint. For each step, we can fit individual weighted regression function (base learner) to realize the optimization gradually. The base learners are chosen as weighted regression tree and vector tree, which constitute two algorithms named LDLogitBoost and AOSO-LDLogitBoost in this paper. Experiments on facial expression recognition, crowd opinion prediction on movies and apparent age estimation show that LDLogitBoost and AOSO-LDLogitBoost can achieve better performance than traditional LDL algorithms as well as other LogitBoost algorithms.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Deep Age Distribution Learning for Apparent Age Estimation

Deep Age Distribution Learning for Apparent Age Estimation

引用

IEEE computer Society Conference on computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Zengwei Huo Xu Yang Chao Xing Ying Zhou Peng Hou Jiaqi Lv Xin Geng Key Lab of Computer Network and Information Integration (Ministry of Education) Southeast University Nanjing China

Apparent age estimation has attracted more and more researchers since its potential applications in the real world. Apparent age estimation differs from chronological age estimation that in apparent age estimation each facial image is lab.lled by multiple individuals, the mean age is the ground truth age and the uncertainty is introduced by the standard deviation. In this paper, we propose a novel method called Deep Age Distribution Learning(DADL) to deal with such situation. According to the given mean age and the standard deviation, we generate a Gaussian age distribution for each facial image as the training target instead of the single age. DADL first detects the facial region in image and aligns the facial image. Then, it uses deep Convolutional Neural network(CNN) pre-trained based on the VGGFace and fine-tuned on the age dataset to extract the predicted age distribution. Finally it uses ensemble method to get the result. Our DADL method got a good performance in ChaLearn Looking at People 2016-Track 1: Age Estimation and ranked the 2nd place among 105 registered participants.

关键词： Estimation Training Standards Face Predictive models Uncertainty Correlation

来源：评论

学校读者我要写书评

暂无评论

Logistic Boosting Regression for lab.l Distribution Learning

Logistic Boosting Regression for Label Distribution Learning

引用

IEEE Conference on computer Vision and Pattern Recognition

作者： Chao Xing Xin Geng Hui Xue Key Lab of Computer Network and Information Integration (Ministry of Education) School of Computer Science and Engineering Southeast University

ISBN: (纸本)9781467388528

关键词： Low-Density Lipoproteins Maximum entropy Regression (Psychology) Accelerated aging Cinema Boost Parametric statistics derivation extra message

来源：评论

学校读者我要写书评

暂无评论

Highly Compact Virtual Counters for Per-Flow Traffic Measurement through Register Sharing

Highly Compact Virtual Counters for Per-Flow Traffic Measure...

引用

IEEE Global Communications Conference

作者： You Zhou Yian Zhou Min Chen Qingjun Xiao Shigang Chen Department of Computer & Information Science & Engineering University of Florida Key Lab of Computer Network and Information Integration Southeast University Ministry of Education

ISBN: (纸本)9781509013296

Per-flow traffic measurement is a fundamental problem in the era of big network data, providing critical information for many practical applications including capacity planning, traffic engineering, data accounting, resource management, and scan/intrusion detection in modern computer networks. It is challenging to design highly compact data structures for approximate per-flow measurements. In this paper, we show that a highly compact virtual counter architecture can achieve fast processing speed (slightly more than 1 memory access per packet) and provide accurate measurement results under tight memory allocation. Extensive experiments based on real network trace data demonstrate its superior performance over the best existing work.

关键词： Radiation detectors Registers Estimation Memory management Time measurement Encoding

来源：评论

学校读者我要写书评

暂无评论

Analysis of the paragraph vector model for information retrieval 16

Analysis of the paragraph vector model for information retri...

引用

2016 ACM International Conference on the Theory of information Retrieval, ICTIR 2016

作者： Ai, Qingyao Yang, Liu Guo, Jiafeng Croft, W. Bruce College of Information and Computer Sciences University of Massachusetts Amherst AmherstMA United States CAS Key Lab. of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China

ISBN: (纸本)9781450344975

Previous studies have shown that semantically meaningful representations of words and text can be acquired through neural embedding models. In particular, paragraph vector (PV) models have shown impressive performance in some natural language processing tasks by estimating a document (topic) level language model. Integrating the PV models with traditional language model approaches to retrieval, however, produces unstable performance and limited improvements. In this paper, we formally discuss three intrinsic problems of the original PV model that restrict its performance in retrieval tasks. We also describe modifications to the model that make it more suitable for the IR task, and show their impact through experiments and case studies. The three issues we address are (1) the unregulated training process of PV is vulnerable to short document overfitting that produces length bias in the final retrieval model;(2) the corpus-based negative sampling of PV leads to a weighting scheme for words that overly suppresses the importance of frequent words;and (3) the lack of word-context information makes PV unable to capture word substitution relationships. © 2016 ACM.

关键词： Natural language processing systems

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：