检索结果-内蒙古大学图书馆

FIFAWC:a dataset with detailed annotation and rich semantics for group activity recognition

Frontiers of Computer Science 2024年第6期18卷 271-272页

作者： Duoxuan PEI Di HUANG Yunhong WANG State Key Laboratory of Software Development Environment School of Computer Science and EngineeringBeihang UniversityBeijing 100191China Intelligent Recognition and Image Processing Lab. School of Computer Science and EngineeringBeihang UniversityBeijing 100191China

1 *** Activity Recognition(GAR),which aims to identify activities performed collectively in videos,has gained significant attention *** conventional action recognition centered on single individuals,GAR explores the c... 详细信息

关键词： has collective gained

来源：评论

学校读者我要写书评

暂无评论

Rethinking Disentanglement in Unsupervised Domain Adaptation for Medical Image Segmentation

Rethinking Disentanglement in Unsupervised Domain Adaptation...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Yan Wang Yixin Chen Yingying Zhang Haogang Zhu School of Instrumentation and Optoelectronic Engineering Beihang University Beijing China State Key Laboratory of Software Development Environment Beijing Advanced Innovation Center for Biomedical Engineering Beihang University Beijing China BioMind Technology Zhongguancun Medical Engineering Center Beijing China School of Biological Science and Medical Engineering Beihang University Beijing China Blockchain Lab. Xiong’An Intelligent City Innovation Federation China

Domain adaptation has become an important topic because the trained neural networks from the source domain generally perform poorly in the target domain due to domain shifts, especially for medical image analysis. Previous DA methods mainly focus on disentangling domain features. However, it is based on feature independence, which often can not be guaranteed in reality. In this work, we present a new DA approach called Dimension-based Disentangled Dilated Domain Adaptation (D 4 A) to disentangle the storage locations between the features to tackle the problem of domain shift for medical image segmentation tasks without the annotations of the target domain. We use Adaptive Instance Normalization (AdaIN) to encourage the content information to be stored in the spatial dimension, and the style information to be stored in the channel dimension. In addition, we apply dilated convolution to preserve anatomical information avoiding the loss of information due to downsampling. We validate the proposed method for cross-modality medical image segmentation tasks on two public datasets, and the comparison experiments and ablation studies demonstrate the effectiveness of our method, which outperforms the state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A cooperative scheduling framework for shared transportation services 19

A cooperative scheduling framework for shared transportation...

引用

19th COTA International Conference of Transportation Professionals: Transportation in China - Connecting the World, CICTP 2019

作者： Wang, Xinli Qiao, Yanan Wang, Tianyu Guo, Jifu Zhou, Xuesong Xian, Kai Tong, Lu Carol Xie, Jindong Natl. Eng. Lab. for Compreh. Transp. Big Data Applic. Technol. Sch. of Transp. Sci. and Engineering Beihang Univ. Beijing100191 China State Key Lab of Software Development Environment School of Computer Science and Engineering Beihang Univ. Beijing100191 China Beijing Transport Institute No. 9 LiuLiQiao South Lane Fengtai District China

ISBN: (数字)9780784482292

ISBN: (纸本)9780784482292

To improve the efficiency of metropolitan shared transportation services (STS), this paper proposes a cooperative scheduling framework to avoid congestion. Two procedures are considered: shared path scheduling and congestion solving. In a known static traffic network, classic vehicle routing problem (VRP) solutions may obtain an optimal path. But with an increasing number of shared transportation services required, congestion is likely, triggered by open loop VRP scheduling, especially when shared vehicles overwhelm private ones. Dynamic traffic assignment (DTA) solutions could be employed for short-term traffic situation prediction. However, VRP and DTA cannot be combined linearly, due to uncontrolled recursive calls of routing procedures within VRP and DTA. Hence, a software structure is further studied to guarantee convergence of the cooperative framework. Using two open-source transportation packages, VRPLite and DTALite, we test our framework with the Western 3rd Ring Road of the Beijing regional network. Results verify the framework's usability and flexibility. © ASCE.

关键词： Scheduling

来源：评论

学校读者我要写书评

暂无评论

Detecting context dependent messages in a conversational environment 26

Detecting context dependent messages in a conversational env...

引用

26th International Conference on Computational Linguistics, COLING 2016

作者： Li, Chaozhuo Wu, Yu Wu, Wei Xing, Chen Li, Zhoujun Zhou, Ming State Key Lab. of Software Development Environment Beihang University Beijing China Microsoft Research Beijing China Nankai University Tianjin China

ISBN: (纸本)9784879747020

While automatic response generation for building chatbot systems has drawn a lot of attention recently, there is limited understanding on when we need to consider the linguistic context of an input text in the generation process. The task is challenging, as messages in a conversational environment are short and informal, and evidence that can indicate a message is context dependent is scarce. After a study of social conversation data crawled from the web, we observed that some characteristics estimated from the responses of messages are discriminative for identifying context dependent messages. With the characteristics as weak supervision, we propose using a Long Short Term Memory (LSTM) network to learn a classifier. Our method carries out text representation and classifier learning in a unified framework. Experimental results show that the proposed method can significantly outperform baseline methods on accuracy of classification. © 1963-2018 ACL.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

A web text classification technique for unlab.led training samples

A web text classification technique for unlabeled training s...

引用

IEEE International Conference on software Engineering and Service Sciences (ICSESS)

作者： Francois Tchiegue Rui Li Shilong Ma State Key Lab. Of Software Development Environment Beihang University Beijing China

The common classification is conducted under the supervised learning algorithms, which design classifiers through learning the lab.led training samples. However, in actual situations, it is very costly to acquire class-lab.led samples, because manually lab.ling documents requires a lot of time and efforts from experts. Therefore, it restrains the text classification to a great extent. To solve the issue that lab.led texts are hard to retrieve from the Internet, this paper has proposed the text classification method combining Fuzzy Partition Clustering Method (FPCM) and Naive Bayesian Augment Learning to integrate the unsupervision of the clustering with the prior knowledge of the sample, which has solved the bottleneck problem of unlab.led training set in the text classification, further improved the classification performance by estimating the classification error loss to balance the sample selection, and constructed superior classification learning method.

关键词： Training Clustering methods Bayes methods Text categorization Clustering algorithms Classification algorithms Data models

来源：评论

学校读者我要写书评

暂无评论

Ontology-based Requirements Generation for Credibility Validation of Safety-critical System

Ontology-based Requirements Generation for Credibility Valid...

引用

IEEE International Conference on Ubiquitous Computing and Communications

作者： Rui Li Shilong Ma Wentao Yao State Key Lab. Of Software Development Environment School of Computer Science & Engineering Beihang University Beijing 100191 China

ISBN: (纸本)9781509001552

As a kind of critical system, safety-critical system is always used for the key areas such as aerospace, national defense, transportation, nuclear energy, health and so on, which require the high security. Due to the inherent defects which caused by the complexity of the organizational structure, and the external threats which caused by the open and dynamic environment, some unexpected results will be produced inevitably which reduce the credibility of the safety-critical system. Therefore, requirements analysis for credibility validation has gradually become an essential work. However, there still lacks a systematic method to guide the elicitation of trustworthiness requirements. In this paper, we present an ontology-based requirements analysis method to elicit and model the credibility-related requirements. Using the formal representation, we model the system from static and dynamic aspects, model the inherent defects and the external threats that may exist. Further, we enable a set of rules to reason the requirements from the knowledge base we build. At last, the approach is evaluated on a mission electronic system.

关键词： ontology requirements analysis credibility validation safety-critical system

来源：评论

学校读者我要写书评

暂无评论

An Approach to Estimate Traffic Speed Based on Cellular Network Signaling Data on Highways

An Approach to Estimate Traffic Speed Based on Cellular Netw...

引用

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Zhixin Song Tongyu Zhu Dongdong Wu Suai Lius State Key Lab of Software Develop Environment Beihang University Beijing China Beihang University Beijing CN

Traffic speed is one of the most essential parameters representing traffic conditions in intelligent traffic system (ITS). In recent years, there have been several approaches estimating traffic speed based on cellular network signaling data. However, the accuracy of these approaches is unsatisfactory because they have a poor performance in filtering out noisy data and minimizing deviations of traffic speed values' trend in adjacent time intervals. In this paper, a new approach is proposed to solve the two problems above. The approach filters out noisy data according to educated judgment, and adopts a modified Kalman filter algorithm to minimize the deviations. The performance study on real data sets of Beijing shows that the accuracy of the proposed approach is higher when compared with existing two notable estimation approaches. Further the approach will contribute to developing intelligent navigation systems and pursuing artificial intelligence applications.

关键词： Road transportation Estimation Market research Kalman filters Accuracy Vehicles Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Sleep scheduling method based on half-sleep state in the distributed sensor network 9

Sleep scheduling method based on half-sleep state in the dis...

引用

9th International ICST Conference on Testbeds and Research Infrastructures for the development of Networks and Communities, TridentCom 2014

作者： Deng, Pan Chen, Feng Yan, Biying Zhang, Jianwei Zhao, Long Wan, Jiafu Lab. of Parallel Software and Computational Science Institute of Software Chinese Academy of Sciences Beijing China State Key Laboratory of Software Development Environment Beihang University Beijing China College of Electrical Engineering and Automation Jiangxi University of Science and Technology Ganzhou China

ISBN: (纸本)9783319133256

In order to extend the sensor’s lifetime, this paper researched deeply into the sleep scheduling mechanism in the distributed sensor network. Now, the commonly used sleep scheduling methods based on the coverage have the problem of response delay, so we proposed a sleep scheduling method based on the half-sleep state to overcome this shortcoming. Under the control of regional agent node, this method adopts a minimum coverage algorithm based on the approximate solution to select the minimum coverage node set. Experimental results show that the proposed scheduling method can both reduce power consumption of the whole network effectively and extend the lifetime of the sensor noticeably. © Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2014.

关键词： Sensor networks

来源：评论

学校读者我要写书评

暂无评论

The next-generation search engine: Challenges and key technologies

The next-generation search engine: Challenges and key techno...

引用

International Conference on Data Engineering and Internet Technology, DEIT 2011

作者： Lang, Bo Liu, Xianglong Li, Wei State Key Lab. of Software Development Environment Beihang University Beijing China

ISBN: (纸本)9783642288067

This paper analyzes limitations and challenges of state-of-the-art internet search engines, points out the features and key technologies of next-generation search engines. The solutions of relevant key technologies are proposed and discussed, including a new search engine architecture, a multidimensional data model, the distributed data storage and parallel processing techniques, and intelligent service oriented query language. Finally an unstructured data retrieval system is established based on the above ideas. © 2013 Springer-Verlag GmbH.

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

Hash bit selection using Markov process for approximate nearest neighbor search 13

Hash bit selection using Markov process for approximate near...

引用

11th International Conference on Advances in Mobile Computing and Multimedia, MoMM 2013

作者： Zhang, Danchen Liu, Xianglong Lang, Bo State Key Lab. of Software Development Environment Beihang University Beijing China

ISBN: (纸本)9781450321068

Hashing for nearest neighbor search has attracted great attentions in the past years. Many hashing methods have been successfully applied in real-world applications like the mobile product search. The performance of these applications usually highly relies on the quality of hash bits. However, it still lacks of a general method that can provide good hash bits for different scenarios. In this paper, we propose a novel method that can select compact, independent and informative hash bits using the Markov Process. Our method can serve as a unified framework compatible with different hashing methods. We design two algorithms, BS-CMP and BS-DMP, and formulate the selection problem as the subgraph discovery on a graph. Experiments are conducted for two important selection scenarios when applying hash techniques, i.e., hashing using different hashing algorithms and hashing with multiple features. The result indicates that our proposed bit selection approaches outperform naive selection methods significantly under aforementioned two scenarios. © 2013 ACM.

关键词： Nearest neighbor search

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：