检索结果-内蒙古大学图书馆

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Yu Wang Shenjie Zhao Key Laboratory of Embedded System and Service Computing Ministry of Education P. R. China Mojie Technology (Ningbo)

ISBN: (纸本)9781728176055;9781728176062

Zero-shot learning (ZSL) aims to recognize novel classes without training samples through transferring knowledge from seen classes, based on the assumption that both the seen and unseen classes share a latent semantic space. Previous works either focus on directly learning various mapping functions between visual space and semantic space, or searching a latent common subspace to alleviate semantic gap between different modalities. However, few methods directly learn modality-invariant representations for ZSL. In this paper, we propose a Cross-Modal Representation Reconstruction (CM-RR) framework to bridge the semantic gap between visual features and semantic attributes, as well as introducing a novel regularizer for automatically feature selection. Moreover, an iterative optimization process based on the ALM (Augmented Lagrangian Method) algorithm with the alternating direction strategy is developed to solve the proposed formulation. Extensive experiments on four benchmark datasets show the effectiveness of the proposed approach, and even the performance surpasses some deep learning based methods.

关键词： Training Visualization Semantics Signal processing algorithms Signal processing Feature extraction Iterative algorithms

来源：评论

学校读者我要写书评

暂无评论

Cross-Domain Semantic Segmentation of Urban Scenes via Multi-Level Feature Alignment

Cross-Domain Semantic Segmentation of Urban Scenes via Multi...

引用

International Conference on Pattern Recognition

作者： Bin Zhang Shengjie Zhao Rongqing Zhang Key Laboratory of Embedded System and Service Computing Ministry of Education China School of Software Engineering Tongji University Shanghai China

Semantic segmentation is an essential task in plenty of real-life applications such as virtual reality, video analysis, autonomous driving, etc. Recent advancements in fundamental vision-based tasks ranging from image classification to semantic segmentation have demonstrated deep learning-based models' high capability in learning complicated representation on large datasets. Nevertheless, manually labeling semantic segmentation dataset with pixel-level annotation is extremely labor-intensive. To address this problem, we propose a novel multi-level feature alignment framework for cross-domain semantic segmentation of urban scenes by exploiting generative adversarial networks. In the proposed multi-level feature alignment method, we first translate images from one domain to another one. Then the discriminative feature representations extracted by the deep neural network are concatenated, followed by domain adversarial learning to make the intermediate feature distribution of the target domain images close to those in the source domain. With these domain adaptation techniques, models trained with images in the source domain where the labels are easy to acquire can be deployed to the target domain where the labels are scarce. Experimental evaluations on various mainstream benchmarks confirm the effectiveness as well as robustness of our approach.

关键词： Image segmentation Solid modeling Semantics Neural networks Virtual reality Feature extraction Robustness

来源：评论

学校读者我要写书评

暂无评论

Designing and Analysis of a New Book-Lending system Based on Logic Petri Nets

Designing and Analysis of a New Book-Lending System Based on...

引用

International Conference on Electric Information and Control Engineering

作者： Xia Jiang WenJing Luan Department of Computer Laiwu Vocational and Technical College The Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University

A new book-lending system is designed and analyzed based on logic Petri nets in this paper. The batch processing function and indeterminacy of readers are included in the system. Its logic Petri net model is establish... 详细信息

ISBN: (纸本)9781424480364

关键词： Book-lending system Batch processing Designing Verification Logic Petri net

来源：评论

学校读者我要写书评

暂无评论

Study and implementation of agent-based grid resource monitoring model

Study and implementation of agent-based grid resource monito...

引用

International Conference on Information Science and Engineering (ICISE)

作者： Liu Ming Junqi Zhang Yu Wang Jie Li Department of Computer Science and Technology The Key Laboratory of Embedded System and Service Computing Ministry of Education University of Tongji Shanghai China

ISBN: (纸本)9781424476169

Grid is a promising infrastructure which enables scientists and engineers to access geographically distributed resources. Grid computing is a new technology which focuses on aggregating various kinds of resource (e.g., processor cycles, disk storage, and contents) into one computing platform. The realization of grid computing requires a resource agent to manage and monitor available resources. Based on study of past models, this paper presents a new agent-based resource monitoring model whose main feature is multi-layered monitoring architecture, which enhances the ability to monitor related resource efficiently. In the meantime, the new model has been implemented in the development of a resource monitoring module integrated within a academic grid project.

关键词： Monitoring Computational modeling Databases Grid computing Automation Resource management XML

来源：评论

学校读者我要写书评

暂无评论

Quantized H2 Filtering for Markovian Jump Linear systems over Networks with Non-accessible Mode Information

Quantized H2 Filtering for Markovian Jump Linear Systems ove...

引用

The 8th World Congress on Intelligent Control and Automation(第八届智能控制与自动化世界大会 WCICA 2010)

作者： Tao Liu Qijun Chen Hao Zhang Department of Electronics and Information Engineering Tongji University The Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai China

This paper is concerned with the problems of quantized *** for discrete-time Markovian jump linear systems over networks with non-accessible mode information. The quantizer considered here is logarithmic quantizer. In this paper, a linear time-invariant mode-independent quantized *** is designed such *** error system is stochastically stable. *** conditions for the existence of *** is given in terms of linear matrix inequalities. A numerical example is provided to demonstrate the effectiveness of the proposed approach.

关键词： Quantization Bismuth Linear matrix inequalities Symmetric matrices Linear systems Upper bound Networked control systems

来源：评论

学校读者我要写书评

暂无评论

Research on a Remote Network Monitoring Model for Large-scale Materials Manufacturing

Research on a Remote Network Monitoring Model for Large-scal...

引用

2011 International Conference on Advanced Materials and Computer Science(ICAMCS 2011)

作者： Xiaohui ZENG Manhua LI Wenlang LUO Department of Computer Science and Technology Jinggangshan University The Key Laboratory of Embedded System and Service Computing Ministry of EducationTongji University

A remote network monitoring model for large-scale materials manufacturing is proposed, including five modules: center control module, data collection and fault alarm module, graph drawing module and data storage module. The center control module not only interacts with users, but also controls the other four modules to work together in harmony. According to this monitoring model, a remote network monitoring platform is designed and realized. The user can interact with the control center module through an Internet browser, and the information about the monitored manufacturing machines and devices can be displayed by means of text, chart, graphic and sound, etc. Moreover, the details about the problems or faults from the monitored objects can be obtained in time. The experimental results indicate that the network monitoring platform can accurately get the information of the monitored objects, and users can conveniently get the online running state of those monitored objects.

关键词： remote network monitoring data storage fault alarm materials manufacturing

来源：评论

学校读者我要写书评

暂无评论

A New One-Class Classification Method with Multiple Encoder-Decoder Pairs for Images

A New One-Class Classification Method with Multiple Encoder-...

引用

International Conference on Intelligent Human-Machine systems and Cybernetics, IHMSC

作者： Dongxiang Chen Chungang Yan Mimi Wang Department of Electronics and Information Engineering Tongji University The Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai China

One of the main destinations of image classification methods is to screen out the images belonging to the target class (positive) and identify the images of other classes (negative). Although most classifiers are trained on both positive samples and negative samples, in reality, negative samples are often unavailable. One-class classifiers trained only on positive samples, are proposed to solve this problem. However, how to train effectively a classifier remains a daunting challenge. Considering the success of deep learning in the field of computer vision in recent years, we propose a one-class classification model for images based on convolutional neural network (CNN). The model consists of two parts of networks with different responsibilities. The network of the first part works as the discriminator, used to identify whether the images are positive. The networks of the second part, each of which consists of an encoder-decoder pair work as the guiders of the discriminator. They guide the discriminator to learn what images it should identify to be negative. Different encoder-decoder pairs can restore images to different degrees. Images restored to different degrees can be used to train the discriminator. The discriminator learns that images under a specific restored degree don't belong to the target class. The experiment results on CIFAR-10 show that our method can achieve good performance, with less difficulty in training than the GAN-based counterparts'.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Lane Detection Method Based on Improved RANSAC Algorithm

Lane Detection Method Based on Improved RANSAC Algorithm

引用

International Symposium on Autonomous Decentralized systems (ISADAS)

作者： Jie Guo Zhihua Wei Duoqian Miao Ministry of Education Key Laboratory of Embedded System and Service Computing Shanghai China Department of Computer Science and Technology Tongji University

ISBN: (纸本)9781479982622

Lane detection based on computer vision is a key technology of Automatic Drive system for intelligent vehicles. In this paper, we propose a real-time and efficient lane detection algorithm that can detect lanes appearing in urban streets and highway roads under complex background. In order to enhance lane boundary information and to be suitable for various light conditions, we adopt canny algorithm for edge detection to get good feature points. We use the generalized curve lane parameter model, which can describe both straight and curved lanes. We propose an improved random sample consensus (RANSAC) algorithm combined with the least squares technique to estimate lane model parameters based on feature extraction. Experiments are conducted on both real road lane videos captured by Tongji University and Caltech Lane Datasets. The experimental results show that our algorithm is can meet the real time requirement and fit lane boundaries well in various challenging road conditions.

关键词： Feature extraction Roads Computational modeling Image edge detection Algorithm design and analysis Real-time systems Mathematical model

来源：评论

学校读者我要写书评

暂无评论

keystroke dynamics in password authentication for multi-user account

引用

Journal of Computational Information systems 2015年第1期11卷 321-331页

作者： Zhang, Xiaomeng Zhao, Peihai Wang, Mimi Department of Computer Science and Technology Tongji University Shanghai China The Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China

In the field of identity authentication, existing researches on user keystroke authentication only focus on the situation in which a single user uses a single account. When multiple users share one account, there emerges the problem of inaccurate modeling. The key to construct the keyboard behaviour pattern in a single-account-for-multiple-users case is to cluster and build the unique keyboard behaviour pattern for each user under the shared account. In this paper, the original K-means clustering algorithm is improved by adding variance determination conditions. And when the number of users is unknown, the algorithm will determine whether the account is a multi-user account or not and identify the number of users under the account to carry out keyboard behaviour clustering in a single-account-for-multiple-users situation. We build a model based on keyboard behaviour data after clustering. Compared with other methods, experiments arrive at the expected results. This method can be used for keyboard behaviour authentication in real-world scenarios in which multiple users share one account at home or in companies. ©, 2014, Journal of Computational Information systems. All right reserved.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

SelectCast: Scalable data aggregation scheme in wireless sensor networks

SelectCast: Scalable data aggregation scheme in wireless sen...

引用

IEEE INFOCOM 2011

作者： Wang, Cheng Tang, Shaojie Li, Xiang-Yang Jiang, Changjun Department of Computer Science Tongji University Shanghai China Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai China Department of Computer Science Illinois Institute of Technology Chicago IL 60616 United States TNLIST School of Software Tsinghua University China

ISBN: (纸本)9781424499212

In this work, for a wireless sensor network (WSN) of n randomly placed sensors with node density λ ∈ [1, n], we study the tradeoffs between the aggregation throughput and gathering efficiency. The gathering efficiency refers to the ratio of the number of the sensors whose data have been gathered to the total number of sensors. Specifically, we design two efficient aggregation schemes, called single-hop-length (SLH) scheme and multiple-hop-length (MLH) scheme. By novelly integrating these two schemes, we theoretically prove that our protocol achieves the optimal tradeoffs, and derive the optimal aggregation throughput depending on a given threshold value (lower bound) on gathering efficiency. Particularly, we show that under the MLH scheme, for a practically important set of symmetric functions called perfectly compressible functions, including the mean, max, or various kinds of indicator functions, etc., the data from Θ(n) sensors can be aggregated to the sink at the throughput of a constant order Θ(1), implying that our MLH scheme is indeed scalable. © 2011 IEEE.

关键词： Efficiency

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：