检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Yang, Ke Shen, Xiaolong Qiao, Peng Li, Shijie Li, Dongsheng Dou, Yong National Laboratory for Parallel and Distributed Processing College of Computer National University of Defense Technology Changsha China

Temporal action localization is an important task of computer vision. Though many methods have been proposed, it still remains an open question how to predict the temporal location of action segments precisely. Most state-of-the-art works train action classifiers on video segments pre-determined by action proposal. However, recent work found that a desirable model should move beyond segment-level and make dense predictions at a fine granularity in time to determine precise temporal boundaries. In this paper, we propose a Frame Segmentation Network (FSN) that places a temporal CNN on top of the 2D spatial CNNs. Spatial CNNs are responsible for abstracting semantics in spatial dimension while temporal CNN is responsible for introducing temporal context information and performing dense predictions. The proposed FSN can make dense predictions at frame-level for a video clip using both spatial and temporal context information. FSN is trained in an end-to-end manner, so the model can be optimized in spatial and temporal domain jointly. We also adapt FSN to use it in weakly supervised scenario (WFSN), where only video level labels are provided when training. Experiment results on public dataset show that FSN achieves superior performance in both frame-level action localization and temporal action localization. Copyright © 2019, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Container-Based Complex Programming Skills Training Platform

Container-Based Complex Programming Skills Training Platform

引用

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

作者： Wei Wang Tao Wang Gang Yin National Laboratory for Parallel and Distributed Processing National University of Defense Technology Changsha Hunan Province China

ISBN: (数字)9781728109459

ISBN: (纸本)9781728109466

In recent years, online programming education and evaluation have developed rapidly. The traditional online education platform focuses on the teaching of knowledge, lacking a good evaluation platform to assess the learning outcomes, while the existing online evaluation platform only focuses on the evaluation of algorithms or languages. Until now, no platform can support the training of engineering-level complex technologies. In this paper, we present our solution - Educoder. Educoder is an one-stop service platform that integrates “teaching”, “learning” and “use”. It not only supports simple programming language training type, but also supports the training of complex technology such as Hadoop, Spring, Machine Learning, Docker, etc. The code environment for student learning and evaluation is managed by Gitlab, and the runtime environment is provided by Kubernetes pod, which guarantees good isolation. For complex types of training, we provide the Docker Web Terminal module for SSH connection to enter the pod for operation and use docker in docker technology to provide support for training that requires multiple services or multiple nodes. In Educoder, we use scripts to serialize the training evaluation steps, and we formed a private evaluation script template library for training teacher to reference, which greatly reduced the time cost of writing a new training course.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Quantitative analysis of collaborative-based annotation in software engineering education 8

Quantitative analysis of collaborative-based annotation in s...

引用

2018 8th International Workshop on Computer Science and Engineering, WCSE 2018

作者： Yu, Jie Wang, RenMin Zeng, LingBin Wang, Tao Yin, Gang Fan, Qiang Yu, Yue National Laboratory for Parallel and Distributed Processing National University of Defense Technology Changsha China

ISBN: (纸本)9789811178610

The primary goal of software engineering education is to develop the ability of students, a common method is to let students to read excellent open source code, so that students can improve themselves through this behavior. When reading the code, we tend to add comments to the code, in the past, the labeling of students tend to be an independent behavior, in this paper we analyze the quantitative of collaborative-based code annotation method, and the result shows the collaborative-based code annotation method is working well in improving students programming skills. © Proceedings of 2018 the 8th International Workshop on Computer Science and Engineering, WCSE 2018. All rights reserved.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

A Heterogeneous Processor Design for CNN-Based AI Applications on IoT Devices

引用

Procedia Computer Science 2020年 174卷 2-8页

作者： Zhiqiang Liu Jingfei Jiang Guoqing Lei Kai Chen Buyue Qin Xiaoqiang Zhao Artificial Intelligence Research Center National Innovation Institute of Defense Technology Beijing China National Laboratory for Parallel and Distributed Processing National University of Defense Technology Changsha China College of Computer National University of Defense Technology Changsha China College of System Engineering National University of Defense Technology Changsha China

This paper proposes a heterogeneous processor design for CNN-based AI applications on IoT devices. The heterogeneous processor contains an embedded RISC-V CPU that works as a general processor and an efficient CNN-accelerator that supports a variety of CNN models with a list of macro instructions. For demonstration, we implement a prototype on an FPGA platform with the RISC-V CPU working under 20 MHz and the CNN accelerator working under 100 MHz. As a case study, we run a CNN-based face detection and recognition application on this prototype. The prototype can process one image in 0.72 seconds and an ASIC implementation working under 400 MHz can process one image in less than 0.15 seconds by estimation, which can satisfy the needs for many IoT scenarios such as access control systems and check-in systems.

关键词： Processor RISC-V Accelerator AI (Artificial Intelligence) CNN (Convolutional Neural Network) IoT (Internet of Things)

来源：评论

学校读者我要写书评

暂无评论

Rev Rec: A two-layer reviewer recommendation algorithm in pull-based development model

引用

Journal of Central South University 2018年第5期25卷 1129-1143页

作者：杨程张迅晖曾令斌范强王涛余跃尹刚王怀民 National Laboratory for Parallel and Distributed Processing College of ComputerNational University of Defense Technology

Code review is an important process to reduce code defects and improve software quality. In social coding communities like GitHub, as everyone can submit Pull-Requests, code review plays a more important role than ever before, and the process is quite time-consuming. Therefore, finding and recommending proper reviewers for the emerging Pull-Requests becomes a vital task. However, most of the current studies mainly focus on recommending reviewers by checking whether they will participate or not without differentiating the participation types. In this paper, we develop a two-layer reviewer recommendation model to recommend reviewers for Pull-Requests （PRs） in GitHub projects from the technical and managerial perspectives. For the first layer, we recommend suitable developers to review the target PRs based on a hybrid recommendation method. For the second layer, after getting the recommendation results from the first layer, we specify whether the target developer will technically or managerially participate in the reviewing process. We conducted experiments on two popular projects in GitHub, and tested the approach using PRs created between February 2016 and February 2017. The results show that the first layer of our recommendation model performs better than the previous work, and the second layer can effectively differentiate the types of participation.

关键词： Pull-Request code reviewer recommendation GitHub open source community

来源：评论

学校读者我要写书评

暂无评论

Optimizing the efficiency and openness of the Kubernetes based code evaluation platform 8

Optimizing the efficiency and openness of the Kubernetes bas...

引用

2018 8th International Workshop on Computer Science and Engineering, WCSE 2018

作者： Zhang, Zhixiong Yin, Gang Wang, Tao Wang, Wei National Laboratory for Parallel and Distributed Processing National University of Defense Technology Changsha410073 China

ISBN: (纸本)9789811178610

With the popularity of programming learning, there are more and more online programming platforms and learners can learn programming skills online. That's good news for users who was bothered by configuring a development environment or some other annoying little things. We have built a multi-purpose code evaluation platform which provides many different kinds of coding training courses. This code evaluation platform is based on Kubernetes and provides unique containers for every submission of users' code so that it's not a problem that many different types of code are running at the same time. Furthermore, it allows experts share their programming skills or other computer technical abilities by creating training courses on the platform, and they can even customize the evaluation methods and the evaluation process of their own training courses by producing new evaluation script. To obtain better user experience for both learners and training contributors, some useful auxiliary systems, such as the evaluating queuing system and the script management system have been introduced. © Proceedings of 2018 the 8th International Workshop on Computer Science and Engineering, WCSE 2018. All rights reserved.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

Versionized process based on non-volatile random-access memory for fine-grained fault tolerance

引用

Frontiers of Information Technology & Electronic Engineering 2018年第2期19卷 192-205页

作者： Wen-zhe ZHANG Kai LU Xiao-ping WANG Science and Technology on Parallel and Distributed Processing Laboratory College of ComputerNational University of Defense Technology

Non-volatile random-access memory（NVRAM） technology is maturing rapidly and its byte-persistence feature allows the design of new and efficient fault tolerance mechanisms. In this paper we propose the versionized process（Ver P）, a new process model based on NVRAM that is natively non-volatile and fault tolerant. We introduce an intermediate software layer that allows us to run a process directly on NVRAM and to put all the process states into NVRAM, and then propose a mechanism to versionize all the process data. Each piece of the process data is given a special version number, which increases with the modification of that piece of data. The version number can effectively help us trace the modification of any data and recover it to a consistent state after a system *** with traditional checkpoint methods, our work can achieve fine-grained fault tolerance at very little cost.

关键词： Non-volatile memory Byte-persistence Versionized process Version number

来源：评论

学校读者我要写书评

暂无评论

Study on the Drill of Maritime Rescue Oriented Modeling Method of Climate Background Environment

Study on the Drill of Maritime Rescue Oriented Modeling Meth...

引用

作者： Sha Chang Xuyun Zhao Bin Song Yu Wang Institute of Meteorology and Oceanography National University of Defense Technology National Laboratory for Parallel and Distributed Processing National University of Defense Technology

In order to provide an about real-world rescue environment for marine rescue simulation training, meteorological marine environment modeling becomes more and more important. In the modeling of meteorological ocean environment, the modeling method of complex environment is becoming more and more mature and the models are becoming more sophisticated, while the climate background models are often overlooked. How to provide real and accurate data-based climate background modeling for marine rescue simulation training has become an urgent problem to be solved. Based on the seasonal-trend decomposition procedure based on Loess(STL) and statistical feature modeling method, a modeling method for constructing dynamic climate background modeling using climate time series is proposed. For different climate model simulation application and the specific characteristics of climate change, our method builds the dynamic climate background model for different sea areas and different months accordingly, while considering the changing of climatic factors at different time scales. The dynamic climate background model is composed of four climate trend models with different time periods, namely, the annual variation trend of climate elements, the daily mean anomaly variation trend, the daily variation trend and the random perturbation. This modeling method of climate background model is not just a way to reflect the trends of climate change, but also to provide a dynamic and numerical climate background information for simulation training. As a result, providing this information to the commander or the rescue equipment can further improve the effectiveness of maritime rescue drill.

关键词： Maritime rescue Simulation training Dynamic climate background model STL decomposition theory

来源：评论

学校读者我要写书评

暂无评论

parallel computing for large-scale author name disambiguation in medline 21

Parallel computing for large-scale author name disambiguatio...

引用

21st IEEE International Conference on High Performance Computing and Communications, 17th IEEE International Conference on Smart City and 5th IEEE International Conference on Data Science and Systems, HPCC/SmartCity/DSS 2019

作者： Tang, Anyao Wu, Chengkun Liu, Jie Wang, Wei Yang, Xi Xing, Yuting Science and Technology on Parallel and Distributed Processing Laboratory Laboratory of Software Engineering for Complex Systems National University of Defense Technology Changsha410073 China State Key Laboratory of High Performance Computing College of Computer National University of Defense Technology Changsha410073 China College of Computer National University of Defense Technology Changsha 410073 China

ISBN: (纸本)9781728120584

Author name disambiguation (AND) is an important task in the field of scientific data mining. It has become a great challenge with the rapid growth of academic digital libraries. The task of AND for a large number of authors is computationally intensive. In particular, an author's name in MEDLINE is represented by full last name and initials, like 'Zhang S', which leads to a lot of identical strings that actually represent different names. In this paper, we proposed an efficient algorithm for parallel AND computation. The proposed algorithm mainly addresses the load balancing issue across many computing nodes. It involves the following strategies:(1) Author-based load balancing, which splits the computation load for each core by author name labels. (2) Matrix-based strategy, which calculates the pairwise similarity between publications and saves them in a matrix globally shared by all processes. Then group them by width-first search. We combine the above two strategies, the second of which is used to calculate authors with a large number of documents, and the other authors apply the first. We constructed a publications database written by Chinese authors from MEDLINE, the biggest public database for biomedical literature (abstracts). For benchmark testing, we experimented our algorithm with a dataset of 1 million publications on the Tianhe-2A supercomputer. Firstly, we trained an AND classifier that can achieve 98.1% of F1. The serial computation time is estimated to be approximately 246 hours, while the parallel execution time is approximately 66 hours in the case of four cores on a single node (with a speedup of 3.7x). Finally, we reduced the total parallel computing time of 1 million documents to about 2 hours and achieved 65.8% of parallelism efficiency using 200 cores on 90 nodes. © 2019 IEEE.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based Cooperative Trail Following for Multi-Robot System

Deep Learning-based Cooperative Trail Following for Multi-Ro...

引用

2018 International Joint Conference on Neural Networks, IJCNN 2018

作者： Geng, Mingyang Li, Yiying Ding, Bo Wang, And Huaimin National Key Laboratory of Parallel and Distributed Processing College of Computer National University of Defense Technology ChangSha China

ISBN: (纸本)9781509060146

Following trails in the wild is an essential capability of out-door autonomous mobile robots. Recently, deep learningbased approaches have made great advancements in this field. However, the existing research only focuses on the trail following with a single robot. In contrast, many robotic tasks in the reality, such as search and patrolling, are conducted by a group of robots. While these robots are grouped to move in the wild, they can cooperate to significantly promote the trail following accuracy, for example, by sharing images of different view angles or real-time decision fusion. This paper proposes such an approach named DL-Cooper that enables multi-robot visionbased trail following based on deep learning algorithms. It allows each robot to make a decision respectively with deep neural network and then fusion the decisions on the collective level with the support of back-end cloud computing infrastructure. It also takes Quality of Service (QoS) assurance, a very essential property of robotic software, into consideration. By limiting the condition to fusion decisions, the time latency can be minimally sacrificed. Experiments on the real-world dataset show that our approach has significantly improved the accuracy of the singlerobot system. © 2018 IEEE.

关键词： Multipurpose robots

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：