Search

Your search keyword '"Zhou, Dajun"' showing total 42 results
Start Over Author "Zhou, Dajun" Publication Year Range Last 10 years
42 results on '"Zhou, Dajun"'

9. Advancement in the EEG-Based Chinese Spelling Systems

Author

Shi, Minghui, Zhou, Changle, Jiang, Min, Hong, Qingyang, Chao, Fei, Xie, Jun, Ren, Weifeng, Zhou, Dajun, Yang, Tianyu, Liu, Xiangqian, Hutchison, David, Series editor, Kanade, Takeo, Series editor, Kittler, Josef, Series editor, Kleinberg, Jon M., Series editor, Mattern, Friedemann, Series editor, Mitchell, John C., Series editor, Naor, Moni, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Weikum, Gerhard, Series editor, Kubota, Naoyuki, editor, Kiguchi, Kazuo, editor, Liu, Honghai, editor, and Obo, Takenori, editor

Published
2016
Full Text
View/download PDF

12. Advancement in the EEG-Based Chinese Spelling Systems

Author

Shi, Minghui, primary, Zhou, Changle, additional, Jiang, Min, additional, Hong, Qingyang, additional, Chao, Fei, additional, Xie, Jun, additional, Ren, Weifeng, additional, Zhou, Dajun, additional, Yang, Tianyu, additional, and Liu, Xiangqian, additional

Published
2016
Full Text
View/download PDF

15. Efficient Imitation Learning for Game AI

Author

Huang Chao, Zhou Dajun, Zhang Like, and Jing Yanqing

Subjects
business.industry, Computer science, Interface (computing), Variation (game tree), Machine learning, computer.software_genre, Automation, Set (abstract data type), Software, Discriminative model, Data structure alignment, Artificial intelligence, Noise (video), business, computer
Abstract

Automation testing is an important approach for bug detection and analysis of software applications, especially for computer games. This paper proposes an efficient imitation method to learn game strategy from a small set of manually recorded game samples, which only takes one hour to complete training. This work can be divided into four steps. Firstly, we collect a set of manually recorded data composed of image frames and user actions. The discriminative region is extracted from image to eliminate noise. Then, data alignment is applied to solve the problem of action delay. Due to the large variation of image samples from different classes, data resampling is performed to avoid bias. Finally, these samples are fed into a fast and lightweight network with LSTM structure, which is designed to boost speed of prediction. Our work discards the dependence of game internal interface and performs well in real time with CPU, which has been verified in a variety of commercial games.

Published
2020

16. Human-like UI Automation through Automatic Exploration

Author

Zhou Dajun, Zhang Like, Li Xudong, and Jing Yanqing

Subjects
InformationSystems_INFORMATIONINTERFACESANDPRESENTATION(e.g.,HCI), business.industry, Computer science, ComputerApplications_COMPUTERSINOTHERSYSTEMS, Directed graph, Graphical user interface testing, computer.software_genre, Convolutional neural network, Automation, Test (assessment), InformationSystems_MODELSANDPRINCIPLES, Test case, Mobile phone, Scripting language, Human–computer interaction, business, computer
Abstract

Most UI testing tools for mobile games are designed to help us create and run the test cases with scripts. However, these scripts must be manually updated for new test cases, which increases the test cost. In this paper, we propose a method to implement humanlike UI automation through automatic exploration in mobile games. Our method can automatically explore most UIs by recognizing and operating the UI elements similar to manual UI testing. First, we design a lightweight convolutional neural network to detect the buttons in the UI image captured from the mobile phone. Next, we build a directed graph model to store the visited UIs during automatic exploration. Finally, according to our exploration strategy, we choose one button from the UI image and send a click action to the mobile phone. Our method obtains over 85% UI and button coverage rates on three popular mobile games.

Published
2020

19. RGVCD

Author

Zhang Like, Zhou Dajun, Jing Yanqing, and Huang Chao

Subjects
Computer science, business.industry, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Optical flow, Set (abstract data type), Task (computing), Range (mathematics), Computer vision, Data pre-processing, Artificial intelligence, CLIPS, Cluster analysis, business, Video game, computer, computer.programming_language
Abstract

Interesting video clip detection is an important task in computer vision, which can be used as data preprocessing for a wide range of applications such as video retrieval and content-based video clustering. In this paper, we propose a new real-time game video clip detection system for interesting moments termed as RGVCD. During training period, we generate a set of game video clips to train a spatial-temporal network. Given a test video, RGVCD first generates potentially interesting video clips. For each clip, we extract features from images and optical flow using deep convolutional network. Finally, RGVCD outputs interesting degree score based on the spatial-temporal features. Additionally, we collect a set of games video clips and provide the corresponding binary label to denote whether the video clip is of our interest. With this dataset, our system demonstrates its efficiency in real-time interesting video clip detection with high accuracy.

Published
2018

20. RGVCD

Author

Huang, Chao, primary, Zhang, Like, additional, Jing, Yanqing, additional, and Zhou, Dajun, additional

Published
2018
Full Text
View/download PDF

23. Study of Incremental Bending Test on Aluminum Sheets

Author

Xu, Wan, primary, Li, Junrui, additional, Yang, Guobiao, additional, Wu, Ruoding, additional, Yang, Lianxiang, additional, Du, Changqing, additional, Zhou, Dajun, additional, Deng, Zhi, additional, Mcguire, John, additional, and Dasu, Raj, additional

Published
2018
Full Text
View/download PDF

24. Test of Inclined Double Beads on Aluminum Sheets

Author

Zhang, Boyang, primary, Xu, Wan, additional, Yang, Guobiao, additional, Li, Junrui, additional, Yang, Lianxiang, additional, Zhou, Dajun, additional, Du, Changqing, additional, Li, Kaiping, additional, and Rawya, Bazzi, additional

Published
2018
Full Text
View/download PDF

29. RGVCD.

Author

Huang, Chao, Zhang, Like, Jing, Yanqing, and Zhou, Dajun

Published
2018
Full Text
View/download PDF

42. Corpus-based Machine Translation: Its Current Development and Perspectives.

Author

Zhou Dajun and Wang Yun

Subjects
MACHINE translating, LINGUISTICS -- Methodology, NATURAL language processing, SEMANTICS, HUMAN-machine systems
Abstract

Corpus technology was introduced to rule-based machine translation (MT) in the late 1980s. Corpus-based MT mainly includes statistic-based MT and example-based MT - the former lays emphasis on statistic model from mathematics, the latter inference through example translation from machine learning. The semanticbased method will become the trend in statistical MT development, while the perspectives for corpus-based MT system is to combine the latest research fruits of theories and technologies of various subjects concerned and to develop multi-mode corpus. [ABSTRACT FROM AUTHOR]

Published
2015

Catalog

Books, media, physical & digital resources
See catalog results