作者机构:
[Xu, Luhui; Gan, Yanling; Chen, Jingying] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Hubei, Peoples R China.
通讯机构:
[Chen, Jingying] C;Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Hubei, Peoples R China.
关键词:
Head pose estimation;Convolutional neural network;Soft labels;Regularized architecture
摘要:
Head pose estimation has many wide applications such as driver monitoring, attention recognition and multi-view facial analysis. Most of the previous works routinely utilize detected face regions to further estimate head pose with hard labels, which limits to explore more discriminative texture information and tends to over-fit. In this paper, we present a novel framework to alleviate this problem, which takes entire images as input and constructs soft labels using a Gaussian distribution function as supervision information, and then introduces a regularized convolutional neural network architecture that is optimized by two types of similarity measure functions: Kullback–Leibler divergence loss and Jeffreys divergence loss. The regularized architecture includes four modules: one backbone net for learning common features, two parallel branches named sub-net1 and sub-net2 for learning complementary features and one feature fusion module, namely, fused net. The architecture is trained in an alternately training fashion, making the learned model more robust and stable. Extensive experiments have been carried out on three public datasets: Pointing04, CAS-PEAL-R1 and CMU Multi-PIE. The results show that our method achieves a significant improvement in performance compared to the state of the art. The best accuracy on the three datasets we achieve are 85.77%, 99.19% and 99.88%, respectively.
摘要:
Facial expression recognition (FER) has recently attracted increasing attention with its growing applications in human-computer interaction and other fields. But a well-performing convolutional neural network (CNN) model learned using hard label/single-emotion label supervision may not obtain optimal performance in real-life applications because captured facial images usually exhibit expression as a mixture of multiple emotions instead of a single emotion. To address this problem, this paper presents a novel FER framework using a CNN and soft label that associates multiple emotions with each expression. In this framework, the soft label is obtained using a proposed constructor, which mainly involves two steps: (1) training a CNN model on a training set using hard label supervision; (2) fusing the latent label probability distribution predicted by the trained model to obtain soft labels. To improve the generalization performance of the ensemble classifier, we propose a novel label-level perturbation strategy to train multiple base classifiers with diversity. Experiments have been carried out on 3 publicly available databases: FER-2013, SFEW and RAF. The results indicate that our method achieves competitive or even better performance (FER-2013: 73.73%, SFEW: 55.73%, RAF: 86.31%) compared to state-of-the-art methods. (C) 2019 Published by Elsevier B.V.
摘要:
With the rapid development of MOOC platforms, the online learning resources are increasing. Because learners differ in terms of cognitive ability and knowledge structure, they cannot rapidly identify learning resources in which they are interested. Traditional collaborative filtering recommendation technologies perform poorly given sparse data and cold starts. Furthermore, the redundant recommended content and the high-dimensional and nonlinear data on online learning users cannot be effectively handled, leading to inefficient resource recommendations. To enhance learner efficiency and enthusiasm, this paper presents a highly accurate resource recommendation model (MOOCRC) based on deep belief networks (DBNs) in MOOC environments. This method deeply mines learner features and course content attribute features and incorporates learner behavior features to build user-course feature vectors as inputs to the deep model. Learner ratings of courses are processed as supervised labels with supervised learning. The MOOCRC model is trained by unsupervised pretraining and supervised feedback fine tuning; moreover, the model is obtained by adjusting the model parameters repeatedly. To verify the effectiveness of the MOOCRC, an experimental analysis is conducted using learner elective data obtained from the starC MOOC platform of Central China Normal University. Real course enrollment data are used to verify the classification accuracy of the MOOCRC. The experimental results show that the MOOCRC has greater recommendation accuracy and converges more quickly than traditional recommendation methods.
作者:
Du, Xu;Yang, Juan;Shelton, Brett;Hung, Jui-Long
期刊:
Information Discovery and Delivery,2019年47(4):173-181 ISSN:2398-6247
通讯作者:
Yang, J
作者机构:
[Du, Xu; Yang, Juan] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Hubei, Peoples R China.;[Shelton, Brett; Hung, Jui-Long] Boise State Univ, Dept Educ Technol, Boise, ID 83725 USA.;[Hung, Jui-Long] Cent China Normal Univ, Natl Engn Lab Educ Big Data, Wuhan, Hubei, Peoples R China.
通讯机构:
[Yang, J ] ;Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Hubei, Peoples R China.
作者:
Cai, Jin;Yang, Harrison Hao*;Gong, Di;MacLeod, Jason;Zhu, Sha
期刊:
Journal of Computing in Higher Education,2019年31(1):137-155 ISSN:1042-1726
通讯作者:
Yang, Harrison Hao
作者机构:
[Cai, Jin] Cent China Normal Univ, Collaborate & Innovat Ctr Educ Technol, Wuhan, Hubei, Peoples R China.;[MacLeod, Jason; Yang, Harrison Hao] Cent China Normal Univ, Sch Educ Informat Technol, Wuhan, Hubei, Peoples R China.;[Gong, Di] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Hubei, Peoples R China.;[Cai, Jin] Hubei Univ Educ, Wuhan, Hubei, Peoples R China.;[Yang, Harrison Hao] SUNY Coll Oswego, Sch Educ, Oswego, NY 13126 USA.
通讯机构:
[Yang, Harrison Hao] C;[Yang, Harrison Hao] S;Cent China Normal Univ, Sch Educ Informat Technol, Wuhan, Hubei, Peoples R China.;SUNY Coll Oswego, Sch Educ, Oswego, NY 13126 USA.
作者机构:
[Ji, Yuchao; Yin, Xinyi; Gong, Shengnan] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430000, Hubei, Peoples R China.
会议名称:
7th International Conference on Information and Education Technology (ICIET)
会议时间:
MAR 29-31, 2019
会议地点:
Univ Aizu, Aizuwakamatsu, JAPAN
会议主办单位:
Univ Aizu
关键词:
Educational video game;Bibliometrics;Visual analysis;Review
摘要:
Since the advent of video games, its powerful interactivity and simulation have attracted the attention of all walks of life, and the "educational video games" formed by the combination of education and video games has also set off in-depth research and exploration by scholars at home and abroad. This paper sorts out the relevant literature from 2008 to 2017 by searching the literature on educational video games in Web of Science and using the methods of bibliometrics and visual analysis. This paper compares the distribution of published time, high-yield research institutions and high-yield researchers, in the educational video game field between China and the United States. Then it reveals the hotspots and development trends of educational video game research in the past ten years. Finally, it summarizes the differences in between China and the United States and gives suggestions for targeted development in the field of educational video games.
作者机构:
[Wang, Xuan] Cent China Normal Univ, Collaborat Innovat Ctr Educ Informat Technol, Wuhan, Hubei, Peoples R China.;[Yang, Harrison Hao] SUNY Coll Oswego, Sch Educ, Oswego, NY 13126 USA.;[Yang, Harrison Hao] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Hubei, Peoples R China.;[Zuo, Can] Hubei Univ Econ, Sch Int Educ, Wuhan, Hubei, Peoples R China.
会议名称:
International Symposium on Educational Technology (ISET)
会议时间:
JUL 02-04, 2019
会议地点:
Univ Hradec Kralove, Hradec Kralove, CZECH REPUBLIC
会议主办单位:
Univ Hradec Kralove
关键词:
educational WeChat official accounts (EOAs);Uses and Gratifications Theory;effects of EOAs;users' gratifications;features of EOAs
摘要:
This study examined the effects of educational WeChat official accounts from five main aspects of users' behavior and learning process: recognizing, following, reading, sharing and learning/reflecting. Two factors important to the effects of educational WeChat official accounts were identified: users' gratifications and features of educational WeChat official accounts. The results of this study indicated that both the degree of users' gratifications and features of educational WeChat official accounts were positively related to the effects of educational WeChat official accounts.
作者机构:
[Lu, Wei; Wen, Xiaoqiao; Wang, Yongliang] Air Force Early Warning Acad, Wuhan 430019, Hubei, Peoples R China.;[Peng, Shixin] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Hubei, Peoples R China.;[Zhong, Liang] China Univ Geosci, Dept Commun Syst, Wuhan 430074, Hubei, Peoples R China.
通讯机构:
[Lu, Wei] A;Air Force Early Warning Acad, Wuhan 430019, Hubei, Peoples R China.