1.这篇文章究竟讲了什么问题?
沉浸式虚拟环境下的情感识别,基于面部情感识别
2.这是否是一个新的问题?
不是
3.这篇文章要验证一个什么科学假设?
基于2D和3D集合特征的表情识别能够在沉浸式虚拟环境下获得较好的识别效果。
- 有哪些相关研究?如何归类?谁是这一课题在这领域值得关注的研究员?
VR用于医疗健康领域的文献:
1)Bekele, Esube Bian, Dayi Zheng, Zhi Peterman, Joel Park, Sohee Sarkar, Nilanjan. 2014.
Responses during Facial Emotional Expression Recognition Tasks Using Virtual Reality
and Static IAPS Pictures for Adults with Schizophrenia. Human-Computer Interaction. - 10.1007/978-3-319-07464-1-21.
- Souto, Teresa Silva, Hugo Leite, Ângela Baptista, Alexandre Queirós, Cristina Marques,
António. 2019. Facial Emotion Recognition: Virtual Reality Program for Facial Emotion
Recognition—A Trial Program Targeted at Individuals With Schizophrenia. Rehabilitation
Counseling Bulletin. 63. 003435521984728. 10.1177/0034355219847284
3)Nyaz Didehbani, Tandra Allen, Michelle Kandalaft, Daniel Krawczyk, Sandra Chap-
man, Virtual Reality Social Cognition Training for children with high functioning
autism, Computers in Human Behavior, Volume 62, 2016, Pages 703-711, ISSN 0747-5632,
https://doi.org/10.1016/j.chb.2016.04.033. - Alcañiz Raya, Mariano Olmos, Elena Abad, Luis. 2019. Use of virtual reality for neurode-
velopmental disorders. A review of the state of the art and future agenda. Medicina. 79.
77-81. - P. C. Petrantonakis and L. J. Hadjileontiadis, "Emotion Recognition From EEG Using Higher
Order Crossings", in IEEE Transactions on Information Technology in Biomedicine, vol.
14, no. 2, pp. 186-197, March 2010. doi: 10.1109/TITB.2009.2034649
情感识别方法:
1)Z. Zhang, L. Cui, X. Liu and T. Zhu, "Emotion Detection Using Kinect 3D Facial Points, "
2016 IEEE/WIC/ACM International Conference on Web Intelligence (WI), Omaha, NE,
2016, pp. 407-410.doi: 10.1109/WI.2016.0063
2)N. Chanthaphan, K. Uchimura, T. Satonaka and T. Makioka, "Facial Emotion Recognition
Based on Facial Motion Stream Generated by Kinect, " 2015 11th International Conference on
Signal-Image Technology and Internet-Based Systems (SITIS), Bangkok, 2015, pp. 117-124.
doi: 10.1109/SITIS.2015.31
3) X. Zhao, J. Zou, H. Li, E. Dellandréa, I. A. Kakadiaris and L. Chen, "Automatic 2.5-
D Facial Landmarking and Emotion Annotation for Social Interaction Assistance, "
in IEEE Transactions on Cybernetics, vol. 46, no. 9, pp. 2042-2055, Sept. 2016. doi:
10.1109/TCYB.2015.2461131
5.论文中提到的解决方案之关键是什么?
主要是将2D、3D角度和人脸关键点之间的欧几里德距离相结合,作为选择的特征。
6.论文中的实验是如何设计的?
LOSO验证,Kinect(v2)、Kinect(v1)、HD RGB分别采用三种不同的方法进行识别。
与其他方法的精度对比。
7.用于定量评估的数据集是什么?代码有没有开源?
收集的17个被试的数据,没有开源
8.论文中的实验及结果有没有很好地支持需要验证的科学假设?
实验结果较好的证明了假设
9.这篇论文到底有什么贡献?
a)比较了RGB和RGB- d数据在人脸表情识别中的性能。
b) 提出了一种基于二维和三维几何特征的沉浸式虚拟环境人脸情感识别方法。
10.下一步呢?有什么工作可以继续深入?
本篇论文没有详细介绍在看表情引诱视频时,被试的人脸表情图片。
未来的工作将集中于在身临其境的虚拟环境中构建人脸虚拟化身动画的实时系统。