Now 8750 visitors
Today:0 Yesterday:0
Total: 143041 216S 51P 5R
2026-10-21, Week 43
Member Login
TACT Journal Homepage
Call for Paper
Committee
Find My Paper
Author Homepage
Statistics & History
Welcome Message
Paper Procedure
FAQ
Paper Archives
Outstanding Papers
Program & Proceedings
Presentation Platform
Hotel & Travel Info
Photo Gallery
Scheduler Login
Seminar
Archives Login
Sponsors


















Online Q&A Session
Paper Number Author:
Paper Title
Keyword
Q&A Number **Select your question number !!
Questioner eMail:
Question
Answer
by
Author
Save Q&A

* Edit or answer any Q&A by selecting Q&A number Hyper Link below + Write button (Save)
ICACT20230035 Question.1
Questioner: vuvietvu@vnu.edu.vn    2023-02-20 오후 7:20:48 		ICACT20230035 Answer.1
Answer by Auhor 21m107fl@stu.teikyo-u.ac.jp   2023-02-20 오후 7:20:48
Chrome Click!!
What is the training time of the proposed method compared with other methods? Thank you for your question. For the training time of the SCN-SAM, due to the different sizes of the datasets, the training time of SCN-SAM on RAF-DB and FERPlus is not the same. The training time on RAF-DB and FERPlus is approximately 90 minutes and 138 minutes, respectively. As for the training time of other methods, we are not very clear, so we did not compare the training time of the model. The main purpose of our research is to improve the accuracy of the method.
ICACT20230035 Question.2
Questioner: mjs9908@g.skku.edu    2023-02-22 오후 12:41:08 		ICACT20230035 Answer.2
Answer by Auhor 21m107fl@stu.teikyo-u.ac.jp   2023-02-22 오후 12:41:08
Chrome Click!!
hi thank you for your presentation Is there any problem in your experiments? If problem is existed, how did you solve it? Thank you for your question. In the experimental steps of this research, the parameter setting of the experiments in the comparison of the experimental results of our proposed new model and other methods are consistent, both in the case of the dataset with and without face masks. Therefore, if there are problems in the experiment, the impact on the experimental results is also very low. Moreover, the parameter setting of the experiments in this research is not complicated. If there are problems in the experiments, the experimental parameters can be reset and the experiments can be performed again.
ICACT20230035 Question.3
Questioner: vuvietvu@vnu.edu.vn    2023-02-23 오후 4:13:58 		ICACT20230035 Answer.3
Answer by Auhor 21m107fl@stu.teikyo-u.ac.jp   2023-02-23 오후 4:13:58
Chrome Click!!
What is the effect of training data for the testing data? Thank you for your question. We mined the samples with high-importance weight in the training data, and then let the model pay more attention to the features of these training samples during training, to improve the recognition accuracy of the testing data.