Where Is My Mind (Looking at)? A Study of the EEG–Visual Attention Relationship

Round 1

Reviewer 1 Report

This paper has done a very interesting work. The authors use EEG to predict the visual attention of the subjects, and the results obtained are similar to those predicted by traditional observation methods. The proposed method is technically feasible, the experimental process is scientific, detailed and rigorous, and the experimental data is abundant. I think this article is worth considering for publication. Here are a few tips to make the paper more informative:
1. Could the authors discuss the experimental effects under different stimuli conditions, such as text, images, videos, etc.?
2. Could the authors discuss the integration of the proposed method with eye tracking technology?

Author Response

Dear reviewer, 

Please file enclosed the response to the reviewer's comments. 

Best regards, 

Author Response File: Author Response.pdf

Reviewer 2 Report

The theme of the study has some degree of innovation. It has potential contributions. The author narrates rich mathematical derivation and details, thanks to the author for their contributions. Also, some important points need to be addressed to improve the quality and scientificity.

1. Figure 1 is too forward and should appear in 3.1. The 1) and 2) in Figure 1 are not clear.
2. Although reference [16] was published in 2020, this model appeared in the field of saliency prediction in 2018. Are there other similar excellent networks that can also be applied to EEG? Such as EML-Net, SAM-ResNet, etc?
3. The BCE of equation 1 and the MSE of equation 2 in 3.4 do not correspond to the text. In addition, BCE loss is more common than MSE loss. Is there any particularity that I ignore for using MSE?
4. The input and output of saliency prediction both are key parameters. It should be shown in the figure.
5. Figure 3 shows only the author's two model results. Is there any work of other scholars in the author's field that can be compared? The comparison of saliency prediction models usually requires the comparison of saliency maps of multiple models, model visualization and model ablation analysis. If such work is not needed in the field of the author's research, it should be explained.

Author Response

Dear reviewer,

Please file enclosed the response to the reviewer's comments.

Best regards,

Author Response File: Author Response.pdf

Reviewer 3 Report

See my comments in the attached pdf file.

Comments for author File: Comments.pdf

Author Response

Dear reviewer,

Please file enclosed the response to the reviewer's comments.

Best regards,

Author Response File: Author Response.pdf

Round 2

Reviewer 2 Report

The authors have addressed the all issues, so I think the manuscript is acceptable.