Review Reports

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

The abstract of this paper should be re-written. Authors should mention dataset they used. They need to emphasize the novelty. The most important quantitative findings should be emphasized.

Lines 23-26: No need to provide that many references since you are not mentioning details of them.

There are too many references in the introduction section and most of them are only listed. Please only use the necessary references and provide more explanation on them.

Lines 28-31: very short sentences

 

You need to use some references for the Section 3.

 

You should include IoU score, precision, recall and F1 values for your experiments.

There should be a concrete discussion section in which you should comprehensively analyze your results with respect to similar studies in the literature. Please mention about drawbacks of your method in terms of visual and statistical results.

The conclusion section is very weak. It is not delivering and scientific message and future insights.

Comments on the Quality of English Language

The conclusion section is very weak. It is not delivering and scientific message and future insights.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

The model created by the authors is very interesting and depending on the results obtained, it leads to a good development of the process of re-identification of the person.

The research conducted is presented as being without limitations. Is it really so? For example, weather conditions have no influence? This aspect needs to be clarified and completed.

I recommend the authors to develop the Conclusions chapter. To improve the research, I recommend that the authors supplement this chapter to compensate for the lack of a discussion section.

Comments on the Quality of English Language

I noticed that there are small typos. For example, on line 247, the space between two words is missing.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors

In this review, the focus is on a person Re-ID method based on multi-branch feature fusion (MFFNet) to solve the problem of insufficient ability of the single-branch network to mine diverse features. Three different branches to solve the problems of person Re-ID in different and complex scenes were used. This interesting topic comes within the scope of the Applied Sciences Journal.

The proposed method is promising, however, some concerns regarding your manuscript need to be resolved as follows:

 

1) What are some of the method's shortcomings, and how may they be overcome? 

2) In the Conclusion section, the authors should concentrate more on the implication of their findings for the development and optimization of the improvement of the system.

Comments on the Quality of English Language

Minor editing of English language required

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 4 Report

Comments and Suggestions for Authors

I would like to thank the authors for a good paper.  However, there are some issues that I am asking authors to address.

1) While the abstract provides an overview of the methodology and the challenges it aims to address, I believe it would benefit significantly from the inclusion of quantitative results (such accuracy, F1 score etc).

2) You have a lot of words that look like the following: represen- tations, main- stream, at- tention, etc... Please correct all these mistakes since it's misleading the readers.

3) Why is the last paragraph of the introduction section mentioning results?

4) Please correct the word "Transformer" in Figure 2.

5) Could you please provide some insight into how you determined the specific probability value of 0.3 for simulating lighting differences by applying random grayscale to the original image in the partial branch of the mixed attention area? Were there specific considerations or experiments that led to this choice?

6) Please replace "Ours" with "this work/paper" in Table 1.

7) Finally, the absence of a limitation section in the paper is a notable shortcoming. Please dedicate a paragraph mentioning the limitations and future directions of the current work.

Comments on the Quality of English Language

Minor editing of English language required

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Comments and Suggestions for Authors

Authors responded most of my comments. However, the concern for the discussion was not solved. They should have a dedicated section in ehich they compare their results with the recent literature.

After revising the discussion, the manuscript could be published.

Comments on the Quality of English Language

Minor editing of English language required

Author Response

Please see the attachment.

Author Response File: Author Response.pdf