All reviews of published articles are made public. This includes manuscript files, peer review comments, author rebuttals and revised materials. Note: This was optional for articles submitted before 13 February 2023.
Peer reviewers are encouraged (but not required) to provide their names to the authors when submitting their peer review. If they agree to provide their name, then their personal profile page will reflect a public acknowledgment that they performed a review (even if the article is rejected). If the article is accepted, then reviewers who provided their name will be associated with the article itself.
Based on the reviewer's comments, the paper is now in good shape to be published.
No comment
No comment
No comment
no comment.
no comment.
no comment.
The authors should take the reviewers' comments into consideration in order to improve the overall quality of the paper.
[# PeerJ Staff Note: Please ensure that all review and editorial comments are addressed in a response letter and any edits or clarifications mentioned in the letter are also inserted into the revised manuscript where appropriate. It is a common mistake to address reviewer questions in the response letter but not in the revised manuscript. If a reviewer raised a question then your readers will probably have the same question so you should ensure that the manuscript can stand alone without the response letter. Directions on how to prepare a response letter can be found at: https://peerj.com/benefits/academic-rebuttal-letters/ #]
There is a misspelling .....Apperance..even in the Title.
It should be taken care of before submission.
No comment
No comment
General Comments
This paper is concerned with personal image generation through graph-based networks along with decomposed particular attributes.
The authors put efforts to propose a generative adversarial network based on the graph.
Both qualitative and quantitative experiments were performed to confirm the proposed method.
The paper is interesting and will be beneficial to a sizable amount of researchers and students.
However the tying error even in the title of the paper ……Apperance …..
should be taken care of before submission.
Such errors are also seen in the text (For example Line 120)
Particular Comments.
1. Line 78 and Lines 93-94, the two statements about the proposed method may confuse the readers. Are they the same or different contributions?
2. Lines 147-148 Can we get the 18 joint points automatically?
3. I wonder how we can know the probabilities defined in equation 11 are non-zero.
The experimental results seem to be significant.
The authors should check the manuscript once again by themselves.
- First of all, there are spelling mistakes in the title, and the capitalization rules are not consistent.
- The single-byte space after the commas and periods are not consistent.
- The operators that are supposed to be Hadamard products are written as e.
- Section 3.1 and 3.2 have the same titles. Perhaps 3.1 should be called "Encoder".
The method is written in a relatively clear manner, including mathematical expressions, but it does not correspond to Figure 3.
- For example, there is no mention of AdaIN, which is included in the Texture Block in the figure.
- Also, the text says that the Pose Block contains GCN, but the Pose Block in the figure is not drawn in such a way as to show this.
There is no mention of how the three Losses are combined.
If the three are to be added together, it should be clearly stated as such.
no comment
All text and materials provided via this peer-review history page are made available under a Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.