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 modifications made by the authors, the paper is now suitable to be accepted.
[# PeerJ Staff Note - this decision was reviewed and approved by Rong Qu, a PeerJ Computer Science Section Editor covering this Section #]
Dear authors,
Revise the paper according to the following comments:
1. Include the explanation for Algorithm 2 as it is important for the readers.
2. Add limitations of your study in the conclusion.
3. Similarly add some numerical results in the Abstract and Conclusion parts.
Authors have done work on my comments and I'm satisfied with the response.
No comments
No comments
No comments
Based on reviewers commentary, the authors are requested to make "major revisions".
[# PeerJ Staff Note: The review process has identified that the English language must be improved. PeerJ can provide language editing services - please contact us at [email protected] for pricing (be sure to provide your manuscript number and title) #]
[# PeerJ Staff Note: Please ensure that all review comments are addressed in a rebuttal 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 rebuttal 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 rebuttal letter. Directions on how to prepare a rebuttal letter can be found at: https://peerj.com/benefits/academic-rebuttal-letters/ #]
1. The content is well-written in clear and unambiguous English
2. References are good, but can add few recent papers as well
3. Structure of the articles is good
4. Relevant results are provided
1. Novelty is good
2. As low-dimensional embedding is concentrated with visual semantics, it is technically innovative
3. Methods are described well and with sufficient detail
All underlying data have been provided; they are robust, statistically sound, & controlled
Conclusions are well stated
The article should include sufficient introduction and background to demonstrate how the work fits into the broader field of knowledge. Relevant prior literature should be appropriately referenced.
"Domain-aware multi-modality fusion network for generalized zero-shot learning" - https://www.sciencedirect.com/science/article/pii/S0925231222002168
"HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning" -https://proceedings.neurips.cc/paper/2021/file/8b0d268963dd0cfb808aac48a549829f-Paper.pdf
Figure 4 is difficult to view. Please enhance the image visibility.
The authors may evaluate the performance of the proposed method in Six traditional benchmark datasets and compare the results obtained in the paper "Domain-aware multi-modality fusion network for generalized zero-shot learning"
no comment
Study proposed a semantic-visual shared knowledge graph (SVKG) for zero-shot learning on the real-world dataset without needing pre-defined attributes.
Authors have done good work. I have just few suggestions.
Research questions and their conclusion should be mentioned.
Why this proposed approach is effective please give some statistical analysis.
Conclusion is too general please mention the finding of the study.
Future directions are missing according to study findings
no comment
no comment
no comment
See my comments below
See my comments below
See my comments below
The authors proposed semantic-visual shared knowledge graph approach for zero shot learning. Problem statement is defined properly. Objectives are clearly stated.
There are major points that need to be addressed as follows:
1. Citation of papers is not proper in the related work section.
2. More surveys on the latest papers are expected for each category in the related work section.
3. Some bad English constructions, grammar mistakes, and misuse of articles: a professional language editing service is strongly recommended to improve the paper’s presentation quality for meeting PeerJ’s high standards.
4. In the problem definition section, a detailed description of the mathematical model is expected.
5. Description of all variables is expected for Eq. No. 2.
6. Rephrasing of sentences is required for line nos. (201-208).
7. Figures 2,3,4,5,6 and 7 are not clear.
8. Examples of seen and unseen labels can be included in the paper.
9. Algorithm of semantic-visual shared knowledge graph can be included in the paper.
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.