PONE-D-25-28239Dual-Stage Framework with Soft-Label Distillation and Spatial Prompting for Image-Text RetrievalPLOS ONE

Dear Dr. Li,

Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process.

==============================

ACADEMIC EDITOR: 

Consider reporting variance measures (e.g.: standard deviation across multiple runs) to demonstrate statistical robustness.

Provide confidence intervals or significance testing (e.g.: t-tests) to further confirm the reliability of performance differences.

Clarify whether all results are based on single-run evaluations or averaged over several seeds.

You used Unicom and Sentence-BERT as teacher models for generating soft labels, but no justification is provided for choosing these specific models over others.

==============================

Please submit your revised manuscript by Aug 07 2025 11:59PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at plosone@plos.org . When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.

Please include the following items when submitting your revised manuscript:

• A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'.
• A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'.
• An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'.

If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter.

If applicable, we recommend that you deposit your laboratory protocols in protocols.io to enhance the reproducibility of your results. Protocols.io assigns your protocol its own identifier (DOI) so that it can be cited independently in the future. For instructions see: https://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols . Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols .

We look forward to receiving your revised manuscript.

Kind regards,

Alessandro Bruno, Ph.D.

Academic Editor

PLOS ONE

Journal Requirements:

When submitting your revision, we need you to address these additional requirements.

1. Please ensure that your manuscript meets PLOS ONE's style requirements, including those for file naming. The PLOS ONE style templates can be found at

https://journals.plos.org/plosone/s/file?id=wjVg/PLOSOne_formatting_sample_main_body.pdf and

https://journals.plos.org/plosone/s/file?id=ba62/PLOSOne_formatting_sample_title_authors_affiliations.pdf

2. Please note that PLOS ONE has specific guidelines on code sharing for submissions in which author-generated code underpins the findings in the manuscript. In these cases, we expect all author-generated code to be made available without restrictions upon publication of the work. Please review our guidelines at https://journals.plos.org/plosone/s/materials-and-software-sharing#loc-sharing-code and ensure that your code is shared in a way that follows best practice and facilitates reproducibility and reuse.

3. We note that the grant information you provided in the ‘Funding Information’ and ‘Financial Disclosure’ sections do not match.

When you resubmit, please ensure that you provide the correct grant numbers for the awards you received for your study in the ‘Funding Information’ section.

4. In the online submission form, you indicated that “Data cannot be shared publicly due to privacy concerns and confidentiality agreements associated with the study participants. However, data may be obtained from Mr. Li (contact via 447808600@qq.com) upon reasonable request and after a formal review process to ensure compliance with ethical standards and legal restrictions.”

All PLOS journals now require all data underlying the findings described in their manuscript to be freely available to other researchers, either 1. In a public repository, 2. Within the manuscript itself, or 3. Uploaded as supplementary information.

This policy applies to all data except where public deposition would breach compliance with the protocol approved by your research ethics board. If your data cannot be made publicly available for ethical or legal reasons (e.g., public availability would compromise patient privacy), please explain your reasons on resubmission and your exemption request will be escalated for approval.

5. Please review your reference list to ensure that it is complete and correct. If you have cited papers that have been retracted, please include the rationale for doing so in the manuscript text, or remove these references and replace them with relevant current references. Any changes to the reference list should be mentioned in the rebuttal letter that accompanies your revised manuscript. If you need to cite a retracted article, indicate the article’s retracted status in the References list and also include a citation and full reference for the retraction notice.

Additional Editor Comments:

Dear Authors,

I recommend dealing with reviewers’ comments and remarks.

Consider reporting variance measures (e.g.: standard deviation across multiple runs) to demonstrate statistical robustness.

Providing confidence intervals or significance testing (e.g.: t-tests) would further confirm the reliability of performance differences.

Clarify whether all results are based on single-run evaluations or averaged over several seeds.

You used Unicom and Sentence-BERT as teacher models for generating soft labels, but no justification is provided for choosing these specific models over others.

Kindest regards,

A.B.

[Note: HTML markup is below. Please do not edit.]

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

1. Is the manuscript technically sound, and do the data support the conclusions?

The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented.

Reviewer #1: Yes

Reviewer #2: Yes

**********

2. Has the statistical analysis been performed appropriately and rigorously?

Reviewer #1: Yes

Reviewer #2: Yes

**********

3. Have the authors made all data underlying the findings in their manuscript fully available?

The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.

Reviewer #1: No

Reviewer #2: Yes

**********

4. Is the manuscript presented in an intelligible fashion and written in standard English?

PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.

Reviewer #1: Yes

Reviewer #2: Yes

**********

5. Review Comments to the Author

Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters)

Reviewer #1: Minor Revisions:

1. Data and Code Availability Transparency

While the authors state that data cannot be shared publicly due to privacy concerns, this is inconsistent with the fact that publicly available datasets such as MSCOCO and Flickr30K were used. It is essential to clearly state where the data used in this research can be accessed and to provide direct links to these standard datasets. Additionally, to ensure transparency and reproducibility, the authors should upload the implementation code, training scripts, and any pre-trained models to a public repository (e.g., GitHub) and cite it within the manuscript. If any customized data, labels, or processing pipelines were used, these should also be explained and shared when ethically and legally permissible. This correction is critical for meeting open science and reproducibility standards, especially in a journal like PLOS ONE.

2. Language and Grammatical Clarity

The manuscript, although generally understandable, contains numerous grammatical errors and awkward phrasings that affect readability and professionalism. Examples include incorrect verb forms (e.g., “is show” instead of “is shown”) and convoluted sentence constructions. A thorough revision of the manuscript’s language is required. It is highly recommended that the authors seek professional editing assistance or have the manuscript reviewed by a native English speaker.

3. Methodological Clarity on Spatial Text Prompting (STP)

The section describing the Spatial Text Prompt (STP) mechanism lacks sufficient detail and clarity. While the general idea is described, the exact process of dividing images into blocks, assigning labels to blocks, and converting these labels into spatial prompts needs to be more thoroughly explained. The authors should include a step-by-step description or pseudocode of the STP generation process and clarify how spatial positioning is encoded and fed into the model. This will help readers fully understand how STP contributes to model performance and ensure the method is reproducible by others.

4. Justification for Choice of Teacher Models

The manuscript uses Unicom and Sentence-BERT as teacher models for generating soft labels, but no justification is provided for choosing these specific models over others. The authors should briefly explain the rationale behind selecting these models highlighting their strengths, prior performance, or relevance to the task of image-text representation learning. This contextualization will strengthen the validity of the experimental setup and support the credibility of the results derived from these models.

5. Absence of Statistical Significance Analysis

Although the manuscript reports performance improvements over baseline models using metrics like R@1 and mAP@R, it does not include any statistical significance testing. This is particularly important when numerical improvements are relatively small, even if they are consistent. The authors are encouraged to conduct and report statistical significance tests (e.g., t-tests or confidence intervals) across multiple runs to ensure the reported gains are robust and not due to random variation. Including this analysis would enhance the scientific rigor of the experimental results and further validate the effectiveness of the proposed method.

Reviewer #2: The experimental design is robust. The authors evaluate their method on three widely used benchmarks—MSCOCO, Flickr30K, and ECCV Caption—using appropriate metrics. The proposed model shows consistent improvements over strong baselines (e.g., CLIP, ALIGN), confirming the utility of the dual-stage framework. The ablation study further supports the contribution of each proposed component.

However, a few enhancements could strengthen the experimental claims:

Consider reporting variance measures (e.g.: standard deviation across multiple runs) to demonstrate statistical robustness.

Providing confidence intervals or significance testing (e.g.: t-tests) would further confirm the reliability of performance differences.

Clarify whether all results are based on single-run evaluations or averaged over several seeds.

**********

6. PLOS authors have the option to publish the peer review history of their article (what does this mean? ). If published, this will include your full peer review and any attached files.

If you choose “no”, your identity will remain anonymous but your review may still be made public.

Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy .

Reviewer #1: Yes:  Shake Ibna Abir

Reviewer #2: Yes:  Mounica Achanta

**********

[NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.]

While revising your submission, please upload your figure files to the Preflight Analysis and Conversion Engine (PACE) digital diagnostic tool, https://pacev2.apexcovantage.com/ . PACE helps ensure that figures meet PLOS requirements. To use PACE, you must first register as a user. Registration is free. Then, login and navigate to the UPLOAD tab, where you will find detailed instructions on how to use the tool. If you encounter any issues or have any questions when using PACE, please email PLOS at figures@plos.org . Please note that Supporting Information files do not need this step.

Dual-Stage Framework with Soft-Label Distillation and Spatial Prompting for Image-Text Retrieval

PONE-D-25-28239R1

Dear Dr. Li,

We’re pleased to inform you that your manuscript has been judged scientifically suitable for publication and will be formally accepted for publication once it meets all outstanding technical requirements.

Within one week, you’ll receive an e-mail detailing the required amendments. When these have been addressed, you’ll receive a formal acceptance letter and your manuscript will be scheduled for publication.

An invoice will be generated when your article is formally accepted. Please note, if your institution has a publishing partnership with PLOS and your article meets the relevant criteria, all or part of your publication costs will be covered. Please make sure your user information is up-to-date by logging into Editorial Manager at Editorial Manager®  and clicking the ‘Update My Information' link at the top of the page. For questions related to billing, please contact billing support .

If your institution or institutions have a press office, please notify them about your upcoming paper to help maximize its impact. If they’ll be preparing press materials, please inform our press team as soon as possible -- no later than 48 hours after receiving the formal acceptance. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information, please contact onepress@plos.org.

Kind regards,

Ming Liu

Academic Editor

PLOS ONE

Additional Editor Comments (optional):

The revisions have been addressed accordingly, recommend to accept the paper

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

1. If the authors have adequately addressed your comments raised in a previous round of review and you feel that this manuscript is now acceptable for publication, you may indicate that here to bypass the “Comments to the Author” section, enter your conflict of interest statement in the “Confidential to Editor” section, and submit your "Accept" recommendation.

Reviewer #1: All comments have been addressed

Reviewer #2: All comments have been addressed

**********

2. Is the manuscript technically sound, and do the data support the conclusions?

The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented.

Reviewer #1: Yes

Reviewer #2: Yes

**********

3. Has the statistical analysis been performed appropriately and rigorously?

Reviewer #1: Yes

Reviewer #2: Yes

**********

4. Have the authors made all data underlying the findings in their manuscript fully available?

The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.

Reviewer #1: Yes

Reviewer #2: Yes

**********

5. Is the manuscript presented in an intelligible fashion and written in standard English?

PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.

Reviewer #1: Yes

Reviewer #2: Yes

**********

6. Review Comments to the Author

Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters)

Reviewer #1: I appreciate the thoughtful and thorough revisions made to the manuscript. All my previous concerns have been carefully addressed:

Data and code availability have been clarified, with direct dataset links and an open GitHub repository now provided. The manuscript has been revised for grammar and clarity, which has improved readability.

The Spatial Text Prompt (STP) methodology is now described in detail, including block segmentation, labeling, and prompt generation, supported by clear figures. The choice of teacher models (Unicoder and Sentence-BERT) is now well justified. Statistical robustness has been added through multiple runs and paired t-tests, confirming the significance of reported improvements.

Overall, the manuscript has been substantially improved and is now suitable for publication. I recommend acceptance pending minor proofreading and typesetting.

Reviewer #2: No comments, paper is technically sound and is good to publish. The revised manuscript provides clearer explanations of STP generation, teacher model rationale, and experimental setup. Ablation studies effectively isolate the contributions of SLD and STP.

**********

7. PLOS authors have the option to publish the peer review history of their article (what does this mean? ). If published, this will include your full peer review and any attached files.

If you choose “no”, your identity will remain anonymous but your review may still be made public.

Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy .

Reviewer #1: Yes:  Shake Ibna Abir

Reviewer #2: Yes:  Mounica Achanta

**********