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.

Authors are advised to revise the manuscript as per the reviewers' comments. 

Please submit your revised manuscript by Oct 18 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.

• 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,

Mudassir Khan, 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. Thank you for uploading your study's underlying data set. Unfortunately, the repository you have noted in your Data Availability statement does not qualify as an acceptable data repository according to PLOS's standards.

At this time, please upload the minimal data set necessary to replicate your study's findings to a stable, public repository (such as figshare or Dryad) and provide us with the relevant URLs, DOIs, or accession numbers that may be used to access these data. For a list of recommended repositories and additional information on PLOS standards for data deposition, please see https://journals.plos.org/plosone/s/recommended-repositories .

3. When completing the data availability statement of the submission form, you indicated that you will make your data available on acceptance. We strongly recommend all authors decide on a data sharing plan before acceptance, as the process can be lengthy and hold up publication timelines. Please note that, though access restrictions are acceptable now, your entire data will need to be made freely accessible if your manuscript is accepted for publication. This policy applies to all data except where public deposition would breach compliance with the protocol approved by your research ethics board. If you are unable to adhere to our open data policy, please kindly revise your statement to explain your reasoning and we will seek the editor's input on an exemption. Please be assured that, once you have provided your new statement, the assessment of your exemption will not hold up the peer review process.

4. If the reviewer comments include a recommendation to cite specific previously published works, please review and evaluate these publications to determine whether they are relevant and should be cited. There is no requirement to cite these works unless the editor has indicated otherwise. 

Additional Editor Comments:

Authors are advised to revise the manuscript as per the reviewers' comments.

[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?

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

Reviewer #1: Yes

Reviewer #2: Yes

**********

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

Reviewer #1: Yes

Reviewer #2: Yes

**********

Reviewer #1: The manuscript addresses a highly relevant challenge of traffic sign recognition for autonomous vehicles, proposing a Conditional Visual Transformer (CViT) with a fail-control mechanism. However, improvements in writing clarity, figure quality, formatting consistency, and critical discussion are required.

1- The sentence structure in abstract need to be improve i-e. “While issues related to object recognition, such as traffic sign recognition… “ is too lengthy and contains overly technical descriptions. Abstract should instead briefly state the problem, the novelty of the approach, key results, and implications.

a. Phrases like “gratuitous” are misused and should be replaced with clearer academic wording.

2- The introduction is informative but contains repetition (e.g., multiple mentions of misclassification risks and safety-critical concerns). Restructuring into a concise flow would improve readability.

a. Sentence like “…a misplaced label can be immensely disastrous will make this more problematic” is grammatically awkward and should be revised for clarity.

3- The listed contributions are significant; however, they should be rewritten more concisely and distinctly in a separate heading, avoiding overlap with methodology descriptions.

a. Also, explain the third contribution, “Proposed CViT incorporates a specialized attention module… “What is meant by specialized attention module here? And how is it specialized?

4- The methodology is presented in detail with equations and figures, which is commendable. However:

a. Several equations (e.g., Eq. (1), Eq. (2)–(4)) lack variable definitions. Every parameter (e.g., P, C, d) should be explicitly explained, as this can confuse readers unfamiliar with the notation.

b. In Eq. (5) bg is not described, what is bg and what is its use in Eq. 5?

c. In 3.1.1 “Then each patch x_i for(i=1,2,…,N) are flattened into a vector of size P^2∙C, where C is the number of channels, for example, for RGB images C=3.” is mentioned but again repeated at the end of 3.1.2. It needs explanation, why is it repeated again?

5. Several grammar issues (e.g., “Figure 6 demonstrate” should be “demonstrates”). The manuscript needs a thorough language polish.

6. Ensure that acronyms (e.g., GAP, FFN, MHA) are introduced at first use and used consistently throughout.

7. Equation numbering is inconsistent, like in Eq. 1 to Eq. 10, parentheses “()” are used, but in Eq. 11-12, square braces “[ ]” are used.

8. In Section 3.1.1, the phrase “as e.g., 224×224” is unpolished. Suggested edit: “e.g., resized to 224×224 pixels.”

9. Reference formatting is inconsistent: some include DOIs, others do not. Standardize per journal guidelines.

Reviewer #2: The manuscript addresses an important and timely challenge in traffic sign recognition for autonomous vehicles by introducing a Conditional Visual Transformer (CViT) with an integrated fail-control mechanism.

The proposed approach is technically relevant and well-motivated. However, the manuscript would benefit from improved writing clarity, figure presentation, and formatting consistency, as well as a more comprehensive critical discussion of the results and limitations to align with the standards of the journal before final acceptance.

1) (a) The related work section is extensive; however, the flow is occasionally interrupted by abrupt transitions. In addition, it lacks critical analysis and a discussion of the limitations of prior studies. It is also unclear why ViT is specifically preferred or emphasized.

(b) Furthermore, please add a new table in the related work section that summarizes the pros and cons of previous methods and clearly illustrates how your contribution relates to them and provides improvements.

2) In Figure 4, what is *N? is it mistaken? if not, please properly explain its working or importance in Figure 4.

3) In 3.2.4, “The Residual & Normalization after Attention, Feed-Forward Network (FFN), and Residual & Normalization after FFN are mathematically represented …” are these the modified equations or just the basic ones? If modified, then please explain them. And if these are just the same as the basic Vision transformer, then please include references.

4) The algorithm of the proposed Conditional Vision Transformer is good and well describes the whole methodology. The fail-control mechanism is a key strength, but its explanation is somewhat limited, and it is not discussed in the abstract.

(a) Table 7 includes valuable metrics, but abbreviations (e.g., “Critical Omissions,” “Error Reduction”) should be explained in captions.

(b) Figure 5 needs to be explained properly with details of metrics and parameters.

5) There are typos in the experimental section may be like “color jitter”, “WeightedRandomSampler”. It also misses the details about the training-testing ratio for the experiments.

(a) Fail Control Mechanism result values and parameters must be explained and discussed properly.

(b) In Result Section T1, T2, …. Are mentioned what are these? Mention and explain them properly. Also, in Table 1 and Table 3 why only top 5 classes or least 5 classes are mentioned. Description about other classes?

6) The acknowledgment, funding, and data availability sections are included, but their formatting should match journal requirements.

7) Some recent and relevant works could be included to broaden the comparison and highlight novelty.

8) On Page 2, Line 28: the phrase “will make this more problematic” is awkwardly worded. Consider rephrasing as “further exacerbates the problem.”

9) Some sentences are very long; breaking them into shorter sentences would enhance readability.

Please revise the manuscript according to the above points and resubmit. Addressing these issues will significantly improve the clarity, rigor, and presentation quality of the paper, enhancing its suitability for final publication.

**********

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:  Dr.Shaik Karimullah

Reviewer #2: No

**********

[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.

Dear Dr.,

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.

Please submit your revised manuscript by Nov 08 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.

• 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 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,

Mudassir Khan, Ph.D

Academic Editor

PLOS ONE

Journal Requirements:

If the reviewer comments include a recommendation to cite specific previously published works, please review and evaluate these publications to determine whether they are relevant and should be cited. There is no requirement to cite these works unless the editor has indicated otherwise. 

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 (if provided):

Reviwer1 and reviewer2 asked the authors to improve this manuscript significantly. I hope that the authors improve this manuscript following the comments.

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

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

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??>

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

Reviewer #1: Yes

Reviewer #2: Yes

**********

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

Reviewer #1: Yes

Reviewer #2: Yes

**********

Reviewer #1: The manuscript presents a well-structured study with a novel Conditional Vision Transformer (CViT) for traffic sign recognition. The work is technically sound, and experimental results are impressive. Only a few minor revisions are suggested for clarity, formatting, and presentation.

1. The abstract is clear but slightly long. Consider shortening by removing repeated phrases, especially where results are restated in the last two sentences.

2. The diagrams are informative, but the resolution and font size are low. Please improve image quality and enlarge labels so they are easily readable.

3. There are small grammatical issues and inconsistent tenses (e.g., “in life-or-death scenarios like autonomous driving, but in safety-critical scenarios…”). A careful language edit would improve clarity.

4. The comparison with recent models (Figure 6) is strong, but adding a short explanation of why CViT outperforms others (e.g., adaptive attention vs. fixed attention) would provide better insight.

5. Some entries are missing DOIs (e.g., refs. [31], [33], [35]). Please revise to follow PLOS ONE reference formatting guidelines.

6. Kindly read and cite these references:

1. Sun, G., Song, L., Yu, H., Chang, V., Du, X.,... Guizani, M. (2019). V2V Routing in a VANET Based on the Autoregressive Integrated Moving Average Model. IEEE Transactions on Vehicular Technology, 68(1), 908-922. doi: 10.1109/TVT.2018.2884525

2. Sun, G., Zhang, Y., Liao, D., Yu, H., Du, X.,... Guizani, M. (2018). Bus-Trajectory-Based Street-Centric Routing for Message Delivery in Urban Vehicular Ad Hoc Networks. IEEE Transactions on Vehicular Technology, 67(8), 7550-7563. doi: 10.1109/TVT.2018.2828651

3. Li, Z., Hu, J., Leng, B., Xiong, L., & Fu, Z. (2024). An Integrated of Decision Making and Motion Planning Framework for Enhanced Oscillation-Free Capability. IEEE Transactions on Intelligent Transportation Systems, 25(6), 5718-5732. doi: 10.1109/TITS.2023.3332655

4. Shen, Z., He, Y., Du, X., Yu, J., Wang, H.,... Wang, Y. (2024). YCANet: Target Detection for Complex Traffic Scenes Based on Camera-LiDAR Fusion. IEEE Sensors Journal, 24(6), 8379-8389. doi: 10.1109/JSEN.2024.3357826

5. Wang, J., Wang, H., Song, J., Chen, X., Guo, J., Li, K.,... Huang, B. (2025). Knowledge-guided self-learning control strategy for mixed vehicle platoons with delays. Nature Communications, 16(1), 7705. doi: 10.1038/s41467-025-62597-x

6. Lu, Y., Chen, S., Zhang, X., Pan, X., Gang, Y.,... Wang, C. (2025). A quantum-enhanced heuristic algorithm for optimizing aircraft landing problems in low-altitude intelligent transportation systems. Scientific Reports, 15(1), 21606. doi: 10.1038/s41598-025-05261-0

7. Song, D., Zhao, J., Zhu, B., Han, J., & Jia, S. (2024). Subjective Driving Risk Prediction Based on Spatiotemporal Distribution Features of Human Driver’s Cognitive Risk. IEEE Transactions on Intelligent Transportation Systems, 25(11), 16687-16703. doi: 10.1109/TITS.2024.3409874

8. Zuo, C., Zhang, X., Zhao, G., & Yan, L. (2025). PCR: A Parallel Convolution Residual Network for Traffic Flow Prediction. IEEE Transactions on Emerging Topics in Computational Intelligence, 9(4), 3072-3083. doi: 10.1109/TETCI.2025.3525656

9. Sun, T., Guo, R., Chen, G., Wang, H., Li, E.,... Zhang, W. (2025). RID-LIO: robust and accurate intensity-assisted LiDAR-based SLAM for degenerated environments. Measurement Science and Technology, 36(3), 36313. doi: 10.1088/1361-6501/adb769

10. Zhou, X., Zhao, Z., Shen, J., Liu, Z., Liu, Y.,... Xue, B. (2025). Sparse Aperture ISAR Autofocusing and Imaging Algorithm Based on Log-Sum Regularization. IEEE Transactions on Geoscience and Remote Sensing, 63. doi: 10.1109/TGRS.2025.3560140

11. Zhu, B., Tang, R., Zhao, J., Zhang, P., Li, W., Cao, X.,... Li, S. (2025). Critical scenarios adversarial generation method for intelligent vehicles testing based on hierarchical reinforcement architecture. Accident Analysis & Prevention, 215, 108013. doi: https://doi.org/10.1016/j.aap.2025.108013

Reviewer #2: Minor Revision:

The authors have carefully addressed the major revision comments, and the manuscript is now much improved. The paper is well explained, and the experimental results are convincing. However, a few minor corrections are still required to further enhance clarity and consistency in presentation:

1. Please ensure that “Conditional Visual Transformer (CViT)” is written in full only at its first occurrence, and that all subsequent mentions use the abbreviation “CViT” consistently throughout the manuscript (including figures, tables, and supplementary material).

2. Ensure that “Convolutional Neural Networks (CNNs)” and “Vision Transformers (ViTs)” are expanded only at their first occurrence, and that all subsequent mentions use the abbreviations “CNNs” and “ViTs” consistently throughout the manuscript.

3. In the Conclusion section, please add the proposed results explicitly, with separate values for accuracy, precision, recall, and F1-score for easier understanding by readers. Moreover, kindly include 2–3 sentences highlighting possible future research directions based on your work.

4. In the Experimental Setup and Results section, add the total number of parameters used in this study to provide a clearer picture of the model’s complexity and computational requirements.

5. Table 6 is presented in the manuscript, but its caption and detailed information are not adequately discussed in the text. Please revise the manuscript to reference and explain the content of Table 6 clearly within the main body of the paper.

6. Please carefully review the numbering of all equations and their citations throughout the manuscript. Some inconsistencies were noted in equation numbering and flow; these should be corrected for accuracy and clarity.

Once these minor issues are corrected, the manuscript will be suitable for publication.

**********

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: No

Reviewer #2: No

**********

[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

Attention to Detail: A Conditional Multi-Head Transformer for Traffic Sign Recognition

PONE-D-25-39099R2

Dear Author,

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,

Mudassir Khan, Ph.D

Academic Editor

PLOS ONE

Additional Editor Comments (optional):

Dear Editor,

Thank you for the opportunity to review the manuscript titled “Attention to Detail: A Conditional Multi-Head Transformer for Traffic Sign Recognition.

Overall, I found the manuscript to be well-written and informative.

Overall, I believe that this manuscript has the potential to make a valuable contribution to the field. However, I recommend that the authors address all the concerns raised during the review process. My decision is to accept in the present form.

Regards,

Dr Mudassir Khan

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

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??>

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

Reviewer #1: Yes

Reviewer #2: Yes

**********

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

Reviewer #1: Yes

Reviewer #2: Yes

**********

Reviewer #1: All the Comments were pefectly addressed in manuscript and the proposed methodology gives possible solutions in the research field.

Reviewer #2: The authors addressed every comment. They have thoroughly and satisfactorily addressed every point that I raised. The manuscript is acceptable in its current form.

**********

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: No

Reviewer #2: No

**********