Dual-branch differential channel hypergraph convolutional network for human skeleton based action recognition

Dong Chen; Kaichen She; Peisong Wu; Mingdong Chen; Chuanqi Li

doi:10.1371/journal.pone.0332066

Peer Review History

Original SubmissionMay 2, 2025
11 Jun 2025 Decision Letter - Xiyu Liu, Editor 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. Please submit your revised manuscript by Jul 26 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, Xiyu Liu 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 your Data Availability Statement is currently as follows: All relevant data are within the manuscript and its Supporting Information files. Please confirm at this time whether or not your submission contains all raw data required to replicate the results of your study. Authors must share the “minimal data set” for their submission. PLOS defines the minimal data set to consist of the data required to replicate all study findings reported in the article, as well as related metadata and methods (https://journals.plos.org/plosone/s/data-availability#loc-minimal-data-set-definition). For example, authors should submit the following data: - The values behind the means, standard deviations and other measures reported; - The values used to build graphs; - The points extracted from images for analysis. Authors do not need to submit their entire data set if only a portion of the data was used in the reported study. If your submission does not contain these data, please either upload them as Supporting Information files or deposit them to a stable, public repository and provide us with the relevant URLs, DOIs, or accession numbers. For a list of recommended repositories, please see https://journals.plos.org/plosone/s/recommended-repositories. If there are ethical or legal restrictions on sharing a de-identified data set, please explain them in detail (e.g., data contain potentially sensitive information, data are owned by a third-party organization, etc.) and who has imposed them (e.g., an ethics committee). Please also provide contact information for a data access committee, ethics committee, or other institutional body to which data requests may be sent. If data are owned by a third party, please indicate how others may request data access. 4. Thank you for stating the following financial disclosure: Key Laboratory of AI and Information Processing, Education Department of Guangxi Zhuang Autonomous Region (Hechi University) (No. 2024GXZDSY015),Guangxi Science and Technology Program (2023AB29003 and 2023AB01005). Please state what role the funders took in the study. If the funders had no role, please state: "The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript." If this statement is not correct you must amend it as needed. Please include this amended Role of Funder statement in your cover letter; we will change the online submission form on your behalf. 5. Thank you for stating the following in the Acknowledgments Section of your manuscript: This work was supported by Key Laboratory of AI and Information Processing, Education Department of Guangxi Zhuang Autonomous Region (Hechi University) (No. 2024GXZDSY015), Guangxi Science and Technology Program (2023AB29003 and 2023AB01005). We note that you have provided funding information that is not currently declared in your Funding Statement. However, funding information should not appear in the Acknowledgments section or other areas of your manuscript. We will only publish funding information present in the Funding Statement section of the online submission form. Please remove any funding-related text from the manuscript and let us know how you would like to update your Funding Statement. Currently, your Funding Statement reads as follows: Key Laboratory of AI and Information Processing, Education Department of Guangxi Zhuang Autonomous Region (Hechi University) (No. 2024GXZDSY015),Guangxi Science and Technology Program (2023AB29003 and 2023AB01005). Please include your amended statements within your cover letter; we will change the online submission form on your behalf. 6. Please amend your list of authors on the manuscript to ensure that each author is linked to an affiliation. Authors’ affiliations should reflect the institution where the work was done (if authors moved subsequently, you can also list the new affiliation stating “current affiliation:….” as necessary). 7. Please update your submission to use the PLOS LaTeX template. The template and more information on our requirements for LaTeX submissions can be found at http://journals.plos.org/plosone/s/latex. [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: Partly Reviewer #2: Partly ******** 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: No Reviewer #2: Yes ****** Reviewer #1: 1. Reference Error and Grammar Issues In the Introduction section, the citation "Error! Reference source not found" suggests a broken reference link. Please correct this to ensure the citation is rendered correctly. Moreover, the manuscript contains multiple grammatical issues. 2.Inconsistency in Figure 2 The joints illustrated in Figure 2 for hypergraph construction do not correspond to those used in the dataset. This mismatch introduces ambiguity regarding the model's input structure. The authors should clarify how the visualized joints relate to the input used during training and inference. 3.Distinction Between ST-HCN and CD-HCN in Figure 3 The structural differences between ST-HCN and CD-HCN are insufficiently reflected in Figure 3. Since these two networks are central to the proposed method, the figure should be updated to highlight their architectural distinctions more clearly. 4.Temporal Modeling in Figure 5 In Figure 5, the temporal modeling components of ST-GCN and CD-GCN appear identical. The figure should be revised or better explained to clarify whether and how CD-GCN differs from ST-GCN in this aspect. Reviewer #2: This paper proposed a dual-branch differential channel hypergraph convolutional neural network to address the challenge of incomplete representation of non-natural dependencies in skeletal structure for skeleton-based human action recognition. The proposed model is evaluated on three public datasets to demonstrate its effectiveness. However, several areas in this paper need further improvement to enhance its quality: 1.The most typical improvement in metric is suggested to add to the abstract in order to validate the superiority of the proposed method in this paper. 2.The references should include more relevant and recent works. The introduction should contain more comprehensive review of recent studies. 3.Some cited reference numbers in the text are incorrectly shown. For example, on Page 2 of this paper, “Yan et al. Error! Reference source not found”, Page 3, “Chen et al. Error! Reference source not found”. And some references do not match the cited numbers in the text. For example, Page 5, “developed by Yan et al.[1]” . Actually, Ref. [1] is not written by Yan et al. 4.The title of each section should be numbered. 5.The format of the text should meticulously checked. For example, “where” followed by a equation does not need indentation, etc. In the text, some fonts about figures and tables like “ Fig.3(b)” should be corrected. 6.In the comparative experiment, it should add more comparison with the state-of-the-art methods. And the results of the existing models in Table 5 should be clarified whether they are cited from the references or are run in the settings of this paper. Furthermore, each existing model is better to be labeled the corresponding number of reference. 7.It is recommended to use more diagrams to demonstrate the effectiveness of the proposed method. For instance, the accuracy curve varying with some hyper-parameters, the accuracy histogram of each category, and some visualization plots for depicting the attention weights of each skeleton joints in each frame. 8.Some figures like the confusion matrices in Fig. 6 are blurry, which do not clearly show the ratio of correct or wrong classification, and the color variance for each square of predicted label-true label. In addition, the accuracy values like 90%, 59.17%, 80%, 8183% in the following analysis can not be found in all the figures and tables. 9.In conclusion, the limitation of this paper should be discussed and the future work should be planned. 10.The model name is sometimes called “BDC-HCN”, sometime called “DBC-HCN”. Please correct this discrepancy. 11.Some full names of the key terms are printed in lowercase, some others are capitalized. 12.In Fig. 2(b), it seems that there are some mistakes in the feature matrix. For example, it should not be 1 but 0 for n1-e3. 13.All the acronyms should be accompanied with the full names in the first appearance of the corresponding terms, then the acronyms can be individually used. ****** 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 . Please note that Supporting Information files do not need this step. Attachments Attachment Submitted filename: PLONE review PONE-D-25-23177.docx https://doi.org/10.1371/journal.pone.0332066.r001
Revision 1
20 Jun 2025 Author Response Response to Reviewers Response to Reviewer #1 1.Reference Error and Grammar Issues In the Introduction section, the citation "Error! Reference source not found" suggests a broken reference link. Please correct this to ensure the citation is rendered correctly. Moreover, the manuscript contains multiple grammatical issues. Response: Thank you for pointing out the references and grammar issues. We have thoroughly checked all the references in the manuscript and corrected any damaged reference links, especially the statement 'Error! Reference source not found' in the introduction. Specifically, the citation by Yan et al. [1] has been confirmed to correspond to the correct reference "Spatiotemporal Graph Convolutional Networks for Skeleton based Action Recognition". In addition, we made a revision to the grammar of the entire manuscript, resolving grammar errors and improving writing fluency. 2.Inconsistency in Figure 2 The joints illustrated in Figure 2 for hypergraph construction do not correspond to those used in the dataset. This mismatch introduces ambiguity regarding the model's input structure. The authors should clarify how the visualized joints relate to the input used during training and inference. 3.Distinction Between ST-HCN and CD-HCN in Figure 3 The structural differences between ST-HCN and CD-HCN are insufficiently reflected in Figure. Response: We appreciate your feedback on the figure. Figure 2 was intended to illustrate the general concept of hypergraph construction using a simplified joint representation for clarity. To avoid ambiguity, we have updated the graphic titles to ensure that the joints constructed by the hypergraph shown in Figure 2 correspond to the joints used in the dataset. 3.Since these two networks are central to the proposed method, the figure should be updated to highlight their architectural distinctions more clearly. Response: We agree that the architectural differences between the two streams were not sufficiently highlighted. CD-HCN and ST-HCN have similar overall structures, both focusing on spatiotemporal hypergraph interaction, but CD-HCN also performs channel differencing on input data. Therefore, the revised Figure 3 has annotated the key modules: we specifically marked the Channel Differential Mechanism (CDM) in CD-HCN. 4.Temporal Modeling in Figure 5 In Figure 5, the temporal modeling components of ST-GCN and CD-GCN appear identical. The figure should be revised or better explained to clarify whether and how CD-GCN differs from ST-GCN in this aspect. Response: The original image does not clearly show the time processing differences between ST-GCN and CD-GCN. In the updated Figure 5, we demonstrate the spatial and temporal modeling of ST-HCN and CD-HCN, where their temporal modeling structures are very similar. Response to Reviewer # 2 1.The most typical improvement in metric is suggested to add to the abstract in order to validate the superiority of the proposed method in this paper. Response: Thank you for your suggestion. We have updated the abstract to clearly demonstrate the performance of our model on the NTU RGB+D 60 dataset: "The accuracy of the cross X-View and X-Sub benchmarks on the NTU RGB+D 60 dataset reached 96.9% and 92.7%, respectively," which validates the superiority of our method. 2.The references should include more relevant and recent works. The introduction should contain more comprehensive review of recent studies. Response: We acknowledge the need for a more comprehensive literature review. The relevant work section has been expanded to include recent research (2023-2025), such as "SA TDGFormer [35]" and "SpSt GCN [34]". In addition, in the introduction section, we also included a discussion on recent hypergraph based methods to demonstrate the novelty of our approach. 3.Some cited reference numbers in the text are incorrectly shown. For example, on Page 2 of this paper, “Yan et al. Error! Reference source not found”, Page 3, “Chen et al. Error! Reference source not found”. And some references do not match the cited numbers in the text. For example, Page 5, “developed by Yan et al.[1]” . Actually, Ref. [1] is not written by Yan et al. Response: All citations have been systematically checked. For example, the error in the original text is "Yan et al., wrong! The reference source not found "has been corrected to" Yan et al. [1] ", and the reference list now accurately matches the citation in the article. We apologize for any confusion caused by previous errors and ensure consistency between citations and references. 4.The title of each section should be numbered. Response: We have verified the chapter numbering and ensured that all major chapters (e.g. "1. Abstract," 2. Introduction) and subsections (e.g. "3.1. Action Recognition Methods Based on RNN and CNN") have been correctly numbered. The format has been standardized to follow academic publishing conventions. 5.The format of the text should meticulously checked. For example, “where” followed by a equation does not need indentation, etc. In the text, some fonts about figures and tables like “ Fig.3(b)” should be corrected. Response: We have numbered the titles of all sections as per your suggestion and have carefully checked the format of the manuscript. We corrected instances where "where" was incorrectly followed by an equation without indentation, as well as other minor formatting inconsistencies like figure references (e.g., “Fig. 3(b)”). 6.In the comparative experiment, it should add more comparison with the state-of-the-art methods. And the results of the existing models in Table 5 should be clarified whether they are cited from the references or are run in the settings of this paper. Furthermore, each existing model is better to be labeled the corresponding number of reference. Response: We have added more advanced methods in the comparative analysis, including "SA TDGFormer [35]" and "SpSt GCN [34]" in Table 3-5. For Table 5, each result of the existing model is now labeled with a corresponding reference number (e.g. "ST-GCN [1]"), and the footnote clarifies that all baseline results are referenced from the original publication, while our results were obtained under the same evaluation scheme. 7.It is recommended to use more diagrams to demonstrate the effectiveness of the proposed method. For instance, the accuracy curve varying with some hyper-parameters, the accuracy histogram of each category, and some visualization plots for depicting the attention weights of each skeleton joints in each frame. Response: The new visualization includes: the histogram in Figure 7 displays the accuracy distribution of 60 action categories for x-sub and x-view in NTU RGB+D 60. 8.Some figures like the confusion matrices in Fig. 6 are blurry, which do not clearly show the ratio of correct or wrong classification, and the color variance for each square of predicted label-true label. In addition, the accuracy values like 90%, 59.17%, 80%, 81,83% in the following analysis can not be found in all the figures and tables. Response: We agree with your suggestion. Figure 6 has been replaced with a confusion matrix of NTU RGB+D 60 for better high-resolution redrawing. The color gradient now clearly indicates the proportion of correct classification (darker colors result in higher accuracy). In addition, accuracy values such as 90%, 59.17%, 80%, 81%, and 83% in the analysis can be obtained based on the newly generated Figure 7 analysis. 9.In conclusion, the limitation of this paper should be discussed and the future work should be planned. Response: We agree with your suggestion. The conclusion section has been expanded to discuss limitations: 1. Dual branch architecture and hypergraph computing increase computational complexity, limiting real-time edge deployment. Constructing dynamic hypergraphs using the K-NN/K-means method may limit their ability to generalize unconventional action patterns. In addition, future work was outlined, including lightweight hypergraph design, attention driven hyperedge weighting, and practical applications in medical rehabilitation. 10.The model name is sometimes called “BDC-HCN”, sometime called “DBC-HCN”. Please correct this discrepancy. Response: All instances of 'BDC-HCN' in the manuscript have been modified to 'DBC-HCN' to maintain consistency. The acronym was correctly defined as "Dual-Branch Differential Channel Hypergraph Convolutional Network" when it first appeared. 11.Some full names of the key terms are printed in lowercase, some others are capitalized. Response: We have standardized the key terms throughout the manuscript and printed them in capital letters. 12.In Fig. 2(b), it seems that there are some mistakes in the feature matrix. For example, it should not be 1 but 0 for n1-e3. Response: We appreciate your feedback on the graph. Due to our negligence, the joints constructed in the hypergraph shown in Figure 2 do not correspond to the joints used in the dataset. Therefore, we performed overall correction on Figure 2 to correspond to the joints in the dataset and ensured the correctness of the feature matrix in Figure 2 (b). 13.All the acronyms should be accompanied with the full names in the first appearance of the corresponding terms, then the acronyms can be individually used. Response: A thorough inspection was conducted to ensure that each abbreviation (such as ST-HCN, CDM, DTC) is accompanied by its full name when first mentioned. For example, the term 'Spatiotemporal Dynamic Hypergraph Convolutional Network (ST-HCN)' has now been correctly defined in Section 4.3. And abbreviations will also be used in the future. We sincerely appreciate the reviewers’ meticulous feedback, which has significantly improved the quality of our manuscript. All suggested modifications have been implemented, and we believe the revised version addresses the concerns raised. Please let us know if further adjustments are needed. Attachments Attachment Submitted filename: rebuttal letter.docx https://doi.org/10.1371/journal.pone.0332066.r002
19 Aug 2025 Decision Letter - Xiyu Liu, Editor 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. Please submit your revised manuscript by Oct 03 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, Xiyu Liu 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. [Note: HTML markup is below. Please do not edit.] Reviewers' comments: Reviewer's Responses to Questions Comments to the Author Reviewer #3: (No Response) Reviewer #4: All comments have been addressed Reviewer #5: All comments have been addressed ******** 2. Is the manuscript technically sound, and do the data support the conclusions??> Reviewer #3: Yes Reviewer #4: Yes Reviewer #5: Yes ****** 3. Has the statistical analysis been performed appropriately and rigorously? -->?> Reviewer #3: Yes Reviewer #4: Yes Reviewer #5: Yes ****** 4. Have the authors made all data underlying the findings in their manuscript fully available??> The PLOS Data policy Reviewer #3: Yes Reviewer #4: Yes Reviewer #5: Yes ****** 5. Is the manuscript presented in an intelligible fashion and written in standard English??> Reviewer #3: Yes Reviewer #4: Yes Reviewer #5: Yes ****** Reviewer #3: This paper proposes a novel dual-branch hypergraph convolutional network (DBC-HCN) that integrates spatial-temporal and channel-differential mechanisms to enhance skeleton-based human action recognition. Although the topic is novel and thought-provoking, I still have several concerns. 1. The manuscript should be carefully reviewed for formatting, layout, and language issues. Professional academic editing is strongly recommended. For example, in Section 5.4, “NTU RGB+D 60 dataset” was incorrectly written as “NTU RGB+D 60dataset”; “NTU RGB+D 60” appeared as “NTU RGB D 60”; and “Fig 6 shows” was incorrectly written as “Fig 6shows”. 2. The model code should be publicly released on an open-source platform such as GitHub and should not be removed, in order to ensure the reproducibility and verifiability of the research. 3. The manuscript should provide a more detailed explanation of the parameter settings, including all model hyperparameters, training configurations, and dataset partitioning strategies, to improve the transparency of the methodology. 4. The following articles appear to be closely related to your work and the authors should refer to DOI: 10.1016/j.inffus.2025.103016 and DOI: 10.1109/TBDATA.2024.3362188 Reviewer #4: I can see that the authors addressed all the required comments by reviewers. This research sounds interesting, and the authors present a promising result. Future work is required to improve their results. Reviewer #5: I have carefully read the paper, as well as the previous reviewers' comments. From my understanding, the authors have addressed all the previously expressed concerns/inconsistencies and the paper is ready 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 #3: No Reviewer #4: Yes: Mona Ali Reviewer #5: 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 https://doi.org/10.1371/journal.pone.0332066.r003
Revision 2
20 Aug 2025 Author Response Reviewer #3: 1. The manuscript should be carefully reviewed for formatting, layout, and language issues. Professional academic editing is strongly recommended. For example, in Section 5.4, “NTU RGB+D 60 dataset” was incorrectly written as “NTU RGB+D 60dataset”; “NTU RGB+D 60” appeared as “NTU RGB D 60”; and “Fig 6 shows” was incorrectly written as “Fig 6shows”. Thank you for your suggestions. We have made modifications to the format, layout, and language issues of the manuscript. 2. The model code should be publicly released on an open-source platform such as GitHub and should not be removed, in order to ensure the reproducibility and verifiability of the research. Our code has been published at https://github.com/hhh1234hhh/DBC-HCN. 3. The manuscript should provide a more detailed explanation of the parameter settings, including all model hyperparameters, training configurations, and dataset partitioning strategies, to improve the transparency of the methodology. We have made additional additions to the parameter settings for the experiment in the manuscript. 4. The following articles appear to be closely related to your work and the authors should refer to DOI: 10.1016/j.inffus.2025.103016 and DOI: 10.1109/TBDATA.2024.3362188 Thank you for your suggestions. We have referenced these documents in our manuscript. Reviewer #4: I can see that the authors addressed all the required comments by reviewers.This research sounds interesting, and the authors present a promising result.Future work is required to improve their results. Thank you for your recognition and suppor. Reviewer #5: I have carefully read the paper, as well as the previous reviewers' comments. From my understanding, the authors have addressed all the previously expressed concerns/inconsistencies and the paper is ready for publication. Thank you for your recognition and support. Attachments Attachment Submitted filename: rebuttal_letter_auresp_2.docx https://doi.org/10.1371/journal.pone.0332066.r004
26 Aug 2025 Decision Letter - Xiyu Liu, Editor Dual-Branch Differential Channel Hypergraph Convolutional Network for Human Skeleton based Action Recognition PONE-D-25-23177R2 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, Xiyu Liu Academic Editor PLOS ONE Additional Editor Comments (optional): Reviewers' comments: Reviewer's Responses to Questions Comments to the Author Reviewer #3: All comments have been addressed Reviewer #5: All comments have been addressed ******** 2. Is the manuscript technically sound, and do the data support the conclusions??> Reviewer #3: Yes Reviewer #5: Yes ****** 3. Has the statistical analysis been performed appropriately and rigorously? -->?> Reviewer #3: Yes Reviewer #5: Yes ****** 4. Have the authors made all data underlying the findings in their manuscript fully available??> The PLOS Data policy Reviewer #3: Yes Reviewer #5: Yes ****** 5. Is the manuscript presented in an intelligible fashion and written in standard English??> Reviewer #3: Yes Reviewer #5: Yes ****** Reviewer #3: The authors propose the Dual-Branch Differential Channel Hypergraph Convolutional Network (DBC-HCN), which leverages hypergraphs’ ability to represent a priori non-natural dependencies in skeletal structures. Reviewer #5: As stated on the previous round of reviews, I consider the article ready for publication, without any additional changes. ****** 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 #3: Yes: Hao Wu Reviewer #5: No ******** https://doi.org/10.1371/journal.pone.0332066.r005
Formally Accepted
Acceptance Letter - Xiyu Liu, Editor PONE-D-25-23177R2 PLOS ONE Dear Dr. Li, I'm pleased to inform you that your manuscript has been deemed suitable for publication in PLOS ONE. Congratulations! Your manuscript is now being handed over to our production team. At this stage, our production department will prepare your paper for publication. This includes ensuring the following: * All references, tables, and figures are properly cited * All relevant supporting information is included in the manuscript submission, * There are no issues that prevent the paper from being properly typeset You will receive further instructions from the production team, including instructions on how to review your proof when it is ready. Please keep in mind that we are working through a large volume of accepted articles, so please give us a few days to review your paper and let you know the next and final steps. Lastly, if your institution or institutions have a press office, please let them know about your upcoming paper now to help maximize its impact. If they'll be preparing press materials, please inform our press team within the next 48 hours. 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. You will receive an invoice from PLOS for your publication fee after your manuscript has reached the completed accept phase. If you receive an email requesting payment before acceptance or for any other service, this may be a phishing scheme. Learn how to identify phishing emails and protect your accounts at https://explore.plos.org/phishing. If we can help with anything else, please email us at customercare@plos.org. Thank you for submitting your work to PLOS ONE and supporting open access. Kind regards, PLOS ONE Editorial Office Staff on behalf of Professor Xiyu Liu Academic Editor PLOS ONE https://doi.org/10.1371/journal.pone.0332066.r006

Open letter on the publication of peer review reports

PLOS recognizes the benefits of transparency in the peer review process. Therefore, we enable the publication of all of the content of peer review and author responses alongside final, published articles. Reviewers remain anonymous, unless they choose to reveal their names.

We encourage other journals to join us in this initiative. We hope that our action inspires the community, including researchers, research funders, and research institutions, to recognize the benefits of published peer review reports for all parts of the research system.

Learn more at ASAPbio .