Skip to yearly menu bar Skip to main content


ICCV 2025 Author Guidelines

Thank you for submitting your paper(s) to ICCV 2025. This document outlines the expectations for all authors and submissions.

Contents

What’s New for Submissions & Authors at ICCV 2025 ?

  1. Every author is required to serve as a reviewer (unless they hold another role in ICCV 2025).
  2. The maximum number of submissions per author is limited to 25 papers.
  3. The deadline for both the paper and supplementary materials is now the same.

Please visit this page for a detailed explanation of these changes. 

Submission Policies

All authors should carefully review the following policies that govern the submission and review process, as failure to comply with these policies may result in the rejection of your submission as well as possible additional sanctions in the case of dual submissions and plagiarism. In addition, authors are urged to consult the ethics guidelines and the FAQs.

Paper formatting: Papers are limited to eight pages, including figures and tables, in the ICCV style. Additional pages containing only cited references are allowed. Please download the ICCV 2025 Author Kit for detailed formatting instructions.

Papers that are not properly anonymized, or do not use the template, or have more than eight pages (excluding references) will be rejected without review.

Submission and review process: ICCV 2025 will be using OpenReview to manage submissions. Consistent with the review process for previous ICCV conferences, submissions under review will be visible only to their assigned members of the program committee (area chairs and reviewers). The reviews and author responses will never be made public, and we will not be soliciting comments from the general public during the reviewing process. 

Anyone who plans to submit a paper as an author or a co-author will need to create (or update) their OpenReview profile by the full paper submission deadline. By submitting a paper to ICCV, the authors agree to the review process and understand that papers are processed by the OpenReview system to match each manuscript to the best possible area chairs and reviewers.

OpenReview author instructions can be found here.

Exceptions and Accommodations: Due to the large number of submissions, deadlines and policies will be strictly enforced. There will be no exceptions or accommodations for: 

  • late submissions;
  • misconfigured author or co-author accounts on OpenReview; and/or
  • changes to the author lists after the paper submission deadline.

You should not expect a response or detailed explanation of any policies from the PCs for any of these issues no matter the reason. If there is a large-scale technical catastrophe affecting the entire community, the PCs will be aware of the issue and communicate the resolution to the entire community.

Confidentiality: All members of the program committee (program chairs, area chairs, and reviewers) are instructed to keep all information about their assigned submissions confidential and not to share or distribute materials for any reason except to facilitate the reviewing of the submitted work. Misuse of confidential information is a severe professional failure and appropriate measures will be taken when brought to the attention of the ICCV organizers. It should be noted, however, that all program committee members are volunteers, and the ICCV organization is not and cannot be held responsible for the consequences if confidentiality is broken due to a violation during the review process.

Conflict responsibilities: Anyone who plans to submit a paper as an author or a co-author will need to create or update their OpenReview profile. You will be asked to declare two types of conflicts – domain and personal conflicts – by filling out appropriate sections of your OpenReview profile, as described on the OpenReview author instructions page. If any author of a submission is found to have incomplete or inaccurate conflict information, the submission may be summarily rejected. To avoid undeclared conflicts, authors cannot be added or deleted after the paper registration deadline (March 3), but only reordered. The author list is considered final after the paper submission deadline (March 7) and no changes are allowed thereafter,including for accepted papers. Moreover, all authors of a paper must have a valid OpenReview profile by the submission deadline (March 7) to avoid desk rejection.

Double blind review: ICCV reviewing is double blind, in that authors do not know the names of the area chairs or reviewers for their papers, and the area chairs/reviewers cannot, beyond a reasonable doubt, infer the names of the authors from the submission and the additional material. Do not provide information that may identify the authors in the acknowledgments (e.g., co-workers and grant IDs) and in the supplementary material (e.g., titles in the movies, or attached papers). Also do not provide links to websites that identify the authors. Violation of any of these guidelines may lead to rejection without review. If you need to cite any of your own papers that are being submitted concurrently to another venue, you should (1) include anonymized versions of those papers in the supplementary material; (2) cite these anonymized papers; and (3) argue in the body of your paper why your ICCV submission is non-trivially different from these concurrent submissions.

Plagiarism: Plagiarism consists of appropriating the words or results of another, without credit. ICCV 2025's policy on plagiarism is to refer suspected cases to the IEEE Intellectual Property office, which has an established mechanism for dealing with plagiarism and wide powers of excluding offending authors from future conferences and from IEEE journals. You can find information on this office, their procedures, and their definitions of five levels of plagiarism on this webpage. We will be actively checking for plagiarism. Furthermore, the paper matching system is quite accurate. As a result, it regularly happens that a paper containing plagiarized material goes to a reviewer from whom material was plagiarized; experience shows that such reviewers pursue plagiarism cases enthusiastically.

Dual submissions: The goals of ICCV are to publish exciting new work for the first time and to avoid duplicating the effort of reviewers. By registering or submitting a manuscript to ICCV, the authors acknowledge that it has not been previously published or accepted for publication in substantially similar form in any peer-reviewed venue including journal, conference or workshop, or archival forum. Furthermore, no publication substantially similar in content (defined as having 20 percent or more overlap) has been or will be registered or submitted to this or another conference, workshop, or journal during the review period. Violation of any of these conditions will lead to rejection, and will be reported to the other venue to which the submission was sent.

A publication, for the purposes of this policy, is defined to be a written work longer than four pages (excluding references) that was submitted for review by peers for either acceptance or rejection, and, after review, was accepted. In particular, this definition of publication does not depend upon whether such an accepted written work appears in a formal proceedings or whether the organizers declare that such work “counts as a publication.” Under the above definition, arXiv preprints and university technical reports are not considered as publications. However, peer-reviewed workshop papers are considered as publications if their length is more than four pages (excluding references), even if they do not appear in a proceedings. 

Note that a technical report (departmental, arXiv, etc.) version of the submission that is put up without any form of direct peer-review is NOT considered prior art and does NOT NEED to be cited in the submission; authors may cite such material, but cannot be penalized for not citing it.

Supplementary material submission: The authors may optionally submit additional material that could not be included due to constraints of format or space. The authors should refer to the contents of the supplementary material appropriately in the paper. Reviewers will be encouraged to look at it, but are not obligated to do so.

Supplementary material may include videos, proofs, additional figures or tables, more detailed analysis of experiments presented in the paper, or a concurrent submission to another conference. It may not include results on additional datasets, results obtained with an improved version of the method (e.g., following additional parameter tuning or training), or an updated or corrected version of the submission PDF. Papers with supplementary materials violating the guidelines may be summarily rejected.

We encourage (but do not require) authors to upload their code as part of their supplementary material in order to help reviewers assess the quality of the work.

Personal and human subjects data: If a paper makes use of personal data and/or data from human subjects, including personally identifiable information or offensive content, we expect that the collection and use of such data has been conducted carefully in accordance with the ethics guidelines (see below). In many countries and institutions, the collection and use of personally identifiable data or data from human subjects is subject to approval from an Institutional Review Board (IRB, or equivalent). If the use of such data was approved by an IRB, stating this is sufficient. If the use of such data has not (yet) been approved by an IRB, authors should provide information on any pending approval process, how the data was obtained, as well as discuss if and how consent was obtained (or why it, perhaps, could not be obtained). This discussion can be included either in the main paper or in the supplementary material. If the authors use an existing, published dataset, we encourage (but do not require) them to check how data was collected and whether consent was obtained. 

Attendance responsibilities: The authors agree that if the paper is accepted, at least one of the authors will register for the conference and present the paper there.

Publication: All accepted papers will be made publicly available by the Computer Vision Foundation (CVF) two weeks before the conference. Authors wishing to submit a patent should understand that the paper's official public disclosure is two weeks before the conference or whenever the authors make it publicly available, whichever is first. The conference considers papers confidential until published two weeks before the conference, but notes that multiple organizations will have access during the review and production processes, so those seeking patents should discuss filing dates with their IP council. The conference assumes no liability for early disclosures. More information about CVF is available at https://www.thecvf.com/.

Restrictions on publicity and media:  Papers submitted to ICCV must not be discussed with the media until they have been officially accepted for publication. Violations of the embargo will result in the paper being removed from the conference and proceedings.

Authors acting as reviewers:  We expect all authors to be willing to serve as reviewers if asked to do so. To help us identify qualified reviewers, and to match submissions to reviewers, all authors are required to have an up-to-date OpenReview profile (see OpenReview author instructions).

Rebuttal Policies 

After receiving the reviews, the authors may optionally submit a rebuttal to address the reviewers' comments. The rebuttal is limited to a one page PDF file using the rebuttal template included in the ICCV 2025 Author Kit. Responses longer than one page will simply not be reviewed. This includes responses where the margins and formatting are deemed to have been significantly altered from those specified by the style guide.

The rebuttal must maintain anonymity. It cannot include links to external material such as code, videos, etc.

Reviewers should refrain from requesting significant additional experiments for the rebuttal, or penalize for lack of additional experiments. Authors should refrain from including new contributions or experimental results in the rebuttal, especially when not specifically requested to do so by the reviewers. Reviewers are instructed to disregard any such contributions.

Authors also have the possibility to submit a separate confidential comment to the area chair. Please do so only in exceptional circumstances.

Ethics Guidelines for Authors

These guidelines have been adapted from the CVPR 2025 Ethics Guidelines.

As Computer Vision research and applications have increasing real-world impact, the likelihood of meaningful social benefit increases, but so does the attendant risk of harm. The research community should consider not only the potential benefits but also the potential negative societal impacts of CV research, and adopt measures that enable positive trajectories to unfold while mitigating risk of harm.

During the ICCV review process, reviewers will have the ability to flag papers with significant ethical concerns. These will be referred to an ethics committee, which will assess the situation and advise the program chairs. The program chairs reserve the right to reject papers with grave ethical issues, but expect this to occur only in exceptional circumstances.

Potential Negative Societal Impacts

ICCV authors are invited to think about the potential negative societal impacts of their proposed research artifact or application. The ethics consequences of a paper can stem from either the methodology or the application. On the methodology side, for example, a new adversarial attack might give unbalanced power to malicious entities; in this case, defences and other mitigation strategies would be expected, as is standard in computer security. On the application side, in some cases, the choice of application is incidental to the core contribution of the paper, and a potentially harmful application should be swapped out (as an extreme example, replacing ethnicity classification with bird classification), but the potential misuses should be still noted. In other cases, the core contribution might be inseparable from a questionable application (e.g., reconstructing a face given speech). In such cases, one should critically examine whether the scientific (and ethical) merits really outweigh the potential ethical harms.

A non-exhaustive list of potential negative societal impacts is included below. Consider whether the proposed methods and applications can:

  1. Directly facilitate injury to living beings. For example: could it be integrated into weapons or weapons systems?
  2. Raise safety, privacy, or security concerns. For example: is there a risk that applications could cause serious accidents or open security vulnerabilities when deployed in real-world environments? Would they make public people’s identity or other personal information without their consent?
  3. Raise human rights concerns. For example: could the technology be used to discriminate, exclude, or otherwise negatively impact people, including impacts on the provision of vital services, such as healthcare and education, or limit access to opportunities like employment? Please consult the  Toronto Declaration for further details.
  4. Have a detrimental effect on people’s livelihood or economic security. For example: Have a detrimental effect on people’s autonomy, dignity, or privacy at work? Could it be used to increase worker surveillance, or impose conditions that present a risk to the health and safety of employees?
  5. Develop or extend harmful forms of surveillance. For example: could it be used to collect or analyze bulk surveillance data to predict immigration status or other protected categories, or be used in any kind of criminal profiling?
  6. Severely damage the environment. For example: would the application incentivize significant environmental harms such as deforestation, hunting of endangered species, or pollution?
  7. Deceive people in ways that cause harm. For example: could the approach be used to facilitate deceptive interactions that would cause harms such as theft, fraud, or harassment? Could it be used to impersonate public figures to influence political processes, or as a tool of hate speech or abuse?

Whenever a work is associated with significant potential negative impacts (or can be perceived that way by reviewers), submissions should include a discussion of these impacts. Such discussion should consider different stakeholders that could be impacted, paying special attention to vulnerable or marginalized communities. It should also include possible mitigation strategies (e.g., gated release of models, providing defences in addition to attacks, mechanisms for monitoring misuse, mechanisms to monitor how a system learns from feedback over time, improving the efficiency and accessibility of CV models, etc.).

Grappling with ethics is a difficult problem for our field, and thinking about ethics is still relatively new to many authors. A common difficulty with assessing ethical impact is its indirectness: most papers focus on general-purpose methodologies (e.g., object recognition algorithms), whereas ethical concerns are more apparent when considering deployed applications (e.g., surveillance systems). Also, real-world impact (both positive and negative) often emerges from the cumulative progress of many papers, so it is difficult to attribute the impact to an individual paper. In certain cases, the applications can have both significant risks and benefits, or it may not be possible to draw a bright line between ethical and unethical. Authors should not hesitate to acknowledge such ambiguities and err on the side of transparency.

General Ethical Conduct

We assume that all submissions adhere to ethical standards for responsible research practice and due diligence in the conduct.

If the research uses human-derived data, consider whether that data might:

  1. Contain any personally identifiable information or sensitive personally identifiable information. For instance, does the dataset use features or label information about individual names? Did people provide their consent on the collection of such data? Could the use of the data be degrading or embarrassing for some people?
  2. Contain information that could be deduced about individuals that they have not consented to share. For instance, a dataset with medical image annotations by experts could inadvertently disclose user information such as their name, depending on the features provided.
  3. Encode, contain, or potentially exacerbate bias against people of a certain gender, race, sexuality, or who have other protected characteristics. For instance, does the dataset represent the diversity of the community where the approach is intended to be deployed?
  4. Contain human subject experimentation and whether it has been reviewed and approved by a relevant oversight board. For instance, studies predicting characteristics (e.g., mental health status) from human data (e.g., performance of everyday activities) are expected to have their studies reviewed by an ethical board (IRB or equivalent).
  5. Have been discredited by the creators. For instance, the DukeMTMC-ReID dataset has been taken down and it should not be used in ICCV submissions.

In general, there are other issues related to data that are worthy of consideration and review. These include:

  1. Consent to use or share the data. Explain whether you have asked the data owner’s permission to use or share data and what the outcome was. Even if you did not receive consent, explain why this might be appropriate from an ethical standpoint. For instance, if the data was collected from a public forum, were its users asked consent to use the data they produced, and if not, why?
  2. Domain specific considerations when working with high-risk groups. For example, if the research involves work with minors or vulnerable adults, have the relevant safeguards been put in place?
  3. Filtering of offensive content. For instance, when collecting a dataset, how are the authors filtering offensive content such as pornographic or violent images?
  4. Compliance with GDPR and other data-related regulations. For instance, if the authors collect human-derived data, what is the mechanism to guarantee individuals’ right to be forgotten (removed from the dataset)?

This list is not intended to be exhaustive — it is included here as a prompt for author and reviewer reflection.

Author FAQs

About Submitting Papers and Supplementary Material

Q. What does paper registration deadline mean? What do I need to do until then?

A. Until the paper registration deadline, you need to create a submission in openreview, add a title and an abstract for your paper, add all your co-authors (and ideally make sure that these openreview profiles are complete to avoid extra unnecessary stress at the paper submission deadline).

Q. Can we please have an extension on the paper registration or submission deadline?

A. NO. And any incomplete submission or a submission not meeting required criteria will be deleted.

Q. Can I update my paper’s information (e.g., title, abstract, author list) after the paper registration deadline?

A. You can update the title and abstract until the paper submission deadline. You can also reorder the author list until the paper submission deadline. However, after the paper registration deadline, you can no longer create new paper submissions or add/delete authors of your submission(s).

Q. Can I add/remove authors after my paper has been accepted?

A. NO. After the paper registration deadline, the author list is considered final. Changes to the authorship order following acceptance may be considered, but only in special circumstances.

Q. Are there any formatting requirements for PDFs in the supplementary material?

A. No. The important thing is that supplementary PDFs are legible and neatly formatted. Many authors choose to use the official ICCV style for any supplementary PDFs as well, but this is not a must. Formatting supplementary documents in a single-column layout is permitted.

Q. Can I link to an external webpage from my ICCV submission?

A. This is strongly discouraged because it runs a high risk of violating anonymity or the media ban, or circumventing length or deadline restrictions. If you feel you absolutely must link to external materials, see the next question.

Q. Can I link to additional image or video material from the supplementary material?

A. Only if absolutely necessary and as long as the double-blind review process and deadline integrity are preserved. To that end, authors need to ensure the following conditions: (1) The image and video material is too large to include in the supplementary file size limit. (2) The hosting site and the linked material does not reveal the identity and affiliation of the authors. (3) The hosting site or apps do not track or identify who viewed the materials. (4) The authors provide a smaller-sized version of their image or video material in the submitted supplementary material.

Condition 4 ensures that reviewers have a direct way of viewing the material (albeit at a lower quality) and are also able to verify that the externally hosted material has not been modified since the supplementary material deadline.

Authors bear the responsibility and are advised to proceed with caution not to break the double-blind review process. Note, not all hosting services are available in all regions. Authors should also note that, just like for the supplementary material itself, reviewers are under no obligation to review such additional image or video material.

About Preprints, Anonymity, and Media Promotion

Q. Does a Technical Report (departmental, arXiv, etc.) available online count as a prior publication, and therefore is that work ineligible for review and publication at ICCV 2025?

A. Please read the dual submission policy above.

Q. Does a document on GitHub or other open repositories count as a publication, and therefore is ineligible for review and publication at ICCV 2025?

A. Submissions to GitHub and similar repositories cannot be rejected and are accepted by default before any "review" that can take place on such platforms. Given definitions in the dual submission paragraph above, GitHub documents are not publications and won't be treated as such. To preserve anonymity, you should not cite your public codebase. You can say that the code will be made publicly available.

Q. Does a presentation at a departmental seminar during the review period violate the anonymity or media promotion policy?

A. It does not. Presentation of material at an academic talk, without mentioning it as being in submission to ICCV, is acceptable.

Q. Can I list my ICCV submission in an application for a job or graduate program?

A. Yes. As long as you communicate this information confidentially and to a small group of people, it is OK. However, you should not list ICCV submissions on public websites or on media (see below).

Q. Can I post my submission on arXiv? 

A. Yes. 

Q. Can I have a video link in my arXiv paper?

A. Yes, you may. 

Q. Can I build a project website related to my arXiv paper?

A. Yes, you may.

Q. How do I cite my results reported in open challenges?

A. To conform with the double blind review policy, you can report results of other challenge participants together with your results in your paper. For your results, however, you should not identify yourself and should not mention your participation in the challenge. Instead present your results referring to the method proposed in your paper and draw conclusions based on the experimental comparison to other results.

Q. Does my submission need to cite arXiv papers that are related to my work?

A. Consistent with good academic practice, you need to cite all sources that inspired and informed your own work. This said, asking authors to thoroughly compare their work with arXiv reports that appeared shortly before the submission deadline imposes an unreasonable burden. We also do not wish to discourage the publication of similar ideas that have been developed independently and concurrently. Authors and reviewers should keep the following guidelines in mind:

  • Authors are not required to discuss and compare their work with recent arXiv reports, although they must properly cite those that inspired them.
  • To reduce confusion, whenever citing papers that initially appeared on arXiv, the authors should check whether those papers had subsequently been published in a peer-reviewed venue, and to cite those versions accordingly.
  • Failing to cite an arXiv paper or failing to beat its performance SHOULD NOT be sole grounds for rejection.
  • Reviewers SHOULD NOT reject a paper solely because another paper with a similar idea has already appeared on arXiv. If the reviewer suspects plagiarism or academic dishonesty, they are encouraged to bring these concerns to the attention of area and program chairs.
  • It is acceptable for a reviewer to suggest that an author should acknowledge or be aware of something on arXiv.

The anonymity policy and its interpretation


Q: Can I discuss papers submitted to ICCV with the media before they have been officially accepted?

A. You are prohibited from discussing papers, not of the underlying technology. Authors should use reasonable care to avoid communicating their identity to referees. A pedantic author might argue that, although they (say) set up a webpage describing their paper as "in submission at ICCV 2025", they did not discuss it with the media. PCs discourage this class of argument as not being consistent with the intention of the policy. PCs have nearly arbitrary powers to interpret policy, and if necessary will exercise them in what PCs see as the interests of the community. 

Q: What can be said about work before a paper is submitted?

A. The ICCV Media Policy prohibits discussing a submitted paper, but not the core content of a paper that is intended for submission. For instance, it is acceptable to describe the technology, highlight its significance for the organization, and discuss supporting experiments. None of this violates the policy, as it does not refer to a submitted paper. Any discussion about the paper being prepared for submission to ICCV should be avoided.

Q: Can a paper be posted online with a note saying, “this paper will be submitted to ICCV”?

A. This practice is discouraged. Program Chairs (PCs) have advised authors against doing so and have requested authors who have done this to stop. PCs are concerned that such actions could reasonably be interpreted as a violation of anonymity, potentially leading to a desk rejection. While Area Chairs (ACs) and reviewers will not be directed to actively search for anonymity violations, PCs will address any violations that come to their attention.

Q: Once a paper is submitted, what can author A say about the paper?
A. The ICCV Media Policy prohibits discussing a submitted paper, but not the core content of a paper that is intended for submission. For instance, it is acceptable to describe the technology, highlight its significance, and discuss supporting experiments. None of this violates the policy, as it does not refer to a submitted paper. However, please note that any mention of the paper as “under submission to ICCV” is in violation of the policy. 

About Datasets

Q. My research uses datasets that have been withdrawn by their creators, such as DukeMTMC-ReID or MS-Celeb-1M. What should I do?

A. Generally, papers should not use datasets that have been withdrawn by their creators, as doing so may involve ethical violations or even legal complications. Under some circumstances, authors may feel they need to use such datasets — for example, if fair comparison is impossible in any other way. However, authors who use such datasets should always explain the need to do so carefully and in some detail as such claims will be carefully scrutinized. Note that in many cases alternative datasets exist. The recommended course should be to not use the dataset, and (if necessary) explain that this may affect certain comparisons with prior art. It is a violation of policy for a referee or area chair to require comparison on a dataset that has been withdrawn.

Q. My research relies on broadly used public datasets of others, which have not been withdrawn, but for which it is unclear if they have been approved by an IRB. Is this allowed?

A. In the case of broadly used datasets that are still offered by their creators, for which IRB approval status is unclear, authors are encouraged to discuss the situation, e.g., why no better alternatives are available.

Q. I wish to claim a dataset contribution in my paper, but I either cannot release the data publicly, or am not sure I will be able to do so by the time of publication. Is this an issue?

A. YES. If you wish to claim a dataset as one of your contributions, it is expected that your dataset will be ready and available at the time you will be submitting the camera ready paper. If you cannot ensure that you can meet this deadline, then the release of the dataset should not be one of the major scientific contributions of your paper. Note that it is still acceptable to submit work relying on a non-public dataset – you just cannot claim that dataset as one of your contributions, and the paper will have to be evaluated based on its other merits.

About LLMs

Q. What is the LLM policy for authors in ICCV 2025?

A. Authors may use any tools they find productive in preparing a paper, but must be aware that they are responsible for any misrepresentation, factual inaccuracy or plagiarism in their paper.  Papers containing citations of non-existent material will be rejected when found, and may be rejected without review. Similarly, papers containing obvious factual inaccuracies will be rejected when found and may be rejected without review.  It is not a defense to a  charge of plagiarism or of inaccuracy to argue that "an LLM did it". You are responsible for what you submit.

Q. How will the LLM policy be implemented?

A. Referees who find inaccuracies should act as they usually would; as should AC's. Glaring examples of citations to non-existent material can be desk-rejected.