Skip to yearly menu bar Skip to main content


ECCV 2026 Area Chair Guidelines

https://eccv.ecva.net/Conferences/2026/ACGuide

 

Thank you for agreeing to serve on the program committee of ECCV 2026! As an area chair (AC), your job is to ensure that all the submissions you are assigned have high quality reviews and good discussions. You should become familiar with the technical contents of all your submissions and are responsible for making the initial acceptance decisions, with guidance from your senior area chair (SAC).

If you encounter a situation that you are unable to resolve on your own:

  • If it is a general question, please contact the Program Chairs.
  • If you have specific questions related to the handling of a particular paper, please leave a comment on the OpenReview forum for that paper with the readers set to SACs and PCs.

Important Dates

Here is a tentative design of the key dates (all at 11:00 PM CET) related to ACs. They are subject to fine-tuning if needed.

February 26, 2026 - Paper registration deadline  

March 5, 2026 - Paper submission deadline  

March 12, 2026 - Supplementary material deadline  

March 13-20, 2026 - ACs receive papers and suggest reviewers  

March 31, 2026 - Papers assigned to reviewers  

April 21, 2026 - Reviews due  

April 22-May 1, 2026 - ACs ensure every paper has at least 3 high-quality reviews (will need to verify review quality, run after reviewers with missing/poor reviews, and obtain emergency reviews as needed)  

May 2, 2026 - Reviews released to authors  

May 2-11, 2026 - Author rebuttal 

May 12-20, 2026 - ACs discuss papers with reviewers  

May 20, 2026 - Final reviewer recommendations due  

May 25, 2026 - ACs’ preliminary meta-reviews and recommendations due  

May 26 - June 4, 2026 - AC Triplet meetings (flexibly scheduled by each triplet); discussion with SAC

June 9, 2026 - ACs’ final meta-reviews and recommendations due  

June 17, 2026 - Final accept/reject decisions to authors

 

Main Tasks

  1. Preparation:
    • Please ensure that your preferred email address is accurate in your OpenReview profile. We will send most emails from OpenReview (noreply@openreview.net). Such emails are sometimes accidentally marked as spam (and sometimes as updates in Gmail). Please check your spam folder regularly. If you find such an email in there, please whitelist the OpenReview email address so that you will receive future emails from OpenReview.
    • Please log into OpenReview and make sure that your profile is up to date.
    • Read and agree to abide by the ECCV code of conduct.
    • Read what constitutes a conflict of interest for ECCV 2026.
    • Read the Submission Policies.
    • In addition to the guidelines below, please familiarize yourself with the Reviewer guidelines. You will be interacting significantly with reviewers, so please make sure you understand what is expected of them. You may also refer to the SAC guidelines.
  2. Matching reviewers to papers: March 13  – March 20
    • You will be asked to rank reviewers in OpenReview for each one of your papers
    • In addition to the usual ranking based on OpenReview’s paper matching, we will show a new feature on both papers and reviewers: Contribution Types. For detailed instructions on how to use this new feature, please see our AC guide to contribution types.
    • Ideally, contribution types should help reviewers in assessing the correct contributions in the papers, and also help match reviewers’ contribution type preferences to the contribution types of papers.
    • However, this new feature should be viewed as one useful signal among many, rather than a strict requirement for matching. They can help you reason about the potential fit between papers and reviewers, but they are not definitive or binding.
  3. Ensure all papers have at least 3 high-quality reviews: April 22 - May 1
    • Reviews are due April 21. We will send reminders to reviewers with missing reviews during the review window. If a reviewer is unable to deliver a review and communicates this to you in OpenReview, please find a replacement reviewer (instructions to be updated later).
    • Read all reviews carefully. If a review is substandard, you should ask the reviewer to improve their review. Please remember to be polite and provide concrete guidance.
    • Check that reviews correctly assess the paper’s Contribution Type or indicate why they disagree with the author’s Contribution Type choice.
    • Make sure that any questionable papers are flagged for ethics review. These papers will be assigned ethics reviewers, who will effectively join the paper's assigned program committee.
    • We are still planning on how you can get additional/emergency reviewers. We will let you know when the time comes.
  4. Discussion with reviewers: May 12-20 
    • As soon as the authors’ rebuttal is entered into the system, initiate and lead a discussion via OpenReview for each submission, and make sure the reviewers engage in the discussion phase.
    • Monitor and moderate the discussion to ensure that it is respectful of everyone’s opinion. Read the submissions in your stack to steer the discussion toward the most critical aspects.
  5. Ensure all final recommendations have been entered and are of high quality: by May 20
    • As soon as the discussion phase ends, ensure that all reviewers have entered their Final Recommendations with comments that reflect reading the rebuttal, the other reviews, and the discussion with the other reviewers, and match the correct Contribution Type criteria.
    • Also, ensure that all reviewers have entered the Final Rating and that this is consistent with their Final Recommendation.
  6. Writing the preliminary metareviews: May 20 - 25
    • This is considered the final phase of the discussions, and you will write the preliminary metareviews. You can elicit further comments and clarifications from the reviewers. Please reach out to your SAC if you need help. 
    • Write a preliminary meta-review that explains your decision (clear accept/reject or needs discussion). Summarize how the reviews, the authors’ rebuttal, and the discussion support your preliminary decision. 
    • At this stage, a draft metareview is sufficient.
  7. Discussion with the AC triplet: May 26 - June 4
    • An AC triplet lead will be assigned to each triplet. The Lead AC will coordinate the AC meetings and ensure they are scheduled in advance.
    • Discuss all papers with your AC triplet and make sure you allocate sufficient time for borderline cases.
    • If an agreement cannot be reached, reach out to your SAC. Schedule a meeting to discuss the hard cases.
    • For the papers in which the AC’s recommendation goes against the unanimous recommendation of the reviewers, the decision needs to be approved by the PCs.
  8. Writing of the final metareviews and paper recommendations: June 9
    • Your metareviews should augment the reviews and explain how the reviews, the authors’ rebuttal, and the discussion were used to arrive at your decision. Do not dismiss or ignore a review unless you have a good reason for doing so. If the reviewers cannot come to a consensus during the discussion, you should read the paper carefully and write a detailed meta-review. You are expected to discuss such difficult cases with your SAC.
    • Please help us by submitting your metareviews on time. 
  9. ACs respond to PC and SAC requests to recommend spotlight/highlight papers, oral papers, and award candidates, unless those were already requested in the final recommendation form.

 

Responsible AC Policy

Area Chairs play an important role in the review process, from suggesting reviewers for papers and ensuring at least three high-quality reviews per paper, to driving the discussion with reviewers and writing metareviews. If an AC fails to execute even one of these steps, the entire process suffers and slows down. Irresponsible behavior includes failing to follow up with late reviewers, failing to organize substitutes (emergency reviewers), failing to organize reviewer discussion, failing to participate in triplet meetings, failing to provide metareviews, providing metareviews of poor quality, or outsourcing metareviews to LLMs. In particular, failing to perform these steps without any justification and communication to the responsible SAC warrants a "highly irresponsible" categorization. If an SAC flags an AC as "highly irresponsible", all papers on which that AC is an author will face desk rejection at the discretion of the PCs.

 

Best Practices

  • Please respect deadlines and respond to emails as promptly as possible.
  • It is okay to be unavailable for part of the review process (e.g., on vacation for a few days), but if you will be unavailable for more than that—especially during important windows (e.g., discussion, decision-making)—you must let your SAC know as soon as you can.
  • If you notice a conflict of interest with a submission that is assigned to you, please contact your SAC immediately so that the paper can be reassigned.
  • Be professional and listen to the reviewers, but do not give in to undue influence. We expect you to be familiar with all the papers that are assigned to you and to be able to argue about their technical content and contributions. Your responsibility is to make good decisions, not just facilitate reviewer discussions.
  • Follow reviewer consensus for unanimous decisions, unless there are extraordinarily unusual circumstances:
    • For example, to accept a paper with unanimously negative reviews, there should be significant referee error, or a very convincing rebuttal; to reject a paper with unanimously positive reviews, there should be exceptional circumstances such as significant previously undetected technical errors, or undetected fraud or plagiarism.
    • You should be checking reviews as they are submitted, and catching fundamental errors at that time, not during the triplet discussion period.
    • In these cases, the decision needs to be approved by the PCs.
  • Be kind. It is important to acknowledge that personal situations may lead to late or unfinished work among reviewers. In the event that a reviewer is unable to complete their work on time, we encourage you to be considerate of the personal circumstances; you might have to pick up the slack in some cases. In all communications, exhibit empathy and understanding.
  • Keep your discussions within triplets. If you need a conflict-free outside opinion, reach out to your SAC.
  • DO NOT talk to other SACs or ACs about your own submissions (i.e., submissions you are an author on) or submissions with which you have a conflict of interest.
  • If you notice unethical or suspicious behavior by authors or reviewers, please notify your SAC and program chairs.

Writing the meta-review

These guidelines are due to Chris Williams and John Lafferty and lightly adapted.

  • Make sure that you consider the Contribution Types chosen by the authors in your meta-review, or if there is disagreement, explain in detail the reasons.
  • Don't focus too much on the scores. Instead, look carefully at the comments. Judge the quality of the review rather than taking note of the reviewer's confidence score; the latter may be more a measure of personality.
  • Indicate that you have read the author's response, even if you just say "the rebuttal did not overcome the reviewer's objections."
  • If you use information that is not in the reviews (e.g., from corresponding with one of the reviewers after the rebuttal period), tell the authors (a) that you have done so and (b) what that information is.
  • If you find yourself wanting to overrule a unanimous opinion of the referees, the standards for your summary should be at the level of a full review. In these cases, it would probably be best to solicit an auxiliary review.
  • Please attempt to take a decisive stand on borderline papers. Other than papers where there is a genuine disagreement, much of our work will involve borderline papers where no one confidently expresses excitement, nor are any major problems identified. These are the tough decisions where we need your judgment!
  • Try to counter biases you perceive in the reviews. Unfashionable subjects should be treated fairly but often aren't, to the advantage of the papers on more mainstream approaches. To help the community move faster out of local minima, it is important to encourage risk and recognize that new approaches can't initially yield state-of-the-art competitive results. Nor are they always sold according to the recipes we are used to.

Confidentiality

You must keep everything relating to the review process confidential. Do not use ideas, code and results from submissions in your own work until they become publicly available (e.g., via a technical report or a published paper for ideas/results, via open source for code, etc.). Do not talk about or distribute submissions (whether it is the code, or the ideas and results described in them) to anyone without prior approval from the program chairs. Code submitted for reviewing cannot be distributed.