BMVC Author Guidelines

Contents

Introduction

These guidelines are inspired by CVPR’2024 Author Guidelines. BMVC Programme Chairs adapted these guidelines to achieve the goals of BMVC 2024.

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.

Paper formatting

Papers in the BMVC style are limited to nine pages, including figures and tables. Additional pages containing only cited references are allowed. Please download the BMVC 2024 Author Kit for detailed formatting instructions and guidelines. These instructions can be found in the following links.

Download the template

View the Github repository

Get Overlead Template

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

Authors acting as reviewers

Given the growth in paper submissions, we expect all authors to be willing to serve as reviewers if asked to do so. To help us identify qualified reviewers and match submissions to reviewers, all authors are required to have an up-to-date OpenReview profile (see OpenReview author instructions). We will only acknowledge reviewers during the conference and on the BMVC website if the review is above a quality threshold (see Reviewing policies).

Submission and review process

BMVC 2024 will use OpenReview to manage submissions. Consistent with the review process for previous BMVC conferences, submissions under review will be visible only to their assigned members of the program committee (programme chairs, 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 must create (or update) their OpenReview profile by the full paper submission deadline. By submitting a paper to BMVC, 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 in the link below.

Creating or Updating an OpenReview Profile

PCs are facing a huge growth in submissions and are spending all their energies ensuring that papers find appropriate ACs and reviewers. For this reason, PCs will NOT:

and PCs will NOT answer emails on these points.

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 BMVC organisers. It should be noted, however, that all program committee members are volunteers, and the BMVC organisation 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 must 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.

Double-blind review

BMVC 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 authors’ names from the submission and the additional material. Do not provide information that may identify the authors in the acknowledgements (e.g., co-workers and grant IDs) and 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. Suppose you must cite any of your papers being submitted concurrently to BMVC or another venue. In that case, you should (1) include anonymised versions of those papers in the supplementary material, (2) cite these anonymised papers, and (3) argue in the body of your paper why your BMVC submission is non-trivially different from these concurrent submissions.

Plagiarism and LLMs

Authors take complete responsibility for their papers’ accuracy and authenticity when submitting them to BMVC. To ensure a high standard of academic and professional integrity, authors must avoid misrepresentation, factual inaccuracies, and plagiarism at all costs. Any paper with citations of non-existent material or obvious factual inaccuracies will be rejected outright and will not be subject to review. It is important to note that attributing plagiarism or inaccuracy to LLMs or someone else is not a viable defence. As an author, it is your duty to ensure that every aspect of your paper is of the highest standard and that your contribution is both original and ethically sound.

Plagiarism consists of appropriating the words or results of another without credit. We will actively check for plagiarism. Furthermore, the paper matching system is quite accurate. As a result, it regularly happens that a paper containing plagiarised material goes to a reviewer from whom the material was plagiarised; experience shows that such reviewers enthusiastically pursue plagiarism cases. Therefore, if a submission contains plagiarised material, the submission will be rejected.

Dual submissions

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

For this policy, a publication is defined as 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 proceeding or whether the organisers declare that such work “counts as a publication.” Under the above definition, arXiv preprints and university technical reports are not considered publications. However, peer-reviewed workshop papers are considered publications if their length is more than four pages (excluding references), even if they do not appear in a proceeding.

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 penalised for not citing it.

Supplementary material submission

By the supplementary material deadline, the authors may optionally submit additional material that was ready at the time of paper submission but could not be included due to constraints of format or space. The authors should appropriately refer to the supplementary material’s contents 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. 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 to help reviewers assess the quality of the work.

Personal and human subjects data

If a paper uses personal data or data from human subjects, including personally identifiable information or offensive content, we expect that the collection and use of such data have been conducted carefully per the ethics guidelines or policies at the author’s institution. In many countries and institutions, collecting and using personally identifiable data or data from human subjects is subject to approval from an Institutional Review Board 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 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.

Registration and Attendance Responsibilities

The authors agree that if the paper is accepted, at least one of the authors will register for and attend the conference so that the paper can appear in the proceedings.

Publication

The British Machine Vision Association will make all accepted papers publicly available one week before the conference. Authors wishing to submit a patent should understand that the paper’s official public disclosure is one week before the conference or whenever the authors make it publicly available, whichever is first. BMVC considers papers confidential until published one week before the conference. However, BMVC notes that multiple organisations 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.

The copyright of accepted papers at BMVC remains with the authors.