怕存在一些被忽视的流程, 因此本文对CVPR2021的Authors Guidelines:http://cvpr2021.thecvf.com/node/33 进行全文对照翻译。
目录
Conflict Responsibilities 冲突责任
1) Paper submission and review site 论文提交网址
4) Creating a paper submission 创建一个论文的提交
6) Submission Requirements 提交要求
7) Supplementary Material Submission 补充材料的提交
8) Code Submission and Reproducibility 代码提交和复现
Detailed supplementary material guidelines 补充材料提交说明
Rebuttal Instructions 关于Rebuttal的说明
About Submitting Papers 关于论文提交
About the Review Process 关于审稿过程
AUTHOR GUIDELINES 作者(投稿)指南
CMT submissions Website 提交网址
https://cmt3.research.microsoft.com/CVPR2021
注：
Microsoft CMT 是一个一流的，可托管且可扩展的学术会议管理系统。
会议管理工具包（CMT）由Microsoft Research赞助。 CMT在Microsoft Azure云平台上运行，并且跨数据中心对数据进行地理复制。 它具有高度的安全性，可用性，可伸缩性和可靠性。 CMT处理最复杂的学术会议工作流程。 可通过基于Web的界面完全访问其功能。
Microsoft CMT – Best-In-Class, Hosted and Scalable Academic Conference Management System
The Conference Management Toolkit (CMT) is sponsored by Microsoft Research. CMT runs on Microsoft Azure cloud platform with data geo-replicated across data centers. It is highly secure, available, scalable, and reliable. CMT handles the most complex workflows of academic conferences. Its functionalities are fully accessible through web based interfaces.
Call for Papers 投稿主题
Papers in the main technical program must describe high-quality, original research. Topics of interest include all aspects of computer vision and pattern recognition including, but not limited to:
本会议主要技术程序中的论文(即通常所提交的regular papers)必须描述高质量的原创研究。 感兴趣的主题包括计算机视觉和模式识别的所有方面，包括但不限于：
| 2D object recognition | 二维物体识别 |
| 3D computer vision | 三维计算机视觉 |
| 3D object recognition | 三维物体识别 |
| Action and behavior recognition | 动作和行为识别 |
| Adversarial learning, adversarial attack and defense methods | 对抗学习、对抗攻击和防御方法 |
| Biometrics, face, gesture, body pose | 生物识别，如通过面部、姿态、体态 |
| Computational photography | 计算摄像 |
| Datasets and evaluation | 数据集和评估 |
| Efficient training and inference methods for networks | 网络的高效训练和推理方法 |
| Explainable AI, fairness, accountability, privacy, transparency and ethics in vision | 可解释的AI |
| Image and video retrieval | 图像和视频恢复 |
| Image and video synthesis | 图像和视频合成 |
| Image classification | 图像分类 |
| Low-level and physics-based vision | 低层和基于物理的视觉 |
| Machine learning architectures and formulations | 机器学习架构和理论 |
| Medical, biological and cell microscopy | 医学，生物学和细胞显微成像 |
| Motion and tracking | 运动与追踪 |
| Optimization and learning methods | 优化和学习方法 |
| Pose estimation | 姿态估计 |
| Representation learning, deep learning | 表示学习、深度学习 |
| Scene analysis and understanding | 场景分析和理解 |
| Transfer, low-shot, semi- and un- supervised learning | 迁移学习、小样本学习、半监督/无监督学习 |
| Video analysis and understanding | 视频分析和理解 |
| Vision + language, vision + other modalities | 视觉+语言 或 视觉+其他模态 |
| Vision applications and systems, vision for robotics and autonomous vehicles | 视觉应用和系统，如机器人和自动驾驶中的视觉 |
All submissions will be handled electronically. In addition to the main technical program, the conference will include Tutorials, Workshops, Demonstrations, and Exhibits. Submit proposals to the appropriate chair.
所有提交内容将以电子方式处理。 除主要技术程序(regular papers)外，会议还将包括教程，讲习班，演示和展览。 提交的文章将会被分配给合适的主席。
Important dates 重要的日期
| Paper registration deadline 论文注册截止日期 | November 9, 2020 (11:59PM Pacific Time) 北京时间11月10日下午15:59分 |
| Paper Submission Deadline 论文提交截止日期 | November 16, 2020 (11:59PM Pacific Time) 北京时间11月17日下午15:59分 |
| Supplementary Materials Deadline 补充材料提交ddl | November 23, 2020 (11:59PM Pacific Time) 北京时间11月24日下午15:59分 |
| Reviews Released to Authors 将审稿意见发给作者 | January 18, 2021 (11:59PM Pacific Time) 北京时间1月19日下午15:59分 |
| Rebuttal Due rebuttal的ddl | January 25, 2021 (11:59PM Pacific Time) 北京时间1月26日下午15:59分 |
| Final Decisions to Authors 最终决定 | February 28, 2021 2月28日 |
| Camera-Ready Deadline 论文排版定稿ddl | TBD (To Be Discussed / Determined)待定 |
| Main Conference 主会议召开 | June 21 – 24, 2021 2021年6月21-24日 |
* Submission date is fixed, no extension will be given.
*论文提交ddl就是这个，不会因为疫情而推迟
Policies 政策
Important 重要:
Please note that the policies have been updated from the 2020 version, including guidelines related to arXiv prior work, code submission, and authors acting as reviewers.
请注意，该政策相比于2020年有了更新，更新的包括以下部分:
- arXiv中先前的工作；
- 代码提交；
- 对既是审稿人又是作者的人的有关的指南。
Review Process 审稿程序
By submitting a paper to CVPR, the authors agree to the review process and understand that papers are processed by the Toronto system to match each manuscript to the best possible area chairs and reviewers.
在CVPR提交论文时，作者就已经同意接受审稿过程，并了解多伦多系统会处理论文以使每份手稿与最佳的区域主席和审稿人相匹配。
Confidentiality 保密性
The review process of CVPR is confidential. Reviewers are volunteers not part of the CVPR organization and their efforts are greatly appreciated. The practice of keeping all information confidential during the review is part of the standard communication to all reviewers. Misuse of confidential information is a severe professional failure and appropriate measures will be taken when brought to the attention of CVPR organizers. It should be noted, however, that the organization of CVPR is not and cannot be held responsible for the consequences when reviewers break confidentiality.
CVPR的审稿过程是保密的。 审稿人是不属于CVPR组织的志愿者，我们应该感谢他们的努力。 在审阅过程中对所有信息保密的做法是与所有审稿人进行标准沟通的一部分。 滥用机密信息是严重的错误。当这种错误引起CVPR组织者注意时，我们将采取适当的措施。 但是，应该指出的是，当审稿人破坏保密性时，CVPR的组织方不会也不应对后果承担责任。
Conflict Responsibilities 冲突责任
It is the primary author's responsibility to ensure that all authors on their paper have registered their institutional conflicts into the submission system – CMT3 (see details under Domain Conflicts below). If a paper is found to have an undeclared or incorrect institutional conflict, the paper may be summarily rejected. To avoid undeclared conflicts, the author list is considered to be final after the submission deadline and no changes are allowed for accepted papers.
论文的主要作者有责任确保其论文上的所有作者均已将其域冲突注册到提交系统CMT3中（请参阅下面的“域冲突”下的详细信息）。 如果发现论文存在未声明或不正确的机构冲突，则该论文可能会被立即拒绝。 为避免发生未声明的冲突，作者列表在提交截止日期之后被认为是最终版本，并且不允许更改已接受的论文。
Double blind review 双盲审
CVPR reviewing is double blind, in that authors do not know the names of the area chair/reviewers of their papers, and the area chairs/reviewers cannot, beyond reasonable doubt, infer the names of the authors from the submission and the additional material. Avoid providing information that may identify the authors in the acknowledgments (e.g., co-workers and grant IDs) and in the supplemental material (e.g., titles in the movies, or attached papers). Avoid providing links to websites that identify the authors. Violation of any of these guidelines may lead to rejection without review. If you need to cite a different paper of yours that is being submitted concurrently to CVPR, the authors should (1) cite these papers; (2) argue in the body of your paper why your CVPR paper is non trivially different from these concurrent submissions; and (3) include anonymized versions of those papers in the supplemental material.
CVPR审稿是双盲的，因为作者不知道其论文的区域主席/审稿人的姓名，并且区域主席/审稿人通常情况下(即对论文作者不存在疑问的情况下)不能从来稿和其他材料中推断出作者的姓名。 因此，作者应该避免在致谢（例如，同事和授权ID）和补充材料（例如，电影中的标题或随附的论文）中提供可能标识作者的信息。 避免提供指向标识作者的网站的链接。 违反这些准则中的任何一条都可能导致拒绝审稿。 如果您需要引用同时提交您的正在提交给CVPR的另一篇论文，作者应该（1）引用这些论文； （2）在您的论文正文中说明为什么您的CVPR论文与这些同时提交的论文有什么不同； （3）在补充材料中包含这些论文的匿名版本。
Plagiarism 剽窃
Plagiarism consists of appropriating the words or results of another, without credit. CVPR 2021'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 at 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.
CVPR 2021对剽窃的处理政策是将可疑案件移交给IEEE知识产权局，该局拥有处理窃的既定机制，并具有将违法作者排除在未来会议和IEEE期刊之外的权力。 您可以在网页上(省略)找到有关该办公室，其程序以及关于五个级别的剽窃定义的信息。 我们将积极检查剽窃行为。 此外，纸张匹配系统非常准确。 结果，经常发生的是，抄袭者的论文常常会由被抄袭者作为审稿人，经验表明，这类被抄袭的审稿人热衷于审稿这类剽窃案例hhh
Dual/Double Submissions 多稿提交
The goals of CVPR are to publish exciting new work for the first time and to avoid duplicating the effort of reviewers. By submitting a manuscript to CVPR, 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 has been or will be 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.
CVPR的目标是将令人兴奋的新作品首次发布，并避免重复审稿人的工作。 通过向CVPR提交手稿，作者应该承认该手稿以前从未在任何经过同行评审的场所（包括期刊，会议或讲习班或论坛）以基本上类似的形式出版或接收。 此外，在审查期间，没有或没有将内容实质相似的出版物提交给本次会议或另一次会议，研讨会或期刊。 违反这些条件中的任何一个都将导致拒绝，并将报告给提交该材料的另一个通道(即多投的那个期刊/ 会议等)。
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”.
就本政策而言，出版物的定义是指书面作品的长度超过四页（不包括参考文献），已提交给同行评审以接受或拒绝，并且在审核后被接受。 特别是，出版物的定义并不取决于这种接受的书面作品是否出现在正式的会议中，也不取决于组织者是否宣称此类作品“算作出版物”。
The above definition does not consider an arXiv.org paper as a publication because it cannot be rejected. It also excludes university technical reports which are typically not peer reviewed. However, this definition of publication does include peer-reviewed workshop papers, even if they do not appear in a proceedings, if their length is more than four pages (excluding citations). Given this definition, any submission to CVPR should not have substantial overlap with prior publications or other concurrent submissions.
上面的定义不会将arXiv.org论文视为出版物，因为它不能被拒绝。 它还不包括通常未经同行评审的大学技术报告。 但是，此出版物的定义的确包括经过同行评审的研讨会论文，即使这些论文没有出现在会议中但它们的长度超过了四页（不包括引文）。 根据这个定义，任何向CVPR提交的材料都不应与先前的出版物或其他同时提交的材料有实质性的重叠。
A submission with substantial overlap is one that shares 20 percent or more material with previous or concurrently submitted publications. Authors are encouraged to contact the Program Chairs about clarifications on borderline cases.
所谓具有实质性重叠，是指与先前或同时提交的出版物有20％或更多的材料重复。 我们鼓励作者联系程序主席，以澄清边界案例。
Note that a technical report (departmental, arXiv.org, etc.) version of the submission that is put up without any form of direct peer-review is NOT considered prior art and should NOT be cited in the submission.
没有经过任何形式的同行评议的技术报告版本，如arxiv等，不被视作之前的工作，也因此不应该被引用。
这句话应该是有争议的，2019 CVPR的版本更为详细：Note that a Technical Report (departmental, arXiv.org, etc.) that is put up without any form of direct peer-review is NOT considered a publication and is therefore allowed, but should NOT be cited. Likewise, mention of the work under review in a presentation is NOT considered a violation. For further information, please refer to Section 8.2.4.F of the IEEE PSPB Operations Manual. 即arxiv等未经过同行评议的工作不应该、但允许引用，而且在presentation中提到送审状态下的工作也并不违规。
除此之外，最后的问答部分中也对最新的arxiv的引用做出了说明，是允许引用最新的代表SOTA的arxiv的.
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.
参会责任：如果作者同意论文被接收，则至少一名作者将注册会议并在此提交论文。
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 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 http://www.cv-foundation.org/.
出版：所有接受的论文将在会议召开前两周由计算机视觉基金会（CVF）公开提供。提交专利的作者应该了解到，论文的正式公开披露时间是在会议召开前两周，或者是作者公开发布的时间，以最先的那个时间为准。 会议认为，在会议召开前两周之前，论文都是机密的，但要注意，多个组织将在审查和生产过程中进行访问，因此，寻求专利的组织应与IP理事会讨论申请日期。 会议不承担任何提前披露的责任。 有关CVF的更多信息，请访问http://www.cv-foundation.org/。
Publicity, social media: Papers submitted to CVPR must not be discussed with the press until they have been officially accepted for publication. Work explicitly identified as a CVPR submission also may not be advertised on social media. Please see the FAQ section for more details. Violations may result in the paper being rejected or removed from the conference and proceedings.
媒体宣传：提交给CVPR的论文只有在被正式接受发表之后，才可以与媒体讨论。 明确标识为CVPR提交的作品也不被允许在社交媒体上做广告。 请参阅“常见问题”部分以了解更多详细信息。 违规行为可能导致论文被拒绝或被从会议和议事录中删除。
Authors acting as reviewers: Given the growth of the number of paper submissions, we expect all authors to be willing to serve as reviewers as well. With a large enough pool of reviewers, we expect that reviewers will be sent of the order of five papers to review. Our timeline expects that papers will go to reviewers about Dec 7, 2020, and reviews should be returned on or before Jan 4, 2021.
担任审稿人的作者：鉴于论文投稿数量的增长，我们希望所有作者都愿意担任审稿人。 由于有足够多的审稿人，我们预计将向审稿人发送五篇论文进行审阅。 我们的时间表预计论文将在2020年12月7日左右提交给审稿人，审稿应于2021年1月4日或之前退还。
Submission Guidelines 提交指南
All submissions will be handled electronically via the conference's CMT Website. By submitting a paper, the authors agree to the policies stipulated in this website. The paper submission deadline is November 16, 2020. Note that each paper should already be registered one week earlier, by November 9, 2020. Supplementary material can be submitted until November 23, 2020.
所有提交的内容都将通过会议的CMT网站进行电子处理。 提交论文的作者应同意本网站中规定的政策。 论文提交截止日期为2020年11月16日。请注意，每篇论文应在2020年11月9日之前提前一周注册。补充材料在2020年11月23日前提交即可。
Papers are limited to eight pages, including figures and tables, in the CVPR style. Additional pages containing only cited references are allowed. Please refer to the following files for detailed formatting instructions:
CVPR样式的论文限于八页，包括图形和表格。 允许仅包含引用参考的其他页面。 请参阅以下文件以获取详细的格式化说明：
- Example submission paper with detailed instructions 有着详细指南的提交样例
- LaTeX/Word Templates Zip file Latex/ word模板
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.
未正确匿名化，不使用模板或超过八页（不包括参考文献）的论文将被拒绝，恕不审查。
1) Paper submission and review site 论文提交网址
Submission Site (bookmark or save this URL!)
Please make sure that your browser has cookies and Javascript enabled.
请确保您的浏览器启用了Cookie和Javascript。
Please add "email@msr-cmt.org" to your list of safe senders (whitelist) to prevent important email announcements from being blocked by spam filters.
请在您的安全发件人列表（白名单）中添加“ email@msr-cmt.org”，以防止重要的电子邮件公告被垃圾邮件过滤器阻止。
Log into CMT3 at https://cmt3.research.microsoft.com. If you do not see “2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)” in the conference list already, click on the “All Conferences” tab and find it there.
通过https://cmt3.research.microsoft.com登录到CMT3。 如果您尚未在会议列表中看到“ 2021 IEEE / CVF计算机视觉和模式识别（CVPR）会议”，请单击“所有会议”选项卡，然后在此处找到它。
2) Author registration 作者注册
When you log in for the first time, you will be asked to set up a user profile and fill out a questionnaire. You will not be able to submit any paper without entering this information. At any time, you can update this information by clicking on your name in the upper-right and selecting “User information” under CVPR2021.
首次登录时，将要求您设置用户个人资料并填写调查表。 如果不输入此信息，您将无法提交任何论文。 您随时可以通过单击右上角的名称并选择CVPR2021下的“用户信息”来更新此信息。
It is the primary author's responsibility to ensure that all authors on their paper have registered on CMT3 and filled out the questionnaire.
主要作者应确保所有论文作者均在CMT3上注册并填写调查表
1. User profile: Here you can update the basic information on your CMT profile.
用户个人资料：您可以在此处更新CMT个人资料的基本信息。
2. Questionnaire: To judge if you are qualified and have matching expertise to review a paper, we ask you for additional information. We expect all authors to be willing to serve as reviewer. If for some reason you are not, we’d like you to motive this. We also need emergency reviewers who are willing to help us out at the last moment for papers that do not have a sufficient number of reviews yet. Our intention is that emergency reviewers will get fewer papers in the first round. If you are willing to serve as emergency reviewer, please indicate so. We also ask for a list of subject areas. Note that, at this stage, you should select the subject areas in which you feel comfortable to act as reviewer (the subject areas for the papers you plan to submit will be asked at a later stage). Please select exactly one topic as primary subject area andup to 10 topics as secondary subject area.
调查表：为了判断您是否有资格且具有相匹配的专业知识来审阅论文，我们要求您提供其他信息。 我们希望所有作者都愿意担任审稿人。 如果出于某些原因您不是，我们希望您也能够帮助我们寻找审稿人。 我们还需要紧急审稿人，他们愿意在最后一刻为我们提供帮助，以帮助审阅审稿人不够的论文。 我们计划让紧急审稿人在第一轮中收到较少的论文。 如果您愿意担任紧急审稿人，请注明。 我们还要求提供主题领域的列表。 请注意，在此阶段，您应该选择自己愿意担任审稿人的主题区域（稍后将询问您计划提交的论文的主题区域）。 请准确选择一个主题作为主要主题区域，最多选择10个主题作为次要主题区域。
3) Conflict information 冲突信息
Authors need to provide information on conflict domains. Each author should list domains of all institutions they have worked for, or have had very close collaboration with, within the last 3 years (example: mit.edu; ox.ac.uk; microsoft.com). DO NOT enter the domain of email providers such as gmail.com. This institutional conflict information will be used in conjunction with prior authorship conflict information to resolve assignments to both reviewers and area chairs. If a paper is found to have an undeclared or incorrect institutional conflict, the paper may be summarily rejected.
作者需要提供有关冲突域的信息。 每位作者都应列出过去三年来与之合作或密切合作的所有机构的域名（例如：mit.edu; ox.ac.uk; microsoft.com）。 不要输入电子邮件提供商的域名，例如gmail.com。 该机构冲突信息将与以前的作者冲突信息一起使用，以完成对审稿人和区域主席的指派。 如果发现论文存在未声明或不正确的机构冲突，则该论文可能会被立即拒绝。
4) Creating a paper submission 创建一个论文的提交
This step must be completed by the paper registration deadline. After this deadline, you will not be able to register new papers, but you will be able to edit the information for existing papers. While it will be possible to make minor edits to the title and abstract until the full paper submission deadline, submissions with “placeholder” abstracts which are rewritten entirely for the full submission may be removed without consideration. Note: we are allowing changes to the author list until the full paper deadline. After that, no changes will be permitted for any reason, including for the camera-ready version.
此步骤必须在论文注册截止日期之前完成。 在此期限之后，您将无法注册新论文，但是将能够编辑现有论文的信息。 尽管可以在论文全文提交截止日期之前对标题和摘要进行少量编辑，但是那些仅仅通过占位符来完成摘要的论文，即在完全提交前重写了摘要的论文可能会被移除(拒绝审稿)。 注意：我们允许在完整论文截止日期之前更改作者列表。但是之后，无论任何原因，包括相机就绪版本，都将不允许进行任何更改。
(a) Click the “+ Create new submission” button in the upper-left to create a new submission. There, you will be prompted to enter the title, abstract, authors, and subject areas. You are strongly encouraged to finalize the author list by the registration deadline.
单击左上角的“ +创建新提交”按钮以创建新提交。 在此处，将提示您输入标题，摘要，作者和主题区域。 强烈建议您在注册截止日期之前完成作者名单的确定。
(b) Check with your co-authors to make sure that: (1) you add them with their correct CMT3 email; and (2) they have logged in to the submission website and filled out the user information questionnaire and conflict information on CMT3. If you add an author with an email that is not in CMT3 and the name and organization is not automatically filled, that means they are not yet in the system, and you should make sure to check that they do not already have an account under a different email before completing the requested information to add them.
与您的合著者确认，以确保：（1）您用正确的CMT3电子邮件添加他们； （2）他们已经登录提交网站，并填写了有关CMT3的用户信息调查表和冲突信息。 如果您添加的作者的电子邮件不在CMT3中，并且名称和组织未自动填写，则表示他们尚未在系统中，因此您应该在提交信息并添加他们之前确保他们没有使用不同邮箱进行注册。
(c) Enter subject (topic) areas for your paper. You must include at least one primary area and up to 10 secondary areas. This information is used to help assign ACs and reviewers.
输入论文的主题（主题）区域。 您必须至少包含一个主要区域，最多10个次要区域。 此信息用于帮助分配区域主席和审稿人。
5) Paper Number 论文号
Once you have registered your paper (i.e. title/authors), you will be assigned a paper number. Insert this into the latex or word template before generating the pdf of your paper for submission. Papers submitted without a number may not be reviewed.
注册论文（即标题/作者）后，您将获得一个论文编号。 在生成要提交的论文pdf之前，将其插入到latex或Word模板中。 没有编号的论文不会被允许审阅。
6) Submission Requirements 提交要求
The maximum size of the abstract is 4000 characters.
摘要的最多4000个字符。
The paper must be PDF only (maximum 50MB). Make sure your paper meets the formatting and anonymity requirements described above.
论文仅包含一个pdf（最大50MB）。 确保您的论文符合上述格式和匿名要求。
The supplementary material can be either PDF or ZIP only (maximum 100MB).
补充材料只能是一个单独的pdf或zip，最大100MB.
7) Supplementary Material Submission 补充材料的提交
By the supplementary material deadline, the authors may optionally submit code and/or 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 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.
在补充材料的截止日期之前，作者可以选择提交代码和/或其他材料，这些代码和/或其他材料在论文提交时已经准备好，但是由于格式或空间的限制而无法包括在内。 作者应在论文中适当参考补充材料的内容。 我们将鼓励审稿人对此进行审查，但他们没有这样做的义务。
Supplementary material may include videos, proofs, additional figures or tables, more detailed analysis of experiments presented in the paper, code, or a concurrent submission to CVPR or 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. Make sure supplementary material does not reveal author identity. Papers with supplementary materials violating the guidelines may be summarily rejected.
补充材料可能包括视频，证明，其他图形或表格，对本文中呈现的实验进行更详细的分析，代码，或是同时提交给CVPR或其他会议的文章。 它不能包括其他数据集上的结果，使用提出方法的改进版本（例如，在进行附加参数调整或训练之后）或提交的PDF的更新或更正版本所获得的结果。 请确保补充材料不泄露作者身份。 补充材料违反指南的论文可能会被拒绝。
8) Code Submission and Reproducibility 代码提交和复现
To improve reproducibility in AI research, we highly encourage authors to voluntarily submit their code as part of supplementary material. Authors should also use the Reproducibility Checklist as a guide for writing reproducible papers. Reviewers are encouraged to check the submitted code to ensure that the paper’s results are trustworthy and reproducible. The code should be anonymized, e.g., author names, institutions and licenses should be removed. We do not expect authors to submit private/sensitive data, only sufficient data to demonstrate the method. All code/data will be reviewed confidentially and kept private.
为了提高AI研究的可重复性，我们强烈鼓励作者自愿将其代码作为补充材料的一部分提交。 作者还应使用“可复制性清单”作为编写可复制论文的指南。 鼓励审稿人检查提交的代码，以确保论文的结果值得信赖且可重复。 该代码应匿名，例如，应删除作者姓名，机构和许可证。 我们不希望作者提交私人/敏感数据，仅需提供足够的数据来证明该方法即可。 所有代码/数据将受到保密审查并保密。
Detailed supplementary material guidelines 补充材料提交说明
(a) All supplementary material must be self-contained and zipped into a single file. The following document and media formats are allowed: avi, mp4, pdf, wmv. CMT imposes a 100MB limit on the size of this file. Note that you can update the file by uploading a new one (after removing the previous version).
所有补充材料必须自成一体，并压缩成一个文件。 允许使用以下文档和媒体格式：avi，mp4，pdf，wmv。 CMT对此文件的大小施加100MB的限制。 请注意，您可以通过上传新文件（删除以前的版本后）来更新文件。
(b) The paper for review (PDF only) must be submitted first before the supplementary material (PDF or ZIP only) can be submitted.
在提交补充材料（仅PDF或ZIP）之前，必须先提交审稿纸（仅PDF）。
(c) Code can be submitted as part of the supplementary zip file or through anonymous Github repositories (include the link in a separate text file in the supplementary zip). The link should point to a branch that will not be modified after the submission deadline.
代码可以作为补充zip文件的一部分或通过匿名Github存储库（在补充zip中的单独文本文件中包含链接）提交。 该链接应指向在提交截止日期之后未被修改的branch。
Rebuttal Instructions 关于Rebuttal的说明
After receiving the reviews, authors may optionally submit a rebuttal to address the reviewers' comments, which will be limited to a one page PDF file using the "CVPR 2021 Rebuttal Template".
在收到审稿意见后，作者可以选择提交rebuttal以应对审稿人的意见，使用“ CVPR 2021 rebuttle模板”将其限于一页PDF文件。
The rebuttal must maintain anonymity and cannot include external links that reveal the author identity or circumvent the length restriction.
反驳必须保持匿名，并且不能包括外部链接以显示作者身份或规避篇幅限制。
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.
超过一页的回复将不会被审核。 这包括认为页边距和格式与样式指南指定的格式相比有显著变化的回复。
The author rebuttal is optional and is meant to provide you with an opportunity to rebut factual errors or to supply additional information requested by the reviewers. It is NOT intended to add new contributions (theorems, algorithms, experiments) that were absent in the original submission and NOT specifically requested by the reviewers. You may optionally add a figure, graph or proof to your rebuttal to better illustrate your answer to the reviewers' comments.
作者的rebuttal是可选的，旨在为您提供反驳审稿人认为的错误或提供审阅者要求的其他信息的机会。 它并不应该添加原始提交中没有的且审稿人未特别要求的新贡献（定理，算法，实验）。 您可以选择在反驳中添加图形，图表或证明，以更好地说明您对审稿人的意见的回答。
Per a passed 2018 PAMI-TC motion, reviewers should not request additional experiments for the rebuttal, or penalize authors for lack of additional experiments. This includes any experiments that involve running code, e.g., to create tables or figures with new results. Examples of such experiments are ablation studies, new baseline results (unless already reported elsewhere), results with additional hyperparameters, or results on new datasets. Authors should not include new experimental results in the rebuttal, and reviewers should discount any such results when making their final recommendation. These also include experiments that were run by authors before the submission deadline but were not included either in the paper or the supplementary material.
根据2018年通过的PAMI-TC议案，审稿人不应要求作者进行额外的实验，也不应因缺乏额外的实验而对作者进行惩罚。 这包括任何涉及运行代码的实验，例如创建具有新结果的表或图形。 这样的实验的例子包括消融实验，新的baseline的结果（除非在其他地方已有报道），带有其他超参数的结果或新数据集的结果。 作者不应在rebuttle中包括新的实验结果，审稿人在做出最终推荐时应不予考虑任何此类结果。 这些还包括作者在提交截止日期之前进行的实验，但未包含在论文或补充材料中。
Should any evidence of new experiments be found in the rebuttal, the reviewers and Area Chairs have the right to disregard the entire rebuttal. We will encourage ACs/reviewers to ignore rather than penalize additional results if they are reported by authors. ACs are expected to monitor reviewers to make sure authors are not penalized for lack of additional results, even if reviewers asked for them.
如果在驳回中发现任何新实验的证据，则审稿人和区域主席有权无视整个驳回。 如果作者给出了了额外的结果，我们将鼓励区域主席 /审稿人选择忽略而不是惩罚额外的结果。 区域主席将会监督审稿人，以确保作者不会因缺少其他结果而受到处罚，即使审稿人要求他们也是如此。
Author FAQs 常见问题
About Submitting Papers 关于论文提交
Q. Can we please have an extension on the deadline?
我们可以延长dll吗？
A. NO. And any incomplete submission or a submission not meeting required criteria will be deleted.
不行，任何不完整的提交或不符合要求的提交将被删除。
Q. Can we get my quota increased for the size of paper submission from 50 MB to something higher?
我们可以将论文提交的配额从50 MB增加到更高吗？
A. NO. We have set hard limits of 50MB (PDF Only) for paper submission and 100MB (PDF or ZIP only) for supplementary materials for submissions for review. As we are expecting many submissions, and as each reviewer is expected to review multiple papers, larger file downloads (and uploads) will tax the system and abilities of reviewers to get to the papers fast enough. Authors should consider adding hi-res images as supplementary material (see supplementary material guidelines).
不行。 对于paper的提交，我们将硬限制设置为50MB（仅PDF），对于补充材料，我们将硬限制设置为100MB（仅PDF或ZIP）。 正如我们期望的那样，有很多投稿，而且每个审稿人都需要审阅多篇论文，较大的文件下载（和上载）将使审稿人的系统和能力加重，使其无法足够快地提交论文。 作者应考虑添加高分辨率图像作为补充材料（请参阅补充材料准则）。
Q. How do I delete Supplementary Material from the CMT site?
如何从提交网址上删除补充材料？
A. After you log in, in the "Author" console, you'll notice "Upload/Delete File" at the end of the supplementary file name. Click on that, and in the page that appears, you can click on the "Delete" button to remove the supplementary file. (Please note that you will not be able to delete the supplementary file after the supplementary material deadline.)
登录后，在“作者”控制台中，您会在补充文件名的末尾看到“上传/删除文件”。 单击该按钮，然后在出现的页面中，单击“删除”按钮以删除补充文件。 （请注意，在补充材料截止日期之后，您将无法删除该补充文件。）
Q. Can we submit color images with our papers for review?
审稿时可以使用彩色图像吗？
A. YES. Reviewers will get the exact pdf file of the paper you submitted, so they can see the color images on the screen. Do be warned though that many reviewers still like to read printed papers and not all have access to high-end color printers. Please make sure to comment in the paper to request the reviewers to see the color online copy.
可以。 审稿人将获得您提交的论文的pdf文件，因此他们可以在屏幕上看到彩色图像。 请注意，尽管许多评论家仍然喜欢阅读打印的论文，但并非所有人都可以使用高端彩色打印机。 请确保在论文中进行评论？，以要求审稿人在线查看颜色。
Q. What is CVPR 2021 policy on DUAL SUBMISSIONS?
CVPR 2021关于双重提交的政策是什么？
A. Please read the dual/double submission paragraph above.
请阅读上方的 dual/double submission段落。
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 CVPR 2021?
在线提供的技术报告（departmental，arXiv等）是否可以算作先前的出版物，因此它不符合CVPR 2021的审阅和发布要求吗？
A. Please read the dual/double submission paragraph above.
请阅读上方的 dual/double submission段落。
Q. Does a document on GitHub or other open repositories count as a publication, and therefore is ineligible for review and publication at CVPR 2021?
GitHub或其他开放存储库上的文档是否算作出版物，因此没有资格在CVPR 2021上进行审核和发布？
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/double 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.
GitHub和类似存储库的提交将不会被拒绝。在此类平台上进行任何“审阅”之前，默认接受这些提交。 结合dual/double submission段落中的定义，GitHub文档不是出版物，也不会被视为出版物。 为了保持匿名，您不应该引用公共代码库。 您可以说该代码将公开提供。
Q. Does a presentation at a departmental seminar during the review period violate the anonymity standard or other CVPR 2021 policy?
审稿期间在部门内部研讨会上的演示是否违反匿名标准或其他CVPR 2021政策？
A. NO. Authors must properly anonymize the written submission as per the guidelines. There is no requirement that the material otherwise be kept confidential during the review process.
不违反。 作者必须按照指南正确匿名化书面意见。 不需要在审核过程中以其他方式对材料保密。
Q. Can I promote my paper in the press or on social media?
我可以在新闻或社交媒体上宣传我的论文吗？
A. As stated in the instructions above, authors are not allowed to go to the press with their submission prior to the end of the review process, or to advertise their work on social media while explicitly identifying it as an CVPR submission. In recent conference cycles, some authors were found posting about their submissions on Twitter or other social media, and even including the title or a snapshot of the paper. This is a violation of anonymity, since the message may go out to many potential reviewers.
如上述说明所述，不允许作者在审稿过程结束前将稿子去媒体，或在社交媒体上做广告宣传且明确将其视为CVPR稿件。 在最近的会议周期中，发现一些作者在Twitter或其他社交媒体上发布了有关其提交的文章，甚至包括论文的标题或快照。 这是对匿名的侵犯，因为该消息可能会发给许多潜在的审稿人。
Authors must not:
- Talk to the media about your work as "in submission to CVPR"
- Make any posts to social media or elsewhere that can be linked to a specific CVPR submission (e.g., mentioning the title of the submission or details and content and saying that it's an CVPR submission)
作者不得：
- 以“提交CVPR”的形式与媒体谈论您的工作
- 在社交媒体或其他地方发布任何可以链接到特定CVPR提交的帖子（例如，提及该提交的标题或详细信息和内容，并说这是CVPR提交）
Authors may:
- Talk about their work in a presentation without saying it's submitted to CVPR
- Submit to arXiv without mentioning CVPR
但您可以
- 在演示中谈论他们的工作，而不说已提交给CVPR
- 提交给arXiv时不提及CVPR
A paper may be rejected if the program chairs feel that the authors have attempted to let potential reviewers know who wrote the paper.
如果程序主席认为作者试图让潜在的审稿人知道谁撰写了该论文，则该论文可能会被拒绝。
Q. How do I cite my results reported in open challenges?
如何引用我在公开比赛中的结果？
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.
为了符合双盲审政策，您可以在报告中报告其他挑战参与者的结果以及您的结果。 但是，为了获得结果，您不应该表明自己的身份，也不应提及您对挑战的参与。 相反，请参考论文中提出的方法介绍您的结果，并根据与其他结果的实验比较得出结论。
Q. Does my submission need to cite arXiv papers that are related to my work?
我的投稿是否需要引用与我的工作相关的arXiv论文？
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.
根据良好的学术习惯相，您需要引用所有启发并启发您自己工作的资料。 这就是说，要求作者将其工作与提交截止日期前不久出现的arXiv报告进行全面比较，但这也会给工作人员带来了不合理的负担。 我们也不希望阻止独立或同时提出的相似工作的出版。 作者和审稿人应牢记以下准则：
- 尽管作者必须恰当地引用那些启发他们的文章，但他们并不需要将他们的工作与最新的arXiv报告进行讨论和比较。
- 为了减少混乱，每当引用最初出现在arXiv上的论文时，作者应检查这些论文随后是否在同行评审的场所发表，并相应地引用这些版本。
- 未能引用arXiv中的论文或未能超越其性能不应是拒绝论文的唯一理由。
- 审稿人不应仅仅因为arXiv上出现了另一种具有类似想法的论文而拒绝发表论文。 如果审稿人怀疑抄袭或学术不诚实，则应鼓励将这些问题向地区和程序主席报告。
- 审稿人建议作者承认arXiv上的某些内容是可以接受的。
About the Review Process 关于审稿过程
Q. Is the CVPR 2021 Review Process CONFIDENTIAL?
CVPR 2021审核过程是否保密？
A. YES, CVPR 2021 Reviewing is considered confidential. All reviewers are required to keep every manuscript they review as confidential documents and not to share or distribute materials for any reason except to facilitate the reviewing of the submitted work.
是的，CVPR 2021审核被视为机密。 所有审稿人都必须将其审阅的每份手稿都保留为机密文件，不得出于任何原因共享或分发材料，除非是为了便于审阅提交的作品。
Q. Are CVPR 2021 Reviews Double BLIND or Single BLIND?
CVPR 2021评论是双盲还是单盲？
A. CVPR reviewing is Double BLIND, in that authors do not know the names of the area chair/reviewers of their papers, and area chairs/reviewers do not know the names of the authors. Please read Section 1.6 of the example paper egpaper_for_review.pdf for detailed instructions on how to preserve anonymity. Avoid providing information that may identify the authors in the acknowledgments (e.g., co-workers and grant IDs) and in the supplemental material (e.g., titles in the movies, or attached papers). Avoid providing links to websites that identify the authors. Violation of any of these guidelines will lead to rejection without review.
CVPR审稿是Double BLIND，因为作者不知道其论文的区域主席/审稿人的姓名，并且区域主席/审稿人不知道作者的姓名。 请阅读示例论文egpaper_for_review.pdf的1.6节，以获取有关如何保留匿名性的详细说明。 避免在致谢（例如，同事和授权ID）和补充材料（例如，电影中的标题或随附的论文）中提供可识别作者身份的信息。 避免提供指向标识作者的网站的链接。 违反这些准则中的任何准则都将导致拒绝，而不再进行审稿。
About Code Submission 关于代码提交
Q. Is code submission required?
是否需要提交代码？
A. No, it is completely optional.
不，它是完全可选的。
Q. Does submitted code need to be anonymized?
提交的代码需要匿名吗？
A. CVPR is a double blind conference, so authors should make a reasonable effort to anonymize the submitted code and data. This means that author names, institution names and licenses should be removed. If the paper gets accepted, we expect the authors to replace the submitted code by a non-anonymized version or link to a public github repository.
CVPR是一次双盲会议，因此作者应做出合理的努力来匿名化所提交的代码和数据。 这意味着应删除作者姓名，机构名称和许可证。 如果论文被接受，我们希望作者将提交的代码替换为非匿名版本或链接到公共github存储库。
Q. Are anonymous github links allowed?
是否允许匿名github链接？
A. Yes. However, they have to be on a branch that will not be modified after the submission deadline. Please enter the github link in a standalone text file in a submitted zip file.
是。 但是，它们必须位于提交截止日期之后不会被修改的分支上。 请在提交的zip文件的独立文本文件中输入github链接。
Q. How will the submitted code be used for decision-making?
提交的代码将如何用于决策？
A. The submitted code will be used as additional evidence provided by the authors to add more credibility to their results. We anticipate that high quality papers whose results are judged by our reviewers to be credible will be accepted to CVPR, even if code is not submitted. However, if something is unclear in the paper, then code, if submitted, will provide an extra chance for reviewers to verify it.
提交的代码将被视为作作者提供的其他证据，以提高结果的可信度。 我们预计，即使未提交代码，但其审稿人认为其结果可信的高质量论文也将被CVPR接受。 但是，如果论文中有不清楚的地方，则代码（如果已提交）将为审阅者提供额外的机会进行验证。
Q. If code is submitted, do you expect it to be published with the rest of the supplementary? Or, could it be withdrawn later?
如果提交了代码，您是否希望它与其余的补充文件一起发布？ 还是可以在以后撤回？
A. We expect submitted code to be published with the rest of the supplementary. However, if the paper gets accepted, then the authors will get a chance to update the code before it is published by adding author names, licenses, etc.
我们希望提交的代码将与其他补充材料一起发布。 但是，如果论文被接受，那么作者将有机会通过添加作者姓名，许可证等在代码发布之前对其进行更新。
Q. Do you expect the code to be standalone? For example, what if it is part of a much bigger codebase?
您希望代码是独立的吗？ 例如，如果它是更大的代码库的一部分，该怎么办？
A. We expect your code to be readable and helpful to reviewers in verifying the credibility of your results. It is possible to do this through code that is not standalone -- for example, with proper documentation.
我们希望您的代码具有可读性，并有助于审阅者验证结果的可信度。 可以通过非独立的代码来实现此目的-例如，使用适当的文档。
Q. What about pseudocode instead of code? Does that count as code submission?
伪代码而不是代码呢？ 可以当作代码提交吗？
A. Yes, we will count detailed pseudocode as code submission as it is helpful to reviewers in validating the credibility of your results.
是的，我们会将详细的伪代码视为代码提交，因为这有助于审阅者验证结果的可信度。
Q. Do you expect authors to submit data?
您希望作者提交数据吗？
A. We understand that many of our authors work with highly sensitive datasets, and are not asking for private data submission. If the dataset used is publicly available, there is no need to provide it. If the dataset is private, then the authors can submit a toy or simulated dataset to illustrate how the code works.
我们了解许多作者使用高度敏感的数据集，因此我们不要求提交私人数据。 如果使用的数据集是公开可用的，则无需提供它。 如果数据集是私有的，那么作者可以部分或模拟数据集以说明代码的工作方式。
Q. Who has access to my code? For how long?
谁可以访问我的代码？ 有效期多久？
A. Only the Program Chairs, the Technical Chairs, and the reviewers and Area Chair assigned to your paper will have access to your code. We will instruct reviewers and Area Chair to keep the code submissions confidential (just like the paper submissions), and delete all code submissions from their machine at the end of the review cycle. Please note that code submission is also completely voluntary.
只有分配给您论文的程序主席，技术主席以及审稿人和区域主席才能访问您的代码。 我们将指示审稿人和区域主席对代码提交保密（就像论文提交一样），并在审阅周期结束时从其计算机中删除所有代码提交。 请注意，代码提交也是完全自愿的。
Q. I would like to revise my code/add code during author feedback. Is this permitted?
我想在作者反馈期间修改我的代码/添加代码。 可以吗？
A. Unfortunately, no. But please remember that code submission is entirely optional.
很不幸的是，不行。 但是请记住，代码提交完全是可选的。
扫一扫
4022
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
