Author Information

We follow closely the BMVC 2015 formatting and submission guidelines, however using an adapted template and different webpage on the CMT paper submission site.

Format Instructions

Please refer to the following files for detailed formatting instructions.

CVPPP 2015 author kit (ZIP file format, LaTeX and Word)
CVPPP 2015 style guide (example PDF)

A complete paper should be submitted using the above templates, which are blind-submission review-formatted templates.

Papers with more than 9 pages (excluding references) will be rejected without review.

Please note: We offer double blind reviewing and strongly encourage authors to adhere to the guidelines outlined in the example PDF above. However, in some cases keeping anonymity may be hard to do and not reasonable. E.g. for a data sharing paper an external link may be needed to give access to data sets that cannot be provided as supplemental material (>10MB). This is allowed and not considered a violation.

Instructions on online paper submission

Step 1: Create a user account on the CMT paper submission site

Please follow this link to sign up as a new user on CMT.
Make sure that your browser has cookies and Javascript enabled.
Please add “cmt@microsoft.com” to your list of safe senders (whitelist) to prevent important email announcements from being blocked by spam filters.
Fill in your contact information. You can edit your contact information at any time (see item near the top right in the submission site). Don’t forget to click the “Update” button to save the edited information.
Note: If you have generated an account (or if an account has been generated for you, e.g. as a CVPPP reviewer) and have forgotten your password, just click on “Reset your password”. Instructions will be emailed to you.

Step 2: Enter the domain of ONLY your current institution

The first time you log on to CMT you will be asked to enter your “Conflict Domains”.
Please only enter the domain of the academic department or institution where you currently work or study (example: cs.toronto.edu). If you worked or studied at more than one institution in the past year, please enter the domain of each institution separated by semicolons (example: cs.washington.edu; microsoft.com).
If your institution is a university, please enter the domain of your academic department rather than the whole university (i.e., enter cs.washington.edu rather than washington.edu)
DO NOT enter the domain of your email provider such as gmail.com, yahoo.com, hotmail.com, 163.com as your institution domain.

For each paper you want to submit, do the following:

Step 3: Enter a title and abstract

Click on the link “Create a new Paper Submission”. You will then be asked for the paper title and abstract. Your title can be up to 256 characters in length. The maximum size of the abstract is 4000 characters.
You can edit the title and abstract at any time up to the submission deadline.

Step 4: Add your co-authors

If your submission has co-authors, you will need to associate them with your submission:

Check with your co-authors if they already have an CVPPP 2015 account on CMT. If so, please make sure you enter the email address that corresponds exactly to their account name. It is important that each person uses exactly one account as author, reviewer, or area chair for CVPPP 2015. This will ensure that they can see your submission when they log onto CMT and allow us to handle conflicts appropriately.
Only if a co-author does not have an CVPPP 2015 account you should create an account: If the email address you enter does not correspond to an existing CMT account for CVPPP 2015, you will be asked to enter your co-author’s information (name, institution, etc.).

Step 5: Select one primary subject area for your paper

Select the most appropriate subject area from the list.

Step 6: Select up to three secondary subject areas

Your primary subject area cannot be selected as a secondary subject area.

You should not upload a file at this stage yet.

Step 7: Include your paper ID

Once you have registered your paper (i.e. title, subject areas, etc), you will be assigned a paper ID by CMT. Insert this ID into the latex template before generating the PDF of your paper for submission.

Step 8: Upload your paper’s PDF

Paper formatting instructions can be found in the body of the example paper found here.
Only PDF files are accepted (maximum size 10MB).
Make sure that your paper’s ID appears on every page in the PDF.

Step 9: Optionally upload a supplementary materials file

The CVPPP 2015 policy on supplementary materials can be found below.
Only one PDF or ZIP file is accepted with a maximum size of 10MB.
You can update this file by uploading a new one (the old one will be deleted and replaced) until the submission deadline.
The paper for review (PDF only) must be uploaded before the supplementary material (PDF or ZIP only) can be uploaded.

Instructions on supplemental material

Authors may optionally upload supplementary material (up to 10MB) which may include:

sample data for Dataset Sharing and Problem Definition papers. Please contact sotirios.tsaftaris@imtlucca.it or h.scharr@fz-juelich.de if you need to upload large files (>10MB).
videos to showcase results/demo of the proposed approach/system,
images and other results in addition to the ones in the paper,
anonymized related submissions to CVPPP or other conferences and journals, and
appendices or technical reports containing extended proofs and mathematical derivations that are not essential to the understanding of the submitted paper.

CVPPP encourages authors to submit videos using an MP4 codec such as DivX contained in an AVI. Also, please submit a README text file with each video specifying the exact codec used and a URL where the codec can be downloaded.

Authors should refer to the contents of the supplementary material appropriately in the paper. Note that reviewers will be encouraged to look at it, but are not obligated to do so. Please note that:

All supplementary material must be self-contained in a single file for upload (i.e., a single pdf, or a zip file containing multiple items).
The supplementary material directly supports the paper as submitted prior to the paper deadline. Only results generated by the algorithm/approach/system reported in the submitted version are allowed. Material based on improvements subsequent to the paper deadline is not allowed.
DO NOT submit a newer version of the paper as supplementary material. Including a newer version of the paper or any portion thereof is forbidden.

Type of Submissions

Computer Vision Solutions to Plant Phenotyping: We invite authors to present unique computer vision approaches, or adaptations of current state of the art methods in computer vision, to solve plant phenotyping problems (segmentation, tracking, etc). Authors are encouraged to provide accurate description of dataset acquisition as well as appropriate problem definitions both from a computer vision and a phenotyping aspect. Papers will be evaluated based on originality and content quality. All accepted papers will appear in the proceedings. Authors are encouraged to share the code of their implementations.

Challenges: We invite authors to address the leaf segmentation and leaf counting challenges in their paper.

Open source implementations, comparison and evaluation of existing methods: We invite authors to present implementations, comparisons and evaluations of existing methods, as well as novel annotation tools. Papers will be evaluated based on originality and content quality. A link to the publicly available code must be made available at the time of camera-ready submission. All accepted papers will appear in the proceedings.

Dataset Sharing and Problem Definition: Authors are invited to submit papers describing datasets and their acquisition. Goal of these paper is to enable computer vision experts to work on plant phenotyping applications. Therefore such papers need to specify what data is available and have CLEAR definition of what is an appropriate annotation. This category is NOT about opinion papers. The papers must include an accurate problem definition (both from a computer vision and phenotyping perspective), describe appropriate evaluation criteria, preferably also in code or pseudo-code, and ground truth and other metadata. The papers must describe the data format, and must specify any usage restrictions. The authors could describe previous algorithmic attempts (if any) and findings in solving the problem, if available. A sample of the shared data must be made publicly available at the time of submission to allow for review. Ideally, please upload it as supplemental material, if possible. Please contact sotirios.tsaftaris@imtlucca.it or h.scharr@fz-juelich.de if you need to upload large files (>10MB). Upon acceptance and submission of the camera ready, the complete dataset must be made publically available (at authors’ responsibility of hosting).

Papers will be evaluated for the content, the uniqueness and challenge of the problem from a computer vision viewpoint, and data quality and data sharing policy. Accepted papers will be presented either orally or in a poster session, and will appear in the proceedings. A superset of the submitted data may be packaged and hosted at a mirror location (to be announced at the workshop). A jointly authored journal paper may be invited describing the datasets made available (to be announced at the workshop).