ICCV 2007

Eleventh IEEE International Conference on Computer Vision

Rio de Janeiro, Brazil, October 14-20, 2007

Please follow the instructions below when submitting a paper.

The submission web site has been closed.


This year there will be significant changes in the handling of the reviewing process.

This is motivated by the recent explosive growth in paper submissions to ICCV which has put a serious strain on the community's ability to recruit a sufficiently large number of experienced and qualified reviewers. Many of these submitted papers are way below the ICCV standards and yet filtering them out requires a very large program committee which undoubtedly introduces fluctuations in the reviewing quality.

This year we will introduce a two-phase review process. In the first phase each paper will be assigned automatically and will be reviewed by 10 reviewers who will be required only to score - not to write a review - based on a set of guiding criteria. A cut-off on the score statistics will be used in order to filter out and reject a significant number of papers which are clearly not ready for publication. We aim at leaving approximately 500- 800 papers for the second phase.

We encourage the submission of both Systems and Regular papers.

A regular paper is one that can possibly contain a theory, algorithm/s and associated experiments and possibly some experimental comparisons. A systems paper primarily contains experimental work possibly involving a novel combination of known algorithms applied to either a well studied domain or a novel domain. We encourage the submission of both Systems and Regular papers.

Here is how a reviewer will base his/her decision in Phase 1. It also clarifies what is the expected content and contribution for systems and regular papers.

For a Systems Paper:

  1. The level of contribution for a Systems paper:
    a) Does it provide a novel application or a novel capability in a known application?
    b) Is there enough novelty and complexity in putting together the parts of the system and/or the parts themselves?

  2. Clarity of the presentation

For a Regular Paper:

  1. Level of novelty in terms of theory/algorithms/approach.

  2. Meaningful and/or novelty of experiments and findings. If applicable comparison to the state of the art in this area.

  3. Clarity of presentation.

The summary page only helps a reviewer to quickly understand what is the paper about, but not to base his/her decision in phase 1 or 2.

Author Kit

Please refer to the following files for detailed formatting instructions:


Summary page: Due to the new two-phase review process, every submitted paper must have a single summary page as shown in egpaper_for_review.pdf, and also included in the LATEX/Word templates above. Papers without a summary page will be automatically rejected.


Paper length: A complete paper should be submitted in camera-ready format. The length should match that intended for final publication. Papers accepted for the conference will be allocated 6 pages in the proceedings, with the option of purchasing up to 2 extra pages for $100 per page (to be paid after paper acceptance at the time of registration for the conference.) So, if you are unwilling or unable to pay the extra charge you should limit yourself to 6 pages. Otherwise the page limit is 8 pages. When you submit camera-ready copy of your paper, please make sure you DON'T include the summary page.


Double blind review: ICCV reviewing is double blind: 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.pdf for detailed instructions on how to preserve anonymity. Also remember to avoid information that may identify the authors in the acknowledgements (e.g. co-workers and grant IDs) and in the supplemental material (e.g. titles in the movies, or attached papers.)


Dual submission: By submitting a manuscript to ICCV 2007, the authors assert that it has not been previously published in substantially similar form. Furthermore, no paper which contains significant overlap with the contributions of this paper either has been or will be submitted during the ICCV 2007 review period to either a journal or a conference (not including ICCV 2007 workshops).

If there are any papers that may appear to the reviewers to violate this condition, then it is your responsibility to (1) cite these papers (preserving anonymity as described in Section 1.6 of the example paper egpaper.pdf), (2) argue in the body of your paper why your ICCV paper is nontrivially different from these concurrent submissions, and (3) include anonymized versions of those papers in the supplemental material.

For ICCV 2007 we allow double submissions to ICCV workshops and the main conference. In case of acceptance, the author will have to decide where the paper should appear (main conference or workshop).

After phase 1 the papers which will not make it to phase 2 can be submitted to other conferences such as ACCV'07. However, those papers which will go to phase 2 can't be submitted to another conference or journal and should abide by the dual submission policy stated above.

Supplemental Material: Authors may optionally upload supplemental material. Typically, this material might include videos of results that cannot be included in the main paper, anonymized related submissions to other conferences and journals, and appendices or technical reports containing extended proofs and mathematical derivations that are not essential for understanding of the paper. Note that the contents of the supplemental material should be referred to appropriately in the paper and that reviewers are not obliged to look at it.

All supplemental material must be zipped or tarred into a single file. There is a 30MB limit on the size of this file. The deadline for supplemental material is April 13th, 11:59pm, EST.