Call For Papers

Submission Details

The Submission Deadline has been extended to December 22nd, 2019 at 11:59pm PST

We call for papers of three categories: Contributed Papers, Extended Abstracts, and Proposals. All submissions should be in PDF format.

Contributed Papers will be published as part of the "WACV Workshop Proceedings" and should, therefore, follow the same guideline as the main conference. Paper submission guidelines of WACV can be accessed here.

Extended Abstracts can be up to 4 pages in length, references not included. This option is meant to provide a non-archival submission option for previously published work, or work that is intended to be published at a future venue. Supplementary appendices are allowed but will be read at the discretion of the reviewers.

Proposals can be up to 2 pages in length, references not included. This option is intended to provide a venue for experts to suggest new re-identification projects to the computer vision community for discussion or to develop collaborations. Providing new data is desired but not required.

All accepted submissions across the three categories will be invited to give poster presentations.

From those accepted, a select few will be invited to give spotlight talks.

Submission to this workshop does not preclude future publication, and previously published relevant work may be submitted.

Contributed Papers

We invite contributed papers intended for peer-reviewed publication in the WACV Workshop Proceedings. Submissions for the contributed papers track should describe projects relevant to animal re-id that involve computer vision or machine learning. These may include (but are not limited to) academic research; deployed results from startups, industry, public institutions, nonprofits, etc.; and new animal re-id datasets. Submissions should provide experimental or theoretical validation of the method presented, as well as specifying what gap the method fills. Algorithms need not be novel from a computer vision perspective if they are applied in a novel domain. Details of methodology need not be revealed if they are proprietary, though transparency is highly encouraged. Submissions publishing novel datasets are welcomed. Datasets should be designed to permit machine learning research (e.g. formatted with clear benchmarks for evaluation). In this case, baseline experimental results on the dataset are preferred, but not required.

Extended Abstracts

We invite extended abstracts not intended for archival publication that are currently in progress, have been previously published, and/or have been deployed. Submissions for the extended abstracts track should describe projects relevant to animal re-id that involve computer vision or machine learning. These may include (but are not limited to) academic research; deployed results from startups, industry, public institutions, nonprofits, etc.; and new animal re-id datasets. Submissions should provide experimental or theoretical validation of the method presented, as well as specifying what gap the method fills. Algorithms need not be novel from a computer vision perspective if they are applied in a novel domain. Details of methodology need not be revealed if they are proprietary, though transparency is highly encouraged. Submissions publishing novel datasets are welcomed. Datasets should be designed to permit machine learning research (e.g. formatted with clear benchmarks for evaluation). In this case, baseline experimental results on the dataset are preferred, but not required.

Proposals

We invite proposals not intended for archival publication with detailed descriptions of current problem statements and ideas for how machine learning may be used in future work. Submissions for the Proposals should describe detailed ideas for how computer vision and general machine learning can be used to solve problems related to animal re-id. While no results need to be demonstrated, proposals will be subject to a very high standard of review. The ideas should be justified as extensively as possible, including motivation for why the problem being solved is important, discussion of why current methods are inadequate, and explanation for how machine learning may provide a solution. We encourage difficult but concise problem statements, that currently seem to have to solution with traditional methods.