Call for Papers

Important Dates:

  • Paper submission deadline: March 14th, 2020 (23:59 PST) March 21st (23:59 PST)
  • Notification to authors: April 2nd, 2020
  • Camera-ready deadline for archived papers: April 9th, 2020 (23:59 PST) April 12th, 2020 (23:59 PST)
  • Camera-ready deadline for non-archived papers: April 20th, 2020 (23:59 PST) April 24th, 2020 (23:59 PST)

Topics:

We invite original contributions on the topic of visual learning with limited labels. Topics of interest include, but are not limited to:

  • Zero-shot learning
  • Few-shot learning for X (image classification, object detection, segmentation, pose estimation, etc.)
  • Any-shot learning – transitioning gracefully between few-shot, mid-shot, and many-shot training
  • Unsupervised/Semi-supervised/Weakly-supervised/Self-supervised learning
  • Cross-domain few-shot learning
  • Domain Adaptation
  • Learning in the “long-tail” scenario – supporting a large variety of categories with different number of training examples

Submission Guidelines:

Authors have two options for submission: 1) Non-archived Extended Abstracts or 2) Archived Papers, as detailed below.

Non-archived Extended Abstracts. The minimum page limit is two pages and the maximum is four pages (including references). We encourage submission of work in progress and work that has been previously published (e.g., at the main CVPR 2020 conference) on relevant topics of the workshop. Note that these submissions cannot be indexed or published in the proceedings. For authors who want to submit their accepted work at this workshop to a different journal or conference, please check their double submission policy.

Archived Papers. Authors have the option to publish their accepted work at the CVPR workshop proceedings. If you choose to publish your paper in the CVPR workshop proceedings, the work should be original and four pages long (excluding references).

Accepted papers (archived or non-archived) will be presented at the poster session and a few of them selected for oral presentation. One paper will be awarded as the best paper. Manuscripts should follow the CVPR 2020 paper template and should be submitted through the CMT link below.

Paper submission Link: https://cmt3.research.microsoft.com/CVPRVL3W2020

Review process: single-blind (i.e., submissions need not be anonymized)