Submission

Call for Submission

We invite submissions in topics related to (but certainly not limited to):

  • Unsupervised and self-­supervised learning with unlabeled videos
  • Cross-­modal self­-supervision (vision and sound, vision and language)
  • Video (future frame) prediction and generation
  • Unsupervised visual concept discovery from videos
  • Unsupervised visual representation learning
  • Learning from noisy web videos
  • Learning for actively acquired videos

We accept submissions of both (1) unpublished work and (2) published/accepted work. We have different processes for these two types of submissions. Please read below carefully. If anything is unclear, please reach out to yalesong@microsoft.com

  1. Unpublished work: These are papers that have not been previously published or accepted for publication in a substantially similar form. These also include papers that are currently under review at another venue such as ICML 2020 and ECCV 2020.
  2. Published work: These are papers that have been published or accepted for publication in a recent venue including journals, conferences, and other workshops. This case also includes papers that will appear at ICLR 2020 and CVPR 2020.

Publication format: All accepted papers will NOT appear in IEEE/CVF CVPR proceedings. For accepted papers submitted as "unpublished work", we encourage authors to post their papers to arxiv and share the links with us; we will provide the links on the workshop website.

Presentation format: Following LUV 2019, all papers will be presented during the poster sessions, and a few selected papers will also be presented during the oral sessions. Oral decisions will be made based on the significance of the work, not based on whether they are unpublished/published elsewhere.


Important Dates

All deadlines are due by 11:59 p.m. Pacific Standard Time on the listed dates.

  • Paper submission: Friday, April 10, 2020. Friday, May 1, 2020
  • Notification to authors: Monday, May 11, 2020. Monday, May 18, 2020

Submission Instruction

CMT Website: https://cmt3.research.microsoft.com/LUV2020

All submissions will be handled electronically via the workshop's CMT Website.

  1. Unpublished work: Papers are limited to 4 pages, including figures, tables, references, and appendices. No additional pages are allowed. The papers will be reviewed by the Program Committee in a double-blind manner. Therefore, authors should properly anonymize their papers. Please refer to the CVPR style for detailed formatting instructions. The reviews will be released to the authors via CMT.
  2. Published work: Authors should submit their accepted papers as they will appear in other venues. There is no need to anonymize or change the format to follow the CVPR 2020 template. These papers will be lightly reviewed by the Organizers (not by the Program Committee).

Authors should indicate whether the paper is unpublished work or published work in the CMT submission form.