Learning From Unlabeled Videos

CVPR 2019 Workshop

Long Beach, CA

Sunday June 16, 2019

Overview

Deep neural networks trained with a large number of labeled images have recently led to breakthroughs in computer vision. However, we have yet to see a similar level of breakthrough in the video domain. Why is this? Should we invest more into supervised learning or do we need a different learning paradigm?

Unlike images, videos contain extra dimensions of information such as motion and sound. Recent approaches leverage such signals to tackle various challenging tasks in an unsupervised/self-supervised setting, e.g., learning to predict certain representations of the future time steps in a video­­ (RGB frame, semantic segmentation map, optical flow, camera motion, and corresponding sound), learning spatio-­temporal progression from image sequences, and learning audio­visual correspondences.

This workshop aims to promote comprehensive discussion around this emerging topic. We invite researchers to share their experiences and knowledge in learning from unlabeled videos, and to brainstorm brave new ideas that will potentially generate the next breakthrough in computer vision.

News and Updates

  • March 14, 2019: Updated author guidelines. Papers should be at most 4 pages *including references*. Papers that exceed 4 pages will count as a publication and could potentially violate the dual submission policy at other conferences
  • March 9, 2019: Due to multiple requests, we are extending the paper submission deadline to April 15, 2019
  • Feb 11, 2019: CMT website is open for submission: https://cmt3.research.microsoft.com/LUV2019

Call For Papers

We invite submissions of 2-4 page extended abstract *including references* in topics related to (but certainly not limited to):

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

We will accept papers that have not been published elsewhere, or have been recently published elsewhere including CVPR 2019. Accepted papers will not appear in CVPR proceedings. We would instead encourage authors of accepted papers to post their papers to arxiv; we will provide links on this workshop website.

All submissions will be handled electronically via the workshop's CMT Website. Papers are limited to four pages, including figures and tables and references; no additional pages are allowed. Please refer to the Author Guidelines for detailed instructions on formatting and review polity.

Important Dates

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

  • Paper submission: Monday, March 4, 2019 Monday, April 15, 2019 (EXTENDED)
  • Notification to authors: Monday, April 1 2019 Monday, May 13

Invited Speakers

Organizers