L3D-IVU - CVPR2022

Workshop on Learning with Limited Labelled Data

for Image and Video Understanding

20th June, 2022

Location: Room 224
Poster boards: 227a-7b Halls D-E Lobby


Deep learning has been widely successful in a variety of computer vision tasks such as object recognition, object detection, and semantic segmentation. It also has been deployed with success in learning spatiotemporal features for video segmentation/detection and action recognition tasks. However, one of the major bottlenecks of deep learning in both image and video understanding tasks is the need for large-scale labelled datasets. Collecting and annotating such datasets can be labor intensive and costly. In many scenarios of practical interest only a few labelled examples of novel categories may be available at model training time. Currently available large-scale data typically cover relatively narrow sets of categories and are constrained by licensing. As such, they are often hard to naively apply to practical problems. It is especially problematic in developing countries that do not have the required resources to collect large scale labelled datasets for new tasks. The goal of this workshop is to explore approaches that learn from limited labelled data, or with side information such as text data, or using data with weak/self supervision, with special focus on scene and video understanding tasks.

News and Updates:

  • January 10, 2022: Workshop Officially Confirmed for CVPR 2022, that will take place on Monday June 20, 2022.

  • January 21, 2022: Paper Submission is open at, https://cmt3.research.microsoft.com/L3DIVU2022

  • February 26, 2022: Submission deadline extended to 12th March, Paper award Prizes announced.

  • April 10, 2022: Authors notifications sent out.

  • April 29, 2022: Oral/Poster decisions sent out to all authors.

  • May 30, 2022: Due to unforeseen circumstances Professor Anima Anandkumar will not be able to present in our workshop.


We will be awarding these best paper awards:

  • $1000 (ServiceNow)

  • 1 GPU (Nvidia)

  • $1000 (Unity)

(Only Ph.D. students are eligible to participate. Government officials, public sector officials, and employees of entities who do business in the Public Sector are not eligible to participate. ServiceNow reserves the right not to make the award if the recipient turns out to be a government official, public sector official, or individual who does business in the public sector.)


We encourage submissions that are under one of the topics of interest, but also we welcome other interesting and relevant research for learning with limited labeled data.

  • Few-Shot classification, detection, and segmentation in still images and video, including objects, actions, and scenes.

  • Cross-domain few-shot learning.

  • Zero-shot learning.

  • Self-supervised Learning.

  • Weakly supervised learning.

  • Semi-supervised learning.

  • Transfer Learning.

  • Open-set learning.

  • New benchmarks.

  • Real-world applications discussing the societal Impact of few-shot learning.

Papers will be peer-reviewed under a double-blind policy and the submission deadline is the 5th of March 2022. Accepted papers will be presented at the poster session, some as orals, and two papers will be awarded as the best paper.

This year, June 19 and 20 mark Juneteenth, a US holiday commemorating the end of slavery in the US, and a holiday of special significance in the US South. We encourage attendees to learn more about Juneteenth and its historical context and to join the city of New Orleans in celebrating the Juneteenth holiday. You can find out more information about Juneteenth here.

Invited Speakers

Dima Damen

University of Bristol

Mohamed Elhoseiny


Leonid Sigal


Katerina Fragkiadaki

Carnegie Mellon University

Hugo Larochelle

Google Brain

Jake Snell

University of Toronto

Zhiding Yu

Nvidia AI


For questions you can contact us at: l3divuworkshop@gmail.com