Skip to main navigation Skip to search Skip to main content

ViewCLR: Learning Self-supervised Video Representation for Unseen Viewpoints

  • University of North Carolina at Charlotte

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

27 Scopus citations

Abstract

Learning self-supervised video representation predominantly focuses on discriminating instances generated from simple data augmentation schemes. However, the learned representation often fails to generalize over unseen camera viewpoints. To this end, we propose ViewCLR, that learns self-supervised video representation invariant to camera viewpoint changes. We introduce a viewpoint-generator that can be considered as a learnable augmentation for any self-supervised pre-text tasks, to generate latent viewpoint representation of a video. ViewCLR maximizes the similarities between the representation of the latent viewpoint and that of the original viewpoint, enabling the learned video encoder to generalize over unseen camera viewpoints. Experiments on cross-view benchmark datasets including NTU RGB+D dataset show that ViewCLR stands as a state-of-the-art viewpoint invariant self-supervised method.

Original languageEnglish
Title of host publicationProceedings - 2023 IEEE Winter Conference on Applications of Computer Vision, WACV 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages5562-5572
Number of pages11
ISBN (Electronic)9781665493468
DOIs
StatePublished - 2023
Event23rd IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2023 - Waikoloa, United States
Duration: Jan 3 2023Jan 7 2023

Publication series

NameProceedings - 2023 IEEE Winter Conference on Applications of Computer Vision, WACV 2023

Conference

Conference23rd IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2023
Country/TerritoryUnited States
CityWaikoloa
Period01/3/2301/7/23

Keywords

  • Algorithms: Video recognition and understanding (tracking, action recognition, etc.)
  • and algorithms (including transfer, low-shot, semi-, self-, and un-supervised learning)
  • formulations
  • Machine learning architectures

Fingerprint

Dive into the research topics of 'ViewCLR: Learning Self-supervised Video Representation for Unseen Viewpoints'. Together they form a unique fingerprint.

Cite this