Skip to content
conftrace_
2024 ICML ICML 2024

EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Computer Vision

Authors

Sunil Hwang, Jaehong Yoon, Youngwan Lee, Sung Ju Hwang

Topics

Machine Learning > Application Areas > Efficient Computing Computer Vision > Processing > Video Understanding Deep Learning > Learning Types > Representation Learning

Keywords

self-supervised learning information density frame selection motion feature spatio-temporal token masked video autoencoder
Download PDF