English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Unsupervised object-centric learning aims to represent the modular,compositional, and causal structure of a scene as a set of objectrepresentations and thereby promises to resolve many critical limitations oftraditional single-vector representations such as poor systematicgeneralization. Although there have been many remarkable advances in recentyears, one of the most critical problems in this direction has been thatprevious methods work only with simple and synthetic scenes but not withcomplex and naturalistic images or videos. In this paper, we propose STEVE, anunsupervised model for object-centric learning in videos. Our proposed modelmakes a significant advancement by demonstrating its effectiveness on variouscomplex and naturalistic videos unprecedented in this line of research.Interestingly, this is achieved by neither adding complexity to the modelarchitecture nor introducing a new objective or weak supervision. Rather, it isachieved by a surprisingly simple architecture that uses a transformer-basedimage decoder conditioned on slots and the learning objective is simply toreconstruct the observation. Our experiment results on various complex andnaturalistic videos show significant improvements compared to the previousstate-of-the-art.

Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videos