Simple unsupervised object-centric learning for complex and naturalistic videos

G Singh, YF Wu, S Ahn - Advances in Neural Information …, 2022 - proceedings.neurips.cc
Unsupervised object-centric learning aims to represent the modular, compositional, and
causal structure of a scene as a set of object representations and thereby promises to …

Neural systematic binder

G Singh, Y Kim, S Ahn - arxiv preprint arxiv:2211.01177, 2022 - arxiv.org
The key to high-level cognition is believed to be the ability to systematically manipulate and
compose knowledge pieces. While token-like structured knowledge representations are …

Roots: Object-centric representation and rendering of 3d scenes

C Chen, F Deng, S Ahn - Journal of Machine Learning Research, 2021 - jmlr.org
A crucial ability of human intelligence is to build up models of individual 3D objects from
partial scene observations. Recent works either achieve object-centric generation but …

Parallelized Spatiotemporal Slot Binding for Videos

G Singh, Y Wang, J Yang, B Ivanovic, S Ahn… - … on Machine Learning, 2024 - openreview.net
While modern best practices advocate for scalable architectures that support long-range
interactions, object-centric models are yet to fully embrace these architectures. In particular …

Parallelized Spatiotemporal Binding

G Singh, Y Wang, J Yang, B Ivanovic, S Ahn… - arxiv preprint arxiv …, 2024 - arxiv.org
While modern best practices advocate for scalable architectures that support long-range
interactions, object-centric models are yet to fully embrace these architectures. In particular …

[BUCH][B] Learning Object-Oriented Models of the Visual World

E Crawford - 2021 - search.proquest.com
Abstract Objects are a central abstraction in human mental life. Indeed, developmental
psychology tells us that humans and many animals have modular, developmentally …