← Search

Matthew J. Vowels

2 accepted papers

2021

VDSM: Unsupervised Video Disentanglement With State-Space Modeling and Deep Mixtures of Experts

CVPR 2021poster

Disentangled representations support a range of downstream tasks including causal reasoning, generative modeling, and fair machine learning. Unfortunately, disentanglement has been shown to be impossible without the incorporation of supervision or inductive bias. Given that supervision is often expe…

Cited by 10PDFcodeScholar