1 citations · 1 across the 3 of their papers we have counts for
Showing cs.CVShow all
2 papers · 1 filter
cs.CV2023
Exploiting Inductive Biases in Video Modeling through Neural CDEs
Johnathan Chiu, Samuel Duffield, Max Hunter-Gordon +3
We introduce a novel approach to video modeling that leverages controlled differential equations (CDEs) to address key challenges in video tasks, notably video interpolation and ma…
cs.CV2023
Variable Length Embeddings
Johnathan Chiu, Andi Gu, Matt Zhou
In this work, we introduce a novel deep learning architecture, Variable Length Embeddings (VLEs), an autoregressive model that can produce a latent representation composed of an ar…