GenTron: Diffusion Transformers for Image and Video Generation
In this study we explore Transformer based diffusion models for image and video
generation. Despite the dominance of Transformer architectures in various fields due to their …
generation. Despite the dominance of Transformer architectures in various fields due to their …
Character-preserving coherent story visualization
Story visualization aims at generating a sequence of images to narrate each sentence in a
multi-sentence story. Different from video generation that focuses on maintaining the …
multi-sentence story. Different from video generation that focuses on maintaining the …
[PDF][PDF] Hamiltonian Operator Disentanglement of Content and Motion in Image Sequences.
MA Khan, AJ Storkey - arXiv preprint arXiv:2112.01641, 2021 - academia.edu
We introduce a deep generative model for image sequences that reliably factorise the latent
space into content and motion variables. To model the diverse dynamics, we split the motion …
space into content and motion variables. To model the diverse dynamics, we split the motion …
Hamiltonian latent operators for content and motion disentanglement in image sequences
A Khan, AJ Storkey - Advances in Neural Information …, 2022 - proceedings.neurips.cc
Abstract We introduce\textit {HALO}--a deep generative model utilising HAmiltonian Latent
Operators to reliably disentangle content and motion information in image sequences …
Operators to reliably disentangle content and motion information in image sequences …
[PDF][PDF] Hamiltonian prior to Disentangle Content and Motion in Image Sequences
We present a deep latent variable model for high dimensional sequential data. Our model
factorises the latent space into content and motion variables. To model the diverse …
factorises the latent space into content and motion variables. To model the diverse …
NeurInt: Learning to Interpolate through Neural ODEs
A wide range of applications require learning image generation models whose latent space
effectively captures the high-level factors of variation present in the data distribution. The …
effectively captures the high-level factors of variation present in the data distribution. The …
[PDF][PDF] Knowledge Elicitation using Psychometric Learning
L Yin - 2023 - research.tue.nl
Knowledge Elicitation using Psychometric Learning Page 1 Knowledge Elicitation using
Psychometric Learning Citation for published version (APA): Yin, L. (2023). Knowledge …
Psychometric Learning Citation for published version (APA): Yin, L. (2023). Knowledge …
[PDF][PDF] Character-Preserving Coherent Story Visualization
HH Shuai - researchgate.net
Story visualization aims at generating a sequence of images to narrate each sentence in a
multi-sentence story. Different from video generation that focuses on maintaining the …
multi-sentence story. Different from video generation that focuses on maintaining the …