Sequential Variational Autoencoder with Adversarial Classifier for Video Disentanglement

In this paper, we propose a sequential variational autoencoder for video disentanglement, which is a representation learning method that can be used to separately extract static and dynamic features from videos. Building sequential variational autoencoders with a two-stream architecture induces indu...

Descripción completa

Detalles Bibliográficos
Autores principales: Haga, Takeshi, Kera, Hiroshi, Kawamoto, Kazuhiko
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10006877/
https://www.ncbi.nlm.nih.gov/pubmed/36904719
http://dx.doi.org/10.3390/s23052515

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10006877/
https://www.ncbi.nlm.nih.gov/pubmed/36904719
http://dx.doi.org/10.3390/s23052515

Ejemplares similares