ConceptMotion VAE
Motion VAE
A class of methods applying variational autoencoders to human motion sequence modeling. The encoder typically uses a Transformer or graph convolutional network, the decoder outputs coherent skeletal pose sequences, and the latent space is used for interpolation, editing, or cross-modal retrieval.
Timeline (last 90 days)
Oct 14
Motion VAE is a class of methods that applies variational autoencoders to human motion sequence modeling; its encoder typically uses a Transformer or graph convolutional network, the decoder outputs a skeletal pose sequence, and the training objective is to maximize the ELBO.
Unverified50%