Goto

Collaborating Authors

 Technology


7b39f4512a2e3899edcc59c7501f3cd4-Paper-Conference.pdf

Neural Information Processing Systems

The LDS model is built on the state-space model and assumes latent factors evolvewith linear dynamics. Ontheother hand, GPFAmodels thelatent vectors by non-parametric Gaussian processes.







Few-shotImageGenerationwith ElasticWeightConsolidation

Neural Information Processing Systems

We demonstrate the effectiveness of our algorithm by generating high-quality results of different target domains, including those with extremely few examples (e.g., 10).