Towards End-to-End Generative Modeling of Long Videos with Memory-Efficient Bidirectional Transformers: "...our method learns to decode the entire spatio-temporal volume of a video in parallel from partially observed patches." https://sites.google.com/view/mebt-cvpr2023
Links for 2023-03-22
Links for 2023-03-22
Links for 2023-03-22
Towards End-to-End Generative Modeling of Long Videos with Memory-Efficient Bidirectional Transformers: "...our method learns to decode the entire spatio-temporal volume of a video in parallel from partially observed patches." https://sites.google.com/view/mebt-cvpr2023