@inproceedings{yan2023skeletonmae, title={SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-training}, author={Yan, Hong and Liu, Yang and Wei, Yushen and Li, Guanbin and Lin, ...

To address this, we developed and implemented a "predictive autoencoder". For sequential (i.e. linearly processed data representing graph growth) and nonsequential based temporal graphical data, ...

However, the invasive exposure to radiation and high imaging cost significantly restrict the application ... we further cast our neural network into a supervised sequential graph VAE, where we use the ...