[BMVC 2021 Oral] Official implementation of our paper "A Unified Framework for Real-world Skeleton-based Action Recognition" on Toyota Smarthome/Penn Action/NTU-RGB+D/Posetics datasets
Thanks for presenting such a great work. Just wondering if you could share the weights of the model pre-trained over the 3D Posetics? I believe the model you shared in the repo is only based on 2D.