05/22/2025 - We developed a lightweight registration package featuring several top-performing models, along with tutorials on how to deploy them on some public datasets and benchmarks. See details ...

Remark: Comparing computation budget under the same setting (1 Tesla V100-32GB, 64 batch size, etc.) on NTU RGB+D 60 Cross-Subject Benchmark. *EfficientNet-B4 requires 4 times higher temporal ...