MSSTNet: Multi-scale facial videos pulse extraction network based on separable spatiotemporal convolution and dimension separable attention

Changchen Zhao, Hongsheng Wang, Yuanjing Feng. MSSTNet: Multi-scale facial videos pulse extraction network based on separable spatiotemporal convolution and dimension separable attention. Virtual Real. Intell. Hardw., 5(2):124-141, April 2023. [doi]

Abstract

Abstract is missing.