PhysMamba: Efficient Remote Physiological Measurement with SlowFast Temporal Difference Mamba
This work addresses the problem of non-contact heart monitoring for applications like healthcare and wellness, offering an incremental improvement over existing CNN and Transformer methods by leveraging state space models.
The paper tackles remote physiological measurement from facial videos by proposing PhysMamba, a Mamba-based framework that efficiently captures long-range spatio-temporal dependencies, achieving state-of-the-art results on three benchmark datasets with improved efficiency.
Facial-video based Remote photoplethysmography (rPPG) aims at measuring physiological signals and monitoring heart activity without any contact, showing significant potential in various applications. Previous deep learning based rPPG measurement are primarily based on CNNs and Transformers. However, the limited receptive fields of CNNs restrict their ability to capture long-range spatio-temporal dependencies, while Transformers also struggle with modeling long video sequences with high complexity. Recently, the state space models (SSMs) represented by Mamba are known for their impressive performance on capturing long-range dependencies from long sequences. In this paper, we propose the PhysMamba, a Mamba-based framework, to efficiently represent long-range physiological dependencies from facial videos. Specifically, we introduce the Temporal Difference Mamba block to first enhance local dynamic differences and further model the long-range spatio-temporal context. Moreover, a dual-stream SlowFast architecture is utilized to fuse the multi-scale temporal features. Extensive experiments are conducted on three benchmark datasets to demonstrate the superiority and efficiency of PhysMamba. The codes are available at https://github.com/Chaoqi31/PhysMamba