Efficient Spatiotemporal Attention Network for Remote Heart Rate Variability Analysis.

Studies have shown that ordinary color cameras can detect the subtle color changes of the skin caused by the heartbeat cycle. Therefore, cameras can be used to remotely monitor the pulse in a non-contact manner. The technology for non-contact physiological measurement in this way is called remote photoplethysmography (rPPG). Heart rate variability (HRV) analysis, as a very important physiological feature, requires us to be able to accurately recover the peak time locations of the rPPG signal. This paper proposes an efficient spatiotemporal attention network (ESA-rPPGNet) to recover high-quality rPPG signal for heart rate variability analysis. First, 3D depth-wise separable convolution and a structure based on mobilenet v3 are used to greatly reduce the time complexity of the network. Next, a lightweight attention block called 3D shuffle attention (3D-SA), which integrates spatial attention and channel attention, is designed to enable the network to effectively capture inter-channel dependencies and pixel-level dependencies. Moreover, ConvGRU is introduced to further improve the network's ability to learn long-term spatiotemporal feature information. Compared with existing methods, the experimental results show that the method proposed in this paper has better performance and robustness on the remote HRV analysis.

Semantic Correlation Attention-Based Multiorder Multiscale Feature Fusion Network for Human Motion Prediction.

Human motion prediction is to predict future human states based on the observed human states. However, current research ignores the semantic correlations between body parts (joints and bones) in the observed human states and motion time; thus, the prediction accuracy is limited. To address this issue, we propose a novel semantic correlation attention-based multiorder multiscale feature fusion network (SCAFF), which includes an encoder and a decoder. In the encoder, a multiorder difference calculation module (MODC) is designed to calculate the multiorder difference information of joint and bone attributes in the observed human states. Then, multiple semantic correlation attention-based graph calculation operators (SCA-GCOs) are stacked to extract the multiscale features of the multiorder difference information. Each SCA-GCO captures joint and bone dependencies of the multiorder difference information, refines them with a semantic correlation attention module (SCAM), and captures temporal dynamics of the refined joint and bone dependencies as the output features. Note that SCAM learns a semantic attention mask describing the semantic correlations between body parts and motion time for feature refinement. Afterward, multiple multiorder feature fusion modules (MOFFs) and multiscale feature fusion modules (MSFFs) are designed to fuse the multiscale features of the multiorder difference information extracted by multiple SCA-GCOs, thus obtaining the motion features of the observed human states. Based on the obtained motion features, the decoder recurrently recruits a composite gated recurrent module (CGRM) and multilayer perceptrons (MLPs) to predict future human states. As far as we know, this is the first attempt to consider the semantic correlations between body parts and motion time in human motion prediction. The results on public datasets demonstrate that SCAFF outperforms existing models.