Beyond Independent Frames: Latent Attention Masked Autoencoders for Multi-View Echocardiography

ArXi:2604.15096v1 Announce Type: cross Echocardiography is a widely used modality for cardiac assessment due to its non-invasive and cost-effective nature, but the sparse and heterogeneous spatiotemporal views of the heart pose distinct challenges. Existing masked autoencoder (MAE) approaches typically process images or short clips independently, failing to capture the inherent multi-view structure required for coherent cardiac representation. We