Facial action units (AU) are the fundamental units to decode human facial expressions. At least three aspects affect performance of automated AU detection: spatial representation, temporal modeling, and AU correlation. Unlike most studies that tackle these aspects separately, we propose a hybrid network architecture to jointly model them. Our network naturally addresses the three issues together, and yields superior performance compared to existing methods that consider these issues independently. Extensive experiments were conducted on two large spontaneous datasets, GFT and BP4D, with more than 400,000 frames coded with 12 AUs. On both datasets, we report improvements over a standard multi-label CNN and feature-based state-of-the-art. Finally, we provide visualization of the learned AU models, which, to our best knowledge, reveal how machines see AUs for the first time.