Facial Action Unit Representation Based on Self-Supervised Learning With Ensembled Priori Constraints.

Facial action units (AUs) focus on a comprehensive set of atomic facial muscle movements for human expression understanding. Based on supervised learning, discriminative AU representation can be achieved from local patches where the AUs are located. Unfortunately, accurate AU localization and characterization are challenged by the tremendous manual annotations, which limits the performance of AU recognition in realistic scenarios.

Development of an improved H-bridge cascaded static synchronous compensator in power system.

This paper presents a new configuration of H-bridge cascaded static synchronous compensator (STATCOM) based on auto disturbance rejection control and modulation wave shifting control intended for installation in industrial and utility power distribution systems. It proposes an improved controller that devotes itself not only to satisfying the requirement of dynamic reactive power compensation but also to achieving the balance of DC capacitor voltage. The new configuration is prominent in having no restriction on the number of power module.