Quality-Aware Network for Face Parsing
This is an incremental application of existing methods to a new domain (face parsing) for computer vision researchers.
The paper applied a state-of-the-art human parsing method to the face parsing task to explore similarities and differences, achieving 86.84% score and second place in a CVPR 2021 challenge.
This is a very short technical report, which introduces the solution of the Team BUPT-CASIA for Short-video Face Parsing Track of The 3rd Person in Context (PIC) Workshop and Challenge at CVPR 2021. Face parsing has recently attracted increasing interest due to its numerous application potentials. Generally speaking, it has a lot in common with human parsing, such as task setting, data characteristics, number of categories and so on. Therefore, this work applies state-of-the-art human parsing method to face parsing task to explore the similarities and differences between them. Our submission achieves 86.84% score and wins the 2nd place in the challenge.