English

Shuffle Transformer with Feature Alignment for Video Face Parsing

Computer Vision and Pattern Recognition 2021-06-17 v1

Abstract

This is a short technical report introducing the solution of the Team TCParser for Short-video Face Parsing Track of The 3rd Person in Context (PIC) Workshop and Challenge at CVPR 2021. In this paper, we introduce a strong backbone which is cross-window based Shuffle Transformer for presenting accurate face parsing representation. To further obtain the finer segmentation results, especially on the edges, we introduce a Feature Alignment Aggregation (FAA) module. It can effectively relieve the feature misalignment issue caused by multi-resolution feature aggregation. Benefiting from the stronger backbone and better feature aggregation, the proposed method achieves 86.9519% score in the Short-video Face Parsing track of the 3rd Person in Context (PIC) Workshop and Challenge, ranked the first place.

Keywords

Cite

@article{arxiv.2106.08650,
  title  = {Shuffle Transformer with Feature Alignment for Video Face Parsing},
  author = {Rui Zhang and Yang Han and Zilong Huang and Pei Cheng and Guozhong Luo and Gang Yu and Bin Fu},
  journal= {arXiv preprint arXiv:2106.08650},
  year   = {2021}
}

Comments

technical report

R2 v1 2026-06-24T03:15:29.667Z