English

Exploiting Spatial-Temporal Semantic Consistency for Video Scene Parsing

Computer Vision and Pattern Recognition 2021-09-07 v1

Abstract

Compared with image scene parsing, video scene parsing introduces temporal information, which can effectively improve the consistency and accuracy of prediction. In this paper, we propose a Spatial-Temporal Semantic Consistency method to capture class-exclusive context information. Specifically, we design a spatial-temporal consistency loss to constrain the semantic consistency in spatial and temporal dimensions. In addition, we adopt an pseudo-labeling strategy to enrich the training dataset. We obtain the scores of 59.84% and 58.85% mIoU on development (test part 1) and testing set of VSPW, respectively. And our method wins the 1st place on VSPW challenge at ICCV2021.

Keywords

Cite

@article{arxiv.2109.02281,
  title  = {Exploiting Spatial-Temporal Semantic Consistency for Video Scene Parsing},
  author = {Xingjian He and Weining Wang and Zhiyong Xu and Hao Wang and Jie Jiang and Jing Liu},
  journal= {arXiv preprint arXiv:2109.02281},
  year   = {2021}
}

Comments

1st Place technical report for "The 1st Video Scene Parsing in the Wild Challenge" at ICCV2021

R2 v1 2026-06-24T05:42:22.016Z