mlsanityData to 7 Oct 2026

Exploiting Spatial-Temporal Semantic Consistency for Video Scene Parsing

arXiv 2109.02281 ↗First posted 6 Sep 2021cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 11 of its 16 references that are in the map. First posted on arXiv 6 Sep 2021.

Builds on

11 of 16 references.

References · 11

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  5. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  6. 2018Unified Perceptual Parsing for Scene Understandingcited by 1,265
  7. 2018Dual Attention Network for Scene Segmentationcited by 1,001
  8. 2021CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windowscited by 526
  9. 2021Semi-Supervised Semantic Segmentation with Cross Pseudo Supervisioncited by 462
  10. 2020ResNeSt: Split-Attention Networkscited by 445
  11. 2018Adversarial Learning for Semi-Supervised Semantic Segmentationcited by 173

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1.

2 papers.

  1. 2022TubeFormer-DeepLab: Video Mask Transformercited by 35
  2. 20231st Place Solution for PVUW Challenge 2023: Video Panoptic Segmentationcited by 7