mlsanityData to 7 Oct 2026

3rd Place Solution for PVUW Challenge 2024: Video Panoptic Segmentation

arXiv 2406.04002 ↗First posted 6 Jun 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Video panoptic segmentation is an advanced task that extends panoptic segmentation by applying its concept to video sequences. In the hope of addressing the challenge of video panoptic segmentation in diverse conditions, We utilize DVIS++ as our baseline model and enhance it by introducing a comprehensive approach centered on the query-wise ensemble, supplemented by additional techniques. Our proposed approach achieved a VPQ score of 57.01 on the VIPSeg test set, and ranked 3rd in the VPS track of the 3rd Pixel-level Video Understanding in the Wild Challenge.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 17 of its 20 references that are in the map. First posted on arXiv 6 Jun 2024.

Builds on

17 of 20 references.

References · 17

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
  3. 2022Vision Transformer Adapter for Dense Predictionscited by 564
  4. 2019Video Instance Segmentationcited by 391
  5. 2019Panoptic-DeepLabcited by 362
  6. 2020MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformerscited by 355
  7. 2021K-Net: Towards Unified Image Segmentationcited by 211
  8. 2023Tracking Anything with Decoupled Video Segmentationcited by 197
  9. 2019UPSNet: A Unified Panoptic Segmentation Networkcited by 175
  10. 2020Video Panoptic Segmentationcited by 141
  11. 2020ViP-DeepLab: Learning Visual Perception with Depth-aware Video Panoptic Segmentationcited by 95
  12. 2022MinVIS: A Minimal Video Instance Segmentation Framework without Video-based Trainingcited by 94
5 more
  1. 2022Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentationcited by 79
  2. 2023DVIS: Decoupled Video Instance Segmentation Frameworkcited by 77
  3. 2022A Generalized Framework for Video Instance Segmentationcited by 52
  4. 2023DVIS++: Improved Decoupled Framework for Universal Video Segmentationcited by 46
  5. 2024UniVS: Unified and Universal Video Segmentation with Prompts as Queriescited by 26

Built on by

Not cited yet.