| Paper | Code | VPQ | VPQ (thing) | VPQ (stuff) | ModelName | ReleaseDate |
|---|---|---|---|---|---|---|
| ViP-DeepLab: Learning Visual Perception with Depth-aware Video Panoptic Segmentation | ✓ Link | 63.1 | 49.5 | 73.0 | VIP-Deeplab | 2020-12-09 |
| PolyphonicFormer: Unified Query Learning for Depth-aware Video Panoptic Segmentation | ✓ Link | 62.3 | - | - | PolyphonicFormer | 2021-12-05 |
| Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation | ✓ Link | 62.2 | 49.8 | 71.8 | Video K-Net (Swin-B) | 2022-04-10 |
| TarViS: A Unified Approach for Target-based Video Segmentation | ✓ Link | 58.9 | 43.7 | 69.9 | TarViS (Swin-L) | 2023-01-06 |
| TarViS: A Unified Approach for Target-based Video Segmentation | ✓ Link | 58.0 | 42.9 | 69.0 | TarViS (Swin-T) | 2023-01-06 |
| Learning to Associate Every Segment for Video Panoptic Segmentation | 57.3 | 44.7 | 66.4 | VPSNet-SiamTrack | 2021-06-17 | |
| Video Panoptic Segmentation | ✓ Link | 57.0 | 44.7 | 66.0 | VPSNet | 2020-06-19 |
| TarViS: A Unified Approach for Target-based Video Segmentation | ✓ Link | 53.3 | 35.9 | 66.0 | TarViS (ResNet-50) | 2023-01-06 |