Video Scene Parsing in the Wild
A Large-scale Dataset for Video Scene Parsing in the Wild
Variants: VSPW
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Video Semantic Segmentation | UniVS(Swin-L) | UniVS: Unified and Universal Video … | 2024-02-28 |
| Video Semantic Segmentation | DVIS++(VIT-L) | DVIS++: Improved Decoupled Framework for … | 2023-12-20 |
| Video Semantic Segmentation | Tube-Link(Swin-large) | Tube-Link: A Flexible Cross Tube … | 2023-03-22 |
| Video Semantic Segmentation | MRCFA(MiT-B5) | Mining Relations among Cross-Frame Affinities … | 2022-07-21 |
| Video Semantic Segmentation | CFFM(MiT-B5) | Learning Local and Global Temporal … | 2022-04-07 |
Recent papers with results on this dataset: