Video Instance Segmentation on OVIS 1.0 (val)
36.2APGRAtt-VIS
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| GRAtt-VISInference Mode=Online, Backbone=ResNet-502023.05 | 36.2 | 60.8 | 36.8 | 16.8 | 40 | |
| GenVISInference Mode=Online, Backbone=ResNet-502023.05 | 35.8 | 60.8 | 36.2 | 16.3 | 39.6 | |
| ROVISInference Mode=Online, Backbone=ResNet-502023.05 | 30.2 | 53.9 | 30.1 | 13.6 | 36.3 | |
| IDOLInference Mode=Online, Backbone=ResNet-502023.05 | 30.2 | 51.3 | 30 | 15 | 37.5 | |
| MinVISInference Mode=Online, Backbone=ResNet-502023.05 | 25 | 45.5 | 24 | 13.9 | 29.7 | |
| InstanceFormerInference Mode=Online, Backbone=ResNet-502023.05 | 20 | 40.7 | 18.1 | 12 | 27.1 | |
| VITAInference Mode=Offline, Backbone=ResNet-502023.05 | 19.6 | 41.2 | 17.4 | 11.7 | 26 | |
| TeViTInference Mode=Offline, Backbone=ResNet-502023.05 | 17.4 | 34.9 | 15 | 11.2 | 21.8 | |
| VISOLOInference Mode=Online, Backbone=ResNet-502023.05 | 15.3 | 31 | 13.8 | 11.1 | 21.7 | |
| SeqFormerInference Mode=Offline, Backbone=ResNet-502023.05 | 15.1 | 31.9 | 13.8 | 10.4 | 27.1 | |
| CrossVISInference Mode=Online, Backbone=ResNet-502023.05 | 14.9 | 32.7 | 12.1 | 10.3 | 19.8 |