Video Object Segmentation on YoutubeObjects (test)
77.3mIoULucidTracker
Evaluation results
| Method | Links | |
|---|---|---|
| LucidTracker# training images=24-126, Flow (F)=true, Annotation Protocol=Uses 1st frame annotation2017.03 | 77.3 | |
| MaskTrack# training images=~11k, Flow (F)=true, Annotation Protocol=Uses 1st frame annotation2017.03 | 72.6 | |
| OSVOS# training images=~2.3k, Flow (F)=false, Annotation Protocol=Uses 1st frame annotation2017.03 | 72.5 | |
| MaskTrackInput=First-frame segmentation mask2016.12 | 71.7 | |
| ObjFlow2016.12 | 70.1 | |
| ObjFlow# training images=0, Flow (F)=true, Annotation Protocol=Uses 1st frame annotation2017.03 | 70.1 | |
| MaskTrack_BoxInput=First-frame box annotation2016.12 | 69.3 | |
| FusionSeg# training images=~95k, Flow (F)=true, Annotation Protocol=Ignores 1st frame annotation2017.03 | 67.9 | |
| Grabcut oracleInput=Segmentation from Grabcut2016.12 | 67.6 | |
| Grabcut oracle# training images=0, Flow (F)=false, Annotation Protocol=Ignores 1st frame annotation2017.03 | 67.6 | |
| BVS2016.12 | 59.7 | |
| BVS# training images=0, Flow (F)=false, Annotation Protocol=Uses 1st frame annotation2017.03 | 59.7 | |
| W162016.12 | 59.2 | |
| Box oracleInput=Box annotation2016.12 | 55.3 | |
| Box oracle# training images=0, Flow (F)=false, Annotation Protocol=Ignores 1st frame annotation2017.03 | 55.3 | |
| Z152016.12 | 52.6 | |
| Mask warping# training images=0, Flow (F)=true, Annotation Protocol=Uses 1st frame annotation2017.03 | 43.2 | |
| Saliency# training images=0, Flow (F)=false, Annotation Protocol=Ignores 1st frame annotation2017.03 | 40.7 | |
| Flow saliency# training images=0, Flow (F)=true, Annotation Protocol=Ignores 1st frame annotation2017.03 | 36.3 |