Unsupervised Video Object Segmentation On 4
評価指標
F-measure (Mean)
Ju0026F
Jaccard (Mean)
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | F-measure (Mean) | Ju0026F | Jaccard (Mean) | Paper Title | Repository |
|---|---|---|---|---|---|
| Propose-Reduce | 73.8 | 70.4 | 67.0 | Video Instance Segmentation with a Propose-Reduce Paradigm | |
| AGS | 59.5 | 57.5 | 55.5 | Learning Unsupervised Video Object Segmentation Through Visual Attention | - |
| RVOS | 45.7 | 41.2 | 36.8 | RVOS: End-to-End Recurrent Network for Video Object Segmentation | |
| STEm-Seg | 67.8 | 64.7 | 61.5 | STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos | |
| PDB | 57.0 | 55.1 | 53.2 | Pyramid Dilated Deeper ConvLSTM for Video Salient Object Detection | - |
| ALBA | 60.2 | 58.4 | 56.6 | ALBA : Reinforcement Learning for Video Object Segmentation | |
| MATNet | 60.4 | 58.6 | 56.7 | MATNet: Motion-Attentive Transition Network for Zero-Shot Video Object Segmentation | |
| DEVA (EntitySeg) | 76.4 | 73.4 | 70.4 | Tracking Anything with Decoupled Video Segmentation | |
| UnOVOST | 69.3 | 67.9 | 66.4 | UnOVOST: Unsupervised Offline Video Object Segmentation and Tracking | |
| MAST | 67.6 | 65.5 | 63.3 | MAST: A Memory-Augmented Self-supervised Tracker |
0 of 10 row(s) selected.