Video Object Segmentation On Youtube Vos
评估指标
F-Measure (Seen)
F-Measure (Unseen)
Jaccard (Seen)
Jaccard (Unseen)
Overall
Params(M)
Speed (FPS)
评测结果
各个模型在此基准测试上的表现结果
比较表格
| 模型名称 | F-Measure (Seen) | F-Measure (Unseen) | Jaccard (Seen) | Jaccard (Unseen) | Overall | Params(M) | Speed (FPS) |
|---|---|---|---|---|---|---|---|
| associating-objects-with-transformers-for | 84.7 | 83.5 | 80.0 | 75.2 | 80.9 | 5.3 | 41.0 |
| rethinking-space-time-networks-with-improved | 87.9 | 87.3 | 83.2 | 79.0 | - | - | - |
| video-object-segmentation-using-space-time | - | - | - | - | 68.2 | - | - |
| collaborative-video-object-segmentation-by | 85.8 | 83.4 | 81.1 | 75.3 | 81.4 | 66.3 | 3.4 |
| xmem-long-term-video-object-segmentation-with | 89.9 | 89.9 | 85.3 | 81.7 | 86.7 | - | - |
| youtube-vos-sequence-to-sequence-video-object | 70.0 | 61.2 | 71.0 | - | 64.4 | - | 55.5 |
| associating-objects-with-scalable | 90.2 | 87.3 | 85.1 | 78.9 | 85.4 | 15.1 | - |
| kernelized-memory-network-for-video-object | 85.6 | 83.3 | 81.4 | 75.3 | 81.4 | - | - |
| associating-objects-with-transformers-for | 89.5 | 88.2 | 84.5 | 79.6 | 85.5 | 14.9 | 6.4 |
| decoupling-features-in-hierarchical | 89.9 | 88.7 | 84.9 | 80.4 | 86.0 | 19.8 | - |
| associating-objects-with-scalable | 88.5 | 87.2 | 83.5 | 78.8 | 84.5 | 13.9 | - |
| modular-interactive-video-object-segmentation | 84.7 | 85.5 | 80.6 | 77.3 | 82.0 | - | - |
| xmem-long-term-video-object-segmentation-with | 89.3 | 88.7 | 84.6 | 80.2 | 85.7 | - | 22.6 |
| one-shot-video-object-segmentation | 60.5 | 60.7 | 59.8 | 54.2 | 58.8 | - | 0.10 |
| decoupling-features-in-hierarchical | 89.4 | - | 84.2 | 78.6 | 84.8 | - | - |
| associating-objects-with-transformers-for | 88.5 | 86.5 | 83.6 | 78.0 | 84.1 | 8.3 | 20.5 |
| video-object-segmentation-with-adaptive | 83.1 | 82.6 | 78.8 | 74.1 | 79.6 | - | - |
| reliable-propagation-correction-modulation | 87.7 | 86.7 | 83.1 | - | 84 | - | - |
| associating-objects-with-scalable | 88.8 | 87.9 | 83.8 | 79.3 | 85.0 | 15.4 | - |
| decoupling-features-in-hierarchical | 90.6 | 88.4 | 85.6 | 80.0 | 86.2 | 70.3 | - |
| efficient-video-object-segmentation-via | 60.1 | 44.0 | 60.0 | 40.6 | 51.2 | - | 7.14 |
| associating-objects-with-transformers-for | 87.5 | 86.0 | 82.6 | 77.7 | 83.5 | 8.3 | 20.5 |
| decoupling-features-in-hierarchical | 88.3 | 86.6 | 83.3 | 77.9 | 84.0 | 10.2 | - |
| associating-objects-with-transformers-for | 87.0 | 85.7 | 82.2 | 77.3 | 83.0 | 7.9 | 27.1 |
| hierarchical-memory-matching-network-for | 87.0 | 84.6 | 82.1 | 76.8 | 82.6 | - | - |
| learning-quality-aware-dynamic-memory-for | 87.5 | 86.4 | 82.7 | 78.4 | 83.8 | - | - |
| associating-objects-with-scalable | 86.1 | 83.5 | 81.4 | 75.5 | 81.6 | 12.5 | - |
| collaborative-video-object-segmentation-by-1 | 86.6 | 85.6 | 81.8 | 77.1 | 82.8 | - | 4.0 |
| rvos-end-to-end-recurrent-network-for-video | 67.2 | 51.0 | 63.6 | - | 56.8 | - | 45.5 |
| efficient-regional-memory-network-for-video | 85.7 | 82.4 | 82.1 | 75.7 | 81.5 | - | - |
| make-one-shot-video-object-segmentation-1 | 66.0 | 73.8 | 71.7 | 74.3 | 71.4 | - | - |
| region-aware-video-object-segmentation-with | 87.8 | 87.4 | 83.1 | 79.1 | 84.4 | - | 23 |
| associating-objects-with-transformers-for | 86.7 | 85.0 | 82.0 | 76.6 | 82.6 | 7.9 | 27.1 |
| delving-into-the-cyclic-mechanism-in-semi | 75.8 | 70.4 | 71.7 | - | 69.9 | - | 61.4 |
| separable-structure-modeling-for-semi | 73.3 | 62.6 | 72.3 | 57.8 | 66.5 | - | 24.1 |
| associating-objects-with-transformers-for | 88.5 | 86.1 | 83.7 | 78.1 | 84.1 | 14.9 | 14.9 |
| capsulevos-semi-supervised-video-object | 68.1 | 59.9 | 67.3 | 53.7 | 62.3 | - | 13.5 |
| putting-the-object-back-into-video-object | 91.0 | 90.1 | 86.6 | 82.2 | 87.5 | - | - |
| self-supervised-video-object-segmentation-by-1 | 68.4 | 73.2 | 67.0 | 64.5 | 68.2 | - | - |
| decoupling-features-in-hierarchical | 88.9 | 87.0 | 83.9 | 78.5 | 84.6 | 13.2 | - |
| xmem-long-term-video-object-segmentation-with | 88.5 | 87.2 | 83.7 | 78.2 | 84.4 | - | 22.6 |
| learning-fast-and-robust-target-models-for | 76.2 | 74.1 | 72.3 | - | 72.1 | - | 65.9 |
| associating-objects-with-scalable | 90.1 | 88.2 | - | 79.6 | 85.8 | - | - |
| associating-objects-with-transformers-for | 89.3 | 86.4 | 84.3 | 77.9 | 84.5 | 65.4 | 9.3 |
| associating-objects-with-transformers-for | 90.1 | 86.9 | 85.1 | 78.4 | 85.1 | 65.4 | 5.2 |
| associating-objects-with-transformers-for | 88.8 | 87.1 | 83.7 | 78.4 | 84.5 | 8.3 | 6.5 |
| associating-objects-with-scalable | 90.7 | 88.9 | 85.6 | 80.7 | 86.5 | 65.6 | - |
| associating-objects-with-transformers-for | 84.5 | 82.2 | 80.1 | 74.0 | 80.2 | 5.3 | 41.0 |
| xmem-long-term-video-object-segmentation-with | 90.3 | 90.2 | 85.6 | 81.7 | 86.9 | - | - |
| reliable-propagation-correction-modulation | 87.9 | 86.9 | 83.3 | 78.9 | 84.3 | - | - |
| xmem-long-term-video-object-segmentation-with | 89.8 | 89.2 | 85.1 | 80.3 | 86.1 | - | 22.6 |
| decoupling-features-in-hierarchical | 86.3 | 84.2 | 81.6 | 75.8 | 82.0 | 7.2 | - |
| associating-objects-with-transformers-for | 87.9 | 86.5 | 82.9 | 77.7 | 83.8 | 8.3 | 16.0 |