Semi Supervised Video Object Segmentation On 1
評価指標
F-measure (Mean)
FPS
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
比較表
| モデル名 | F-measure (Mean) | FPS | Ju0026F | Jaccard (Mean) |
|---|---|---|---|---|
| associating-objects-with-scalable | 86.6 | 12.0 | 82.7 | 78.8 |
| xmem-long-term-video-object-segmentation-with | 84.7 | - | 81.2 | 77.6 |
| associating-objects-with-transformers-for | 85.1 | 12.1 | 81.2 | 77.3 |
| premvos-proposal-generation-refinement-and | 75.8 | - | 71.6 | 67.5 |
| associating-objects-with-scalable | 87.9 | 1.3 | 84.5 | 81.0 |
| video-object-segmentation-without-temporal | 62.1 | - | 57.5 | 52.9 |
| learning-quality-aware-dynamic-memory-for | 85.4 | - | 81.9 | 78.1 |
| lsmvos-long-short-term-similarity-matching | 71.2 | - | 67.4 | 63.7 |
| xmem-long-term-video-object-segmentation-with | 87.0 | - | 83.7 | 80.5 |
| collaborative-video-object-segmentation-by-1 | 81.6 | - | 78.0 | 74.4 |
| tracking-anything-with-decoupled-video | 86.8 | 25.3 | 83.2 | 79.6 |
| decoupling-features-in-hierarchical | 79.0 | 49.2 | 75.4 | 71.9 |
| modular-interactive-video-object-segmentation | 80.2 | - | 76.5 | 72.7 |
| capsulevos-semi-supervised-video-object | 55.2 | - | 51.3 | 47.4 |
| collaborative-video-object-segmentation-by | 78.5 | - | 74.8 | 71.1 |
| efficient-regional-memory-network-for-video | 78.1 | - | 75.0 | 71.9 |
| efficient-video-object-segmentation-via | - | - | 41.3 | 37.7 |
| associating-objects-with-transformers-for | 82.3 | 18.7 | 78.3 | 74.3 |
| reliable-propagation-correction-modulation | 82.6 | - | 79.2 | 75.8 |
| xmem-long-term-video-object-segmentation-with | 85.8 | - | 82.5 | 79.1 |
| kernelized-memory-network-for-video-object | 80.3 | - | 77.2 | 74.1 |
| reliable-propagation-correction-modulation | 84.3 | - | 81 | 77.6 |
| memory-matching-is-not-enough-jointly | 87.4 | - | 83.9 | 80.3 |
| fast-video-object-segmentation-by-reference | 54.4 | - | 52.8 | 51.3 |
| lucid-data-dreaming-for-video-object | 69.9 | - | 66.6 | 63.4 |
| decoupling-features-in-hierarchical | 79.9 | 40.9 | 76.2 | 72.5 |
| ranet-ranking-attention-network-for-fast | 57.3 | - | 55.4 | 53.4 |
| associating-objects-with-scalable | 81.7 | 24.3 | 78.1 | 74.5 |
| hierarchical-memory-matching-network-for | 82.5 | - | 78.6 | 74.7 |
| associating-objects-with-transformers-for | 75.7 | 51.4 | 72.0 | 68.3 |
| associating-objects-with-scalable | 83.6 | 17.5 | 79.9 | 76.2 |
| one-shot-video-object-segmentation | - | - | 50.9 | 47.0 |
| xmem-long-term-video-object-segmentation-with | 86.4 | - | 83.1 | 79.7 |
| decoupling-features-in-hierarchical | 81.7 | 28.5 | 77.9 | 74.1 |
| associating-objects-with-transformers-for | 77.5 | 40.0 | 73.9 | 70.3 |
| associating-objects-with-transformers-for | 79.3 | 29.6 | 75.5 | 71.6 |
| fast-online-object-tracking-and-segmentation | 45.8 | - | 43.2 | 40.6 |
| online-adaptation-of-convolutional-neural | - | - | 52.8 | 49.9 |
| decoupling-features-in-hierarchical | 77.3 | 63.5 | 73.7 | 70.0 |
| decoupling-features-in-hierarchical | 84.5 | 27.0 | 80.7 | 76.9 |
| fast-and-accurate-online-video-object | 44.2 | - | 43.6 | 42.9 |
| video-object-segmentation-using-space-time | 75.2 | - | 72.2 | 69.3 |
| feelvos-fast-end-to-end-embedding-learning | 60.4 | - | 57.8 | 55.1 |
| decoupling-features-in-hierarchical | 86.7 | 15.4 | 82.8 | 78.9 |
| 190408141 | 72.7 | - | 69.5 | 66.4 |
| putting-the-object-back-into-video-object | 89.9 | 36.4 | 86.1 | 82.4 |
| putting-the-object-back-into-video-object | 89.2 | 17.9 | 85.9 | 82.6 |
| siam-r-cnn-visual-tracking-by-re-detection | 58.6 | - | 53.3 | 48.0 |
| rethinking-space-time-networks-with-improved | 83.5 | - | 79.9 | 76.3 |
| rvos-end-to-end-recurrent-network-for-video | 52.6 | - | 50.3 | 47.9 |
| xmem-long-term-video-object-segmentation-with | 84.5 | - | 81.0 | 77.4 |
| associating-objects-with-transformers-for | 83.3 | 18.0 | 79.6 | 75.9 |
| cnn-in-mrf-video-object-segmentation-via | 70.5 | - | 67.5 | 64.5 |
| a-generative-appearance-model-for-end-to-end | 55.3 | - | 52.3 | 49.2 |
| associating-objects-with-scalable | 88.5 | 1.3 | 84.7 | 80.9 |
| make-one-shot-video-object-segmentation-1 | 68.6 | - | 64.8 | 60.9 |
| separable-structure-modeling-for-semi | 63.8 | - | 62.0 | 60.2 |
| putting-the-object-back-into-video-object | 91.4 | 17.9 | 88.1 | 84.7 |
| xmem-long-term-video-object-segmentation-with | 83.4 | - | 79.8 | 76.3 |