Referring Video Object Segmentation On Revos
평가 지표
F
J
Ju0026F
R
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | F | J | Ju0026F | R |
|---|---|---|---|---|
| visa-reasoning-video-object-segmentation-via | 49.0 | 44.9 | 46.9 | 15.5 |
| mevis-a-large-scale-benchmark-for-video | 31.7 | 21.2 | 26.4 | 3.2 |
| end-to-end-referring-video-object | 25.9 | 25.1 | 25.5 | 5.6 |
| lisa-reasoning-segmentation-via-large | 43.5 | 39.8 | 41.6 | 8.6 |
| the-devil-is-in-temporal-token-high-quality | 62.5 | 57.6 | 60 | 18.9 |
| the-devil-is-in-temporal-token-high-quality | 61.6 | 56.6 | 59.1 | 19.7 |
| language-as-queries-for-referring-video | 29.9 | 26.2 | 28.1 | 8.8 |
| visa-reasoning-video-object-segmentation-via | 52.9 | 48.8 | 50.9 | 14.5 |
| tracking-with-human-intent-reasoning | 46.8 | 43.2 | 45.0 | 12.8 |