Referring Video Object Segmentation On Refer
평가 지표
F
J
Ju0026F
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | F | J | Ju0026F |
|---|---|---|---|
| html-hybrid-temporal-scale-multimodal | 63.0 | 59.5 | 61.2 |
| towards-temporally-consistent-referring-video | 68.9 | 65.3 | 67.1 |
| vlt-vision-language-transformer-and-query | 65.6 | 61.9 | 63.8 |
| general-object-foundation-model-for-images | 69.7 | 65.6 | 67.7 |
| html-hybrid-temporal-scale-multimodal | 65.3 | 61.5 | 63.4 |
| language-as-queries-for-referring-video | 64.6 | 61.3 | 62.9 |
| soc-semantic-assisted-object-cluster-for | 67.9 | 64.1 | 66.0 |
| html-hybrid-temporal-scale-multimodal | 65.2 | 61.5 | 63.4 |
| html-hybrid-temporal-scale-multimodal | 59.8 | 57.3 | 58.5 |
| html-hybrid-temporal-scale-multimodal | 59.0 | 56.5 | 57.8 |
| improving-referring-image-segmentation-using | 67.5 | 63.3 | 65.4 |
| cross-modal-self-attention-network-for | 38.1 | 34.8 | 36.4 |
| spectrum-guided-multi-granularity-referring | 67.4 | 63.9 | 65.7 |
| general-object-foundation-model-for-images | 72.9 | 68.2 | 70.6 |
| find-first-track-next-decoupling | 72.0 | 68.6 | 70.3 |
| hyperseg-towards-universal-visual | - | - | 68.5 |
| r-2vos-robust-referring-video-object | 61.5 | 58.9 | 60.2 |
| html-hybrid-temporal-scale-multimodal | 62.9 | 59.9 | 61.4 |