Referring Video Object Segmentation On Ref
Metriken
F
J
Ju0026F
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | F | J | Ju0026F |
|---|---|---|---|
| find-first-track-next-decoupling | 78.5 | 69.9 | 74.2 |
| decoupling-static-and-hierarchical-motion | 68.1 | 61.7 | 64.9 |
| soc-semantic-assisted-object-cluster-for | 69.1 | 62.5 | 65.8 |
| urvos-unified-referring-video-object | 56.0 | 47.3 | 51.6 |
| html-hybrid-temporal-scale-multimodal | 65.1 | 59.2 | 62.1 |
| spectrum-guided-multi-granularity-referring | 66.0 | 60.6 | 63.3 |
| exploring-pre-trained-text-to-video-diffusion | 72.6 | 66.2 | 69.4 |
| referred-by-multi-modality-a-unified-temporal | 71.3 | 64.8 | 68.0 |
| language-as-queries-for-referring-video | 64.1 | 58.1 | 61.1 |
| losh-long-short-text-joint-prediction-network | 66.8 | 61.8 | 64.3 |
| language-bridged-spatial-temporal-interaction-1 | - | - | 54.5 |