Image Retrieval On Photochat
Metriken
R1
R@10
R@5
Sum(R@1,5,10)
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | R1 | R@10 | R@5 | Sum(R@1,5,10) |
|---|---|---|---|---|
| vlmo-unified-vision-language-pre-training | 11.5 | 39.4 | 30.0 | 83.2 |
| vilt-vision-and-language-transformer-without | 11.5 | 25.6 | 33.8 | 71.0 |
| pace-unified-multi-modal-dialogue-pre | 15.2 | 49.6 | 36.7 | 101.5 |
| stacked-cross-attention-for-image-text | 10.4 | 37.1 | 27.0 | 74.5 |
| photochat-a-human-human-dialogue-dataset-with | 9.0 | 35.7 | 26.4 | 71.1 |