Check

Reported on 8 benchmarks across 1 task

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing8 results

Image Captioningonnocaps out-of-domain
B1
47.08
best: 86.28 (PaLI)
Image Captioningonnocaps out-of-domain
B2
22.24
best: 71.28 (GIT, Single Model)
Image Captioningonnocaps out-of-domain
B3
7.41
best: 52.66 (GIT, Single Model)
Image Captioningonnocaps out-of-domain
B4
1.83
best: 32 (PaLI)
Image Captioningonnocaps out-of-domain
CIDEr
36.12
best: 126.67 (PaLI)
Image Captioningonnocaps out-of-domain
METEOR
17.94
best: 30.99 (PaLI)
Image Captioningonnocaps out-of-domain
ROUGE-L
31.57
best: 61.35 (PaLI)
Image Captioningonnocaps out-of-domain
SPICE
9.39
best: 15.7 (GIT, Single Model)