BUTD-Test

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 CaptioningonVizWiz 2020 test
B1
60.98
best: 72.77 (IBM Research AI)
Image CaptioningonVizWiz 2020 test
B2
41.98
best: 54.17 (IBM Research AI)
Image CaptioningonVizWiz 2020 test
B3
28.15
best: 38.97 (IBM Research AI)
Image CaptioningonVizWiz 2020 test
B4
18.52
best: 27.96 (CASIA_IVA)
Image CaptioningonVizWiz 2020 test
CIDEr
36.99
best: 81.04 (IBM Research AI)
Image CaptioningonVizWiz 2020 test
METEOR
16.55
best: 22.25 (IBM Research AI)
Image CaptioningonVizWiz 2020 test
ROUGE-L
41.77
best: 50.2 (IBM Research AI)
Image CaptioningonVizWiz 2020 test
SPICE
11.36
best: 17.79 (CASIA_IVA)