3D-VLP

Reported on 4 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 Processing4 results

Image CaptioningonScanRefer Dataset
BLEU-4
31.87
best: 45.56 (3D CoCa)
Image CaptioningonScanRefer Dataset
CIDEr
50.02
best: 85.42 (3D CoCa)
Image CaptioningonScanRefer Dataset
METEOR
24.53
best: 30.95 (3D CoCa)
Image CaptioningonScanRefer Dataset
ROUGE-L
51.17
best: 61.98 (3D CoCa)