UNIMO-large

Reported on 2 benchmarks across 1 task · 1 paper · 1 SOTA

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

Natural Language Processing2 results

Image CaptioningonCOCO (Common Objects in Context)
BLEU-4· 2020-12-31
39.6
best: 39.9 (IGINet)
SOTA
UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning arXiv:2012.15409
Image CaptioningonCOCO (Common Objects in Context)
CIDEr· 2020-12-31
127.7
best: 143.7 (ExpansionNet v2)
UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning arXiv:2012.15409