Unicoder-VL

Reported on 4 benchmarks across 4 tasks · 1 paper · 4 SOTA

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

Miscellaneous2 results

Image Retrieval with Multi-Modal QueryonCommercialAdsDataset
ADD(S) AUC· 2019-08-16
83.16
best: 91.73 (AlignCMSS)
SOTA
Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training arXiv:1908.06066
Cross-Modal Information RetrievalonCommercialAdsDataset
ADD(S) AUC· 2019-08-16
83.16
best: 91.73 (AlignCMSS)
SOTA
Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training arXiv:1908.06066

Natural Language Processing2 results

Cross-Modal RetrievalonCommercialAdsDataset
ADD(S) AUC· 2019-08-16
83.16
best: 91.73 (AlignCMSS)
SOTA
Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training arXiv:1908.06066
Image-to-Text RetrievalonCOCO (Common Objects in Context)
Recall@10· 2019-08-16
97.2
best: 99.8 (Oscar)
SOTA
Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training arXiv:1908.06066