GbS Ensemble MS-COCO

Reported on 3 benchmarks across 1 task · 1 paper

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

Natural Language Processing3 results

Phrase GroundingonVisual Genome
Pointing Game Accuracy· 2021-04-20
54.55
best: 55.91 (GbS VG)
Detector-Free Weakly Supervised Grounding by Separation arXiv:2104.09829
Phrase GroundingonFlickr30k
Pointing Game Accuracy· 2021-04-20
75.6
best: 85.9 (GBS Ensemble + 12-in-1)
Detector-Free Weakly Supervised Grounding by Separation arXiv:2104.09829
Phrase GroundingonReferIt
Pointing Game Accuracy· 2021-04-20
58.21
best: 62.76 (VG_BiLSTM_VGG)
Detector-Free Weakly Supervised Grounding by Separation arXiv:2104.09829