MCB

Reported on 4 benchmarks across 2 tasks · 2 papers · 3 SOTA

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

Natural Language Processing4 results

Visual Question Answering (VQA)onVQA v2 test-dev
Accuracy· 2016-06-06
64.7
best: 84.3 (PaLI)
SOTA
Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding arXiv:1606.01847
Phrase GroundingonReferIt
Accuracy· 2016-06-06
28.91
SOTA
Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding arXiv:1606.01847
Phrase GroundingonFlickr30k Entities Test
R@1· 2016-06-06
48.69
best: 87.7 (GLIPv2)
SOTA
Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding arXiv:1606.01847
Visual Question Answering (VQA)onCOCO Visual Question Answering (VQA) real images 2.0 open ended
Percentage correct· 2016-12-02
62.27
best: 80.7 (MaMMUT (2B))
Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering arXiv:1612.00837