MUTAN

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

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

Natural Language Processing2 results

Visual Question Answering (VQA)onVQA v2 test-dev
Accuracy· 2017-05-18
67.42
best: 84.3 (PaLI)
SOTA
MUTAN: Multimodal Tucker Fusion for Visual Question Answering arXiv:1705.06676
Visual Question Answering (VQA)onVQA v2 test-std
overall· 2017-05-18
67.4
best: 84.03 (BEiT-3)
SOTA
MUTAN: Multimodal Tucker Fusion for Visual Question Answering arXiv:1705.06676