MCANed-6

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· 2019-06-25
70.63
best: 84.3 (PaLI)
SOTA
Deep Modular Co-Attention Networks for Visual Question Answering arXiv:1906.10770
Visual Question Answering (VQA)onVQA v2 test-std
overall· 2019-06-25
70.9
best: 84.03 (BEiT-3)
SOTA
Deep Modular Co-Attention Networks for Visual Question Answering arXiv:1906.10770