BAN+Glove+Counter

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· 2018-05-21
70.04
best: 84.3 (PaLI)
SOTA
Bilinear Attention Networks arXiv:1805.07932
Visual Question Answering (VQA)onVQA v2 test-std
overall· 2018-05-21
70.4
best: 84.03 (BEiT-3)
SOTA
Bilinear Attention Networks arXiv:1805.07932