NMN+LSTM+FT

Reported on 2 benchmarks across 1 task · 1 paper · 1 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 v1 test-dev
Accuracy· 2015-11-09
58.6
best: 64.5 (SAAA (ResNet))
SOTA
Neural Module Networks arXiv:1511.02799
Visual Question Answering (VQA)onVQA v1 test-std
Accuracy· 2015-11-09
58.7
best: 64.6 (SAAA (ResNet))
Neural Module Networks arXiv:1511.02799