single-hop + LCGN (ours)

Reported on 3 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 Processing3 results

Visual Question Answering (VQA)onGQA test-std
Accuracy· 2019-05-10
56.1
best: 65.14 (ProTo)
SOTA
Language-Conditioned Graph Networks for Relational Reasoning arXiv:1905.04405
Visual Question Answering (VQA)onGQA test-dev
Accuracy· 2019-05-10
55.8
best: 72.1 (CFR)
SOTA
Language-Conditioned Graph Networks for Relational Reasoning arXiv:1905.04405
Visual Question Answering (VQA)onCLEVR
Accuracy· 2019-05-10
97.9
best: 99.8 (NS-VQA (1K programs))
Language-Conditioned Graph Networks for Relational Reasoning arXiv:1905.04405