UNITER + MAC + Graph Networks

Reported on 7 benchmarks across 1 task

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

Natural Language Processing7 results

Visual Question Answering (VQA)onGQA Test2019
Accuracy
59.29
best: 89.3 (human)
Visual Question Answering (VQA)onGQA Test2019
Binary
77.31
best: 91.2 (human)
Visual Question Answering (VQA)onGQA Test2019
Consistency
88.94
best: 98.4 (human)
Visual Question Answering (VQA)onGQA Test2019
Distribution
5.8
best: 93.08 (GlobalPrior)
Visual Question Answering (VQA)onGQA Test2019
Open
43.38
best: 87.4 (human)
Visual Question Answering (VQA)onGQA Test2019
Plausibility
84.43
best: 97.2 (human)
Visual Question Answering (VQA)onGQA Test2019
Validity
96.3
best: 98.9 (human)