NS-VQA (1K programs)

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)onCLEVR
Accuracy· 2018-10-04
99.8
SOTA
Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding arXiv:1810.02338
Visual Question Answering (VQA)onCLEVR-Humans
Accuracy· 2018-10-04
67.8
best: 81.7 (MDETR)
Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding arXiv:1810.02338