VisionTapas-OCR

Reported on 4 benchmarks across 2 tasks · 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)onChartQA
1:1 Accuracy· 2022-03-19
45.5
best: 81.3 (ChartPaLI-5B + PaLM 2-S)
SOTA
ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning arXiv:2203.10244
Visual Question Answering (VQA)onPlotQA
1:1 Accuracy· 2022-03-19
53.9
best: 92.89 (MatCha4096 + LaMenDa)
ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning arXiv:2203.10244

Computer Code2 results

Chart Question AnsweringonChartQA
1:1 Accuracy· 2022-03-19
45.5
best: 81.3 (ChartPaLI-5B + PaLM 2-S)
SOTA
ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning arXiv:2203.10244
Chart Question AnsweringonPlotQA
1:1 Accuracy· 2022-03-19
53.9
best: 92.89 (MatCha4096 + LaMenDa)
ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning arXiv:2203.10244