DUBLIN (variable resolution)

Reported on 2 benchmarks across 1 task · 1 paper

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)onDocVQA test
ANLS· uses extra data· 2023-05-23
0.803
best: 0.9436 (Human)
DUBLIN -- Document Understanding By Language-Image Network arXiv:2305.14218
Visual Question Answering (VQA)onInfographicVQA
ANLS· uses extra data· 2023-05-23
42.6
best: 80.3 (Gemini Ultra (pixel only))
DUBLIN -- Document Understanding By Language-Image Network arXiv:2305.14218