DUBLIN

Reported on 5 benchmarks across 1 task · 1 paper · 3 SOTA

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

Natural Language Processing5 results

Visual Question Answering (VQA)onAI2D
EM· 2023-05-23
51.11
best: 82.5 (SMoLA-PaLI-X Specialist Model)
SOTA
DUBLIN -- Document Understanding By Language-Image Network arXiv:2305.14218
Visual Question Answering (VQA)onWebSRC
EM· 2023-05-23
77.75
SOTA
DUBLIN -- Document Understanding By Language-Image Network arXiv:2305.14218
Visual Question Answering (VQA)onDeepForm
F1· 2023-05-23
62.23
SOTA
DUBLIN -- Document Understanding By Language-Image Network arXiv:2305.14218
Visual Question Answering (VQA)onDocVQA test
ANLS· uses extra data· 2023-05-23
0.782
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
36.82
best: 80.3 (Gemini Ultra (pixel only))
DUBLIN -- Document Understanding By Language-Image Network arXiv:2305.14218