Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Scene Text Visual Question Answering on ST-VQA

68.96Accuracy

Qwen 2.5 VL + ViCrop (rel-att)

51.820856.270460.7265.1696Nov 25, 2025
Updated 4d ago

Evaluation Results

MethodLinks
2025.11
68.96
2025.11
68.31
2025.11
68.09
2025.11
67.91
2025.11
65.49
2025.11
59.3
2025.11
57.06
2025.11
56.95
2025.11
56.81
2025.11
52.48