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

Multi-modal Visual Question Answering on VQA-T

64.84Accuracy

16-bit Baseline

49.458453.451757.44561.4383Nov 15, 2024
Updated 1mo ago

Evaluation Results

MethodLinks
2024.11
64.84
2024.11
59.13
2024.11
57.88
2024.11
50.05