Late Fusion (Bert + InceptionV3)

Reported on 2 benchmarks across 2 tasks

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

Methodology1 result

Multimodal Deep LearningonFood-101
Accuracy (%)
84.59
best: 92.5 (Early Fusion (Bert + InceptionV3))

Natural Language Processing1 result

Multimodal Text and Image ClassificationonFood-101
Accuracy (%)
84.59
best: 92.5 (Early Fusion (Bert + InceptionV3))