Depth-aware Attention Model (DAM)

Reported on 3 benchmarks across 1 task

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

Graphs3 results

Image Paragraph CaptioningonImage Paragraph Captioning
BLEU-4
6.7
best: 11.26 (HSGED(SLL))
Image Paragraph CaptioningonImage Paragraph Captioning
CIDEr
17.3
best: 36.02 (HSGED(SLL))
Image Paragraph CaptioningonImage Paragraph Captioning
METEOR
13.9
best: 18.82 (CAE-LSTM)