M4C-Captioner
Reported on 5 benchmarks across 1 task
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Natural Language Processing5 results
- 18.86best: 22.93 (LSTM-R)
- 80.99best: 103.22 (TAP)
- METEOR19.77best: 21.85 (TAP)
- ROUGE-L43.23best: 46.11 (LSTM-R)
- 12.77best: 14.64 (TAP)