RTT-GAN (Semi + Fully)
Reported on 3 benchmarks across 1 task · 1 paper · 3 SOTA
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Graphs3 results
- BLEU-4· 2017-03-21SOTA9.21best: 11.26 (HSGED(SLL))
- CIDEr· 2017-03-21SOTA20.36best: 36.02 (HSGED(SLL))
- METEOR· 2017-03-21SOTA18.39best: 18.82 (CAE-LSTM)