MTTSNet

Reported on 1 benchmark across 1 task · 1 paper · 1 SOTA

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

Natural Language Processing1 result

Image Captioningonrelational captioning dataset
Image-Level Recall· 2019-03-14
34.27
best: 45.96 (MTTSNet (extended))
SOTA
Dense Relational Captioning: Triple-Stream Networks for Relationship-Based Captioning arXiv:1903.05942