Transitional Adaptation of Pretrained Models for Visual Storytelling

Open paper
Benchmark Model Rank Results
visual-storytelling-on-vistTAPM–CIDEr: 13.8METEOR: 37.2ROUGE-L: 33.1
visual-storytelling-on-vistTAPM (no V&L)–CIDEr: 8.3METEOR: 34.1ROUGE-L: 30.2

Rank counts only results with a code link.