Commonsense Knowledge Aware Concept Selection For Diverse and Informative Visual Storytelling

Open paper
Benchmark Model Rank Results
visual-storytelling-on-vistMCSM+RNN–BLEU-4: 13CIDEr: 11METEOR: 36.1BLEU-3: 23.1ROUGE-L: 30.7

Rank counts only results with a code link.