Vision Transformer Based Model for Describing a Set of Images as a Story
Open paper
Benchmark
Model
Rank
Results
visual-storytelling-on-vist
ViT-model
–
BLEU-4: 12.3
CIDEr: 4.4
METEOR: 35.4
BLEU-1: 63
BLEU-2: 37.5
…
Rank counts only results with a code link.