VLTinT: Visual-Linguistic Transformer-in-Transformer for Coherent Video Paragraph Captioning
Open paper
Benchmark
Model
Rank
Results
video-captioning-on-activitynet-captions
VLTinT (ae-test split) C3D/Ling
#1
BLEU4: 14.5
CIDEr: 31.13
ROUGE-L: 36.56
METEOR: 17.97
Rank counts only results with a code link.