VLCap: Vision-Language with Contrastive Learning for Coherent Video Paragraph Captioning
Open paper
Benchmark
Model
Rank
Results
video-captioning-on-activitynet-captions
VLCap (ae-test split) - Appearance + Language
#2
BLEU4: 13.38
CIDEr: 31.29
ROUGE-L: 35.99
METEOR: 17.48
Rank counts only results with a code link.