VideoBERT: A Joint Model for Video and Language Representation Learning
Open paper
Benchmark
Model
Rank
Results
video-captioning-on-youcook2
VideoBERT + S3D
#10
BLEU-4: 4.33
BLEU-3: 7.59
CIDEr: 0.55
ROUGE-L: 28.80
METEOR: 11.94
Rank counts only results with a code link.