How Much Can CLIP Benefit Vision-and-Language Tasks?
Open paper
Benchmark
Model
Rank
Results
vision-and-language-navigation-on-rxr
CLEAR-CLIP
#3
ndtw: 53.69
visual-entailment-on-snli-ve-val
CLIP-ViL
#6
Accuracy: 80.20
Rank counts only results with a code link.