Accuracy: 87.0
Papers with Code · CC BY-SA 4.0
Visual Entailment
Visual Entailment (VE) - is a task consisting of image-sentence pairs whereby a premise is defined by an image, rather than a natural language sentence as in traditional Textual Entailment tasks. The goal is to predict whether the image semantically entails the text.
논문
Accuracy: 80.9
Accuracy: 91.0
Accuracy: 90.04
Accuracy: 85.00
Accuracy: 86.21
Accuracy: 78.98
Accuracy: 70.81
Accuracy: 80.20
Accuracy: 80.18
Accuracy: 80.32