Accuracy: 0.440
Papers with Code · CC BY-SA 4.0
Visual Question Answering (VQA)
Visual Question Answering (VQA) is a task in computer vision that involves answering questions about an image. The goal of VQA is to teach machines to understand the content of an image and answer questions about it in natural language.
Image Source: visualqa.org
논문
EM: 82.5
Accuracy: 0.455
Accuracy: 0.421
Accuracy: 0.443
Accuracy: 0.441
Accuracy: 87
EM: 51.11
Accuracy: 0.458
Accuracy: 0.474
EM: 79.5
Accuracy: 0.459
Accuracy: 0.471
Accuracy: 0.42
Accuracy: 0.495
Accuracy: 0.480
Accuracy: 0.478
Accuracy: 88.2
Accuracy: 0.441
Accuracy: 0.470
Accuracy: 0.471
Accuracy: 0.470
Accuracy: .457
Video-Text as Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning
Accuracy: 0.462
Accuracy: 0.463
Accuracy: 0.496