BLOCK: Bilinear Superdiagonal Fusion for Visual Question Answering and Visual Relationship Detection
R@100: 20.96R@50: 19.06
Papers with Code · CC BY-SA 4.0
Visual Relationship Detection
Visual relationship detection (VRD) is one newly developed computer vision task aiming to recognize relations or interactions between objects in an image. It is a further learning task after object recognition and is essential for fully understanding images, even the visual world.
논문
R@100: 20.88R@50: 17.73
R@100: 31.89R@50: 22.68
R@100: 14.70R@50: 13.86
R@100: 15.20R@50: 14.07
R@100: 17.1R@50: 15.8
R@100: 20.79R@50: 18.19
Recall@50: 13.73Recall@100: 16.88mAP: 20.08
R@100: 23.29R@50: 19.03
Recall@50: 11.56Recall@100: 14.13mAP: 18.9
R@50 k=1: 15
R@50: 64.4R@100: 66.3mR@50: 21.7mR@100: 23.5