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.
Papers
Showing 1–10 of 82 papers
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | Yu et. al [[Yu et al.2017a]] | R@100 | 31.89 | — | Unverified |
| 2 | vrd-dsr | R@100 | 23.29 | — | Unverified |
| 3 | BLOCK | R@100 | 20.96 | — | Unverified |
| 4 | Dai et. al [[Dai, Zhang, and Lin2017]] | R@100 | 20.88 | — | Unverified |
| 5 | Liang et. al [[Liang, Lee, and Xing2017]] | R@100 | 20.79 | — | Unverified |
| 6 | Peyre et. al [[Peyre et al.2017]] | R@100 | 17.1 | — | Unverified |
| 7 | Zhang et. al [[Hanwang Zhang2017]] | R@100 | 15.2 | — | Unverified |
| 8 | Lu et. al [[Lu et al.2016]] | R@100 | 14.7 | — | Unverified |