| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Relation Detection | VRD (test) | R@5063.4 | 75 | |
| Phrase Detection | VRD (test) | R@5033.8 | 36 | |
| Relationship phrase detection | VRD | Recall@5086.46 | 20 | |
| Relationship phrase detection | VRD (test) | Recall@10094.65 | 17 | |
| Phrase Detection | VRD | R@50 (k=1)33.8 | 13 | |
| Phrase Detection | VRD 1.0 (test) | Recall @ IoU=1.00 (All)19.5 | 11 | |
| Relationship Detection | VRD zero-shot (test) | Recall@507.1 | 10 | |
| Phrase Detection | VRD zero-shot (test) | R@507.4 | 10 | |
| Predicate Detection | VRD zero-shot (test) | R@5023.6 | 10 | |
| Union Box Detection | VRD | Recall@500.1993 | 9 | |
| Predicate Detection | VRD 1.0 (test) | Recall @ 10047.87 | 8 | |
| Relationship detection | VRD | Recall@5019.26 | 8 | |
| Relationship Detection | VRD Zero-Shot | R@100 (k=1)9.75 | 7 | |
| Phrase Detection | VRD zero-shot | R@100 (k=1)11.23 | 7 | |
| Relation Retrieval | VRD (test) | Rr@52.82 | 7 | |
| Relationship Detection | VRD 1.0 (test) | Recall@10014.7 | 7 | |
| Scene Graph Generation | VRD (test) | Recall@5018.32 | 6 | |
| Visual Phrase Detection | VRD (test) | Recall@5026.03 | 6 | |
| Relation Retrieval | VRD zero-shot | Rr@51.42 | 4 | |
| Image Segmentation | VRD (test) | I-Seg43.9 | 4 | |
| Relation Extraction | VRD (test) | RE Score26 | 4 | |
| Relation Detection | VRD zero-shot 1,877 relations | Recall@507.14 | 4 | |
| Visual Relationship Detection | VRD 55 (test) | S-IoU (No Subject)0.568 | 3 | |
| Relation Retrieval | VRD zero-shot 1,877 relations | R@5- | 0 | |
| Phrase Detection | VRD zero-shot 1,877 relations | Recall@50- | 0 |