Visual Dialog On Visual Dialog V1 0 Test Std
评估指标
MRR (x 100)
Mean
NDCG (x 100)
R@1
R@10
R@5
评测结果
各个模型在此基准测试上的表现结果
模型名称 | MRR (x 100) | Mean | NDCG (x 100) | R@1 | R@10 | R@5 | Paper Title | Repository |
|---|---|---|---|---|---|---|---|---|
| MVAN | 64.84 | 3.97 | 59.37 | 51.45 | 90.65 | 81.12 | Multi-View Attention Network for Visual Dialog | |
| ensemble, finetune | 56.42 | 5.47 | 76.17 | 44.32 | 84.52 | 70.23 | - | - |
| disc | 64.43 | 4.13 | 58.19 | 50.7 | 90.18 | 80.83 | - | - |
| 1 | 57.13 | 5.85 | 72.33 | 45.17 | 82.4 | 69.95 | - | - |
| jiuyigedian | 64.79 | 3.98 | 58.25 | 51.32 | 90.38 | 81.0 | - | - |
| VD-PCR | 56.05 | 5.72 | 76.14 | 44.75 | 82.75 | 68.4 | - | - |
| 5xFGA (F-RCNNx101) | 69.3 | 3.14 | 57.20 | 55.65 | 94.05 | 86.73 | Factor Graph Attention | |
| RVA | 63.03 | 4.18 | 55.59 | 49.03 | 89.83 | 80.40 | Recursive Visual Attention in Visual Dialog | |
| 5_4 | 48.37 | 7.05 | 73.08 | 34.65 | 77.53 | 62.98 | - | - |
| lijunlin_7 | 63.7 | 4.26 | 58.59 | 50.3 | 89.15 | 79.47 | - | - |
| gat_disc_3 | 53.19 | 11.96 | 47.51 | 41.4 | 74.15 | 65.85 | - | - |
| Disc, Dense, 4 Ensemble. | 55.11 | 6.55 | 72.41 | 43.23 | 79.77 | 67.65 | - | - |
| Ensemble + Fine-tuning | 56.35 | 5.79 | 76.43 | 45.17 | 82.17 | 68.12 | - | - |
| SCL_48 | 66.63 | 3.41 | 60.91 | 52.52 | 92.27 | 84.1 | - | - |
| HRE-QIH-D | 54.2 | 6.41 | 45.5 | 39.93 | 81.50 | 70.45 | Visual Dialog | |
| bert-double-stream-finetuning | 62.65 | 5.89 | 74.62 | 54.37 | 83.33 | 70.75 | - | - |
| Ensemble + Finetune | 52.14 | 6.53 | 74.88 | 38.92 | 80.65 | 66.6 | Efficient Attention Mechanism for Visual Dialog that can Handle All the Interactions between Multiple Inputs | |
| P1P2+Distill+Ensemble | 56.2 | 5.41 | 77.92 | 44.45 | 83.78 | 68.9 | - | - |
| DLC-4 | 61.09 | 4.65 | 52.57 | 46.83 | 87.42 | 78.22 | - | - |
| 5-2 | 49.03 | 7.07 | 72.85 | 35.88 | 77.75 | 62.88 | - | - |
0 of 80 row(s) selected.