Metric: R@1 (higher is better)
| # | Model↕ | R@1▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | 2 Step: Factor Graph Attention + VD-Bert | 58.3 | No | Ensemble of MRR and NDCG models for Visual Dialog | 2021-04-15 | Code |
| 2 | MRR ensemble (Naive) | 58.27 | No | - | - | - |
| 3 | Two-Step(refactor) | 58.17 | No | - | - | - |
| 4 | Ensemble FGA + BERT | 57.07 | No | - | - | - |
| 5 | 5xFGA (F-RCNNx101) | 55.65 | No | Factor Graph Attention | 2019-04-11 | Code |
| 6 | CAF | 54.67 | No | - | - | - |
| 7 | bert-double-stream-finetuning | 54.37 | No | - | - | - |
| 8 | w/ VQA + CC, single model | 53.85 | No | - | - | - |
| 9 | test1 | 53.85 | No | - | - | - |
| 10 | sh101 | 53.75 | No | - | - | - |
| 11 | Transformer+2cons | 52.62 | No | - | - | - |
| 12 | SCL_48 | 52.52 | No | - | - | - |
| 13 | CARE(Single Model) | 51.82 | No | - | - | - |
| 14 | Bert2constraints | 51.73 | No | - | - | - |
| 15 | single model | 51.62 | No | - | - | - |
| 16 | MVAN | 51.45 | No | Multi-View Attention Network for Visual Dialog | 2020-04-29 | Code |
| 17 | jiuyigedian | 51.32 | No | - | - | - |
| 18 | gr | 51.25 | No | - | - | - |
| 19 | 1 | 50.88 | No | - | - | - |
| 20 | HACAN | 50.88 | No | Making History Matter: History-Advantage Sequenc... | 2019-02-25 | - |
| 21 | zxcdd | 50.8 | No | - | - | - |
| 22 | Bert(two-stream) | 50.78 | No | - | - | - |
| 23 | disc | 50.7 | No | - | - | - |
| 24 | 211 | 50.62 | No | - | - | - |
| 25 | zuizhong | 50.58 | No | - | - | - |
| 26 | single-model | 50.48 | No | - | - | - |
| 27 | lijunlin_7 | 50.3 | No | - | - | - |
| 28 | CAG | 49.85 | No | Iterative Context-Aware Graph Inference for Visu... | 2020-04-05 | Code |
| 29 | clean_wac_4freeze | 49.75 | No | - | - | - |
| 30 | lijunlin_9 | 49.68 | No | - | - | - |
| 31 | DAN | 49.63 | No | Dual Attention Networks for Visual Reference Res... | 2019-02-25 | Code |
| 32 | lkh(single-model) | 49.48 | No | - | - | - |
| 33 | DualVD | 49.25 | No | DualVD: An Adaptive Dual Encoding Model for Deep... | 2019-11-17 | Code |
| 34 | ERIC666 | 49.18 | No | - | - | - |
| 35 | RVA | 49.03 | No | Recursive Visual Attention in Visual Dialog | 2018-12-06 | Code |
| 36 | kbgn_disc_5 | 48.6 | No | - | - | - |
| 37 | wqedasd(single model) | 48.4 | No | - | - | - |
| 38 | Synergistic | 47.9 | No | Image-Question-Answer Synergistic Network for Vi... | 2019-02-26 | - |
| 39 | eightepoch | 47.58 | No | - | - | - |
| 40 | CorefNMN (ResNet-152) | 47.55 | No | Visual Coreference Resolution in Visual Dialog u... | 2018-09-06 | Code |
| 41 | single-model | 47.45 | No | - | - | - |
| 42 | GNN | 47.33 | No | Reasoning Visual Dialogs with Structural and Par... | 2019-04-11 | Code |
| 43 | DLC-4 | 46.83 | No | - | - | - |
| 44 | jkl | 46.35 | No | - | - | - |
| 45 | adasd | 45.6 | No | - | - | - |
| 46 | 1 | 45.42 | No | - | - | - |
| 47 | shanshandu | 45.3 | No | - | - | - |
| 48 | Ensemble + Fine-tuning | 45.17 | No | - | - | - |
| 49 | 1 | 45.17 | No | - | - | - |
| 50 | 1 | 44.82 | No | - | - | - |
| 51 | VD-PCR | 44.75 | No | - | - | - |
| 52 | P1P2+Distill+Ensemble | 44.45 | No | - | - | - |
| 53 | ensemble, finetune | 44.32 | No | - | - | - |
| 54 | sdfsdaf | 44.27 | No | - | - | - |
| 55 | 1 | 44.22 | No | - | - | - |
| 56 | 7 | 44.2 | No | - | - | - |
| 57 | NMN | 44.15 | No | Learning to Reason: End-to-End Module Networks f... | 2017-04-18 | Code |
| 58 | Disc, Dense, 4 Ensemble. | 43.23 | No | - | - | - |
| 59 | gat_disc_relto_4 | 42.7 | No | - | - | - |
| 60 | gat_disc_3 | 41.4 | No | - | - | - |
| 61 | MN-QIH-D | 40.98 | No | Visual Dialog | 2016-11-26 | Code |
| 62 | MN-QIH-D | 40.95 | No | Visual Dialog | 2016-11-26 | Code |
| 63 | HRE-QIH-D | 39.93 | No | Visual Dialog | 2016-11-26 | Code |
| 64 | Ensemble + Finetune | 38.92 | No | Efficient Attention Mechanism for Visual Dialog ... | 2019-11-26 | Code |
| 65 | Ensemble | 38.9 | No | - | - | - |
| 66 | CE-finetuned, single model | 37.95 | No | - | - | - |
| 67 | mvan_len40_test | 36.93 | No | - | - | - |
| 68 | paratraining1epoch | 36.83 | No | - | - | - |
| 69 | 2 | 36.35 | No | - | - | - |
| 70 | trainval_ch_9 | 35.9 | No | - | - | - |
| 71 | 5-2 | 35.88 | No | - | - | - |
| 72 | 10 | 35.77 | No | - | - | - |
| 73 | 5_4 | 34.65 | No | - | - | - |
| 74 | 20 | 33.5 | No | - | - | - |
| 75 | Single | 29.5 | No | - | - | - |
| 76 | 2 | 27.82 | No | - | - | - |
| 77 | simple_test | 25.85 | No | - | - | - |
| 78 | 5TS | 25.65 | No | - | - | - |
| 79 | czczx | 16.62 | No | - | - | - |
| 80 | qqhe | 3.02 | No | - | - | - |