Image Captioning on MSCOCO (test server)
40.3BLEU-4 (c5)X-Trans.
Evaluation Results
| Method | Links | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| X-Trans.2022.10 | 40.3 | 81.9 | 95.7 | 66.9 | 90.5 | 52.4 | 82.5 | 72.4 | 29.6 | 39.2 | 59.5 | 75 | 131.1 | 133.5 | — | — | |
| AoANet w/ Dynamic Prophet Attentionensemble=4 models2022.10 | 39.8 | 81.8 | 96.3 | 66.5 | 91.2 | 51.9 | 83.2 | 73.3 | 29.6 | 39.3 | 59.4 | 75.1 | 130.4 | 133.7 | — | — | |
| M2 Trans.2022.10 | 39.7 | 81.6 | 96 | 66.4 | 90.8 | 51.8 | 82.7 | 72.8 | 29.4 | 39 | 59.2 | 74.8 | 129.3 | 132.1 | — | — | |
| AoANet2022.10 | 39.4 | 81 | 95 | 65.8 | 89.6 | 51.4 | 81.3 | 71.2 | 29.1 | 38.5 | 58.9 | 74.5 | 126.9 | 129.6 | — | — | |
| GCN-LSTM2022.10 | 38.7 | — | — | 65.5 | 89.3 | 50.8 | 80.3 | 69.7 | 28.5 | 37.6 | 58.5 | 73.4 | 125.3 | 126.5 | — | — | |
| GLIED2022.10 | 38.5 | 80.1 | 94.6 | 64.7 | 88.9 | 50.2 | 80.4 | 70.3 | 28.6 | 37.9 | 58.3 | 73.8 | 123.3 | 125.6 | — | — | |
| SGAE2022.10 | 38.5 | 81 | 95.3 | 65.6 | 89.5 | 50.7 | 80.4 | 69.7 | 28.2 | 37.2 | 58.6 | 73.6 | 123.8 | 126.5 | — | — | |
| RFNetensemble=4 RFNets2019.08 | 38 | 80.4 | 95 | — | — | — | — | 69.2 | 28.2 | 37.2 | 58.2 | 73.1 | 122.9 | 125.1 | — | — | |
| RDNensemble_size=9, optimization=CIDEr2019.08 | 37.3 | 80.2 | 95.3 | — | — | — | — | 69.5 | 28.1 | 37.8 | 57.4 | 73.3 | 121.2 | 125.2 | — | — | |
| Up-Down2019.08 | 36.9 | 80.2 | 95.2 | — | — | — | — | 68.5 | 27.6 | 36.7 | 57.1 | 72.4 | 117.9 | 120.5 | — | — | |
| Up-Down2022.10 | 36.9 | 80.2 | 95.2 | 64.1 | 88.8 | 49.1 | 79.4 | 68.5 | 27.6 | 36.7 | 57.1 | 72.4 | 117.9 | 120.5 | — | — | |
| Up-Downoptimization=CIDEr, ensemble=4 models2017.07 | 36.9 | 80.2 | 95.2 | 64.1 | 88.8 | 49.1 | 79.4 | 68.5 | 27.6 | 36.7 | 57.1 | 72.4 | 117.9 | 120.5 | 21.5 | 71.5 | |
| LSTM-A32019.08 | 35.6 | 78.7 | 93.7 | — | — | — | — | 65.2 | 27 | 35.4 | 56.4 | 70.5 | 116 | 118 | — | — | |
| LSTM-A32017.07 | 35.6 | 78.7 | 93.7 | 62.7 | 86.7 | 47.6 | 76.5 | 65.2 | 27 | 35.4 | 56.4 | 70.5 | 116 | 118 | — | — | |
| Att2all2019.08 | 35.2 | 78.1 | 93.7 | — | — | — | — | 64.5 | 27 | 35.5 | 56.3 | 70.7 | 114.7 | 116.7 | — | — | |
| SCST:Att2all2017.07 | 35.2 | 78.1 | 93.7 | 61.9 | 86 | 47 | 75.9 | 64.5 | 27 | 35.5 | 56.3 | 70.7 | 114.7 | 116.7 | 20.7 | 68.9 | |
| Adaptive2019.08 | 33.6 | 74.8 | 92 | — | — | — | — | 63.7 | 26.4 | 35.9 | 55 | 70.5 | 104.2 | 105.9 | 19.7 | 67.3 | |
| Adaptive2017.07 | 33.6 | 74.8 | 92 | 58.4 | 84.5 | 44.4 | 74.4 | 63.7 | 26.4 | 35.9 | 55 | 70.5 | 104.2 | 105.9 | 19.7 | 67.3 | |
| PG-BCMR2017.07 | 33.2 | 75.4 | — | 59.1 | — | 44.5 | — | — | 25.7 | — | 55 | — | 101.3 | — | — | — | |
| Review Net2019.08 | 31.3 | 72 | 90 | — | — | — | — | 59.7 | 25.6 | 34.7 | 53.3 | 68.6 | 96.5 | 96.9 | 18.5 | 64.9 | |
| Review Net2017.07 | 31.3 | 72 | 90 | 55 | 81.2 | 41.4 | 70.5 | 59.7 | 25.6 | 34.7 | 53.3 | 68.6 | 96.5 | 96.9 | 18.5 | 64.9 | |
| NIC2019.08 | 30.9 | 71.3 | 89.5 | — | — | — | — | 58.7 | 25.4 | 34.6 | 53 | 68.2 | 94.3 | 94.6 | 18.2 | 63.6 |