Image Captioning On Vizwiz 2020 Test
평가 지표
B1
B2
B3
B4
CIDEr
METEOR
ROUGE-L
SPICE
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | B1 | B2 | B3 | B4 | CIDEr | METEOR | ROUGE-L | SPICE | Paper Title | Repository |
|---|---|---|---|---|---|---|---|---|---|---|
| IBM Research AI | 72.77 | 54.17 | 38.97 | 27.44 | 81.04 | 22.25 | 50.2 | 17.0 | - | - |
| Test533 | 58.58 | 39.57 | 26.49 | 17.71 | 37.18 | 16.57 | 40.75 | 11.06 | - | - |
| NLP-Course | 54.25 | 37.12 | 24.75 | 15.91 | 29.14 | 14.78 | 38.5 | 9.86 | - | - |
| NLP-685 | 66.62 | 47.41 | 32.66 | 22.34 | 56.19 | 19.54 | 46.42 | 14.72 | - | - |
| aburns | 65.9 | 47.25 | 32.87 | 22.91 | 59.61 | 20.08 | 46.61 | 15.22 | - | - |
| justatest | 30.1 | 19.03 | 11.7 | 7.39 | 14.67 | 9.17 | 29.07 | 5.07 | - | - |
| parambole | 61.47 | 42.4 | 28.4 | 18.69 | 37.82 | 16.68 | 42.03 | 11.48 | - | - |
| Team SSP | 65.7 | 47.15 | 32.97 | 22.8 | 59.56 | 19.79 | 46.38 | 14.88 | - | - |
| CASIA_IVA | 71.97 | 53.59 | 38.94 | 27.96 | 77.7 | 21.93 | 49.9 | 17.79 | - | - |
| BUTD-Test | 60.98 | 41.98 | 28.15 | 18.52 | 36.99 | 16.55 | 41.77 | 11.36 | - | - |
| cs685-nlp-aoa-e | 64.93 | 46.44 | 32.42 | 22.29 | 53.84 | 18.64 | 44.96 | 14.08 | - | - |
| RUC_AIM3 | 68.0 | 49.37 | 35.24 | 25.05 | 72.72 | 20.46 | 47.43 | 15.98 | - | - |
| Wizards of VizWiz | 57.86 | 40.24 | 27.24 | 17.98 | 34.93 | 15.99 | 40.53 | 10.86 | - | - |
0 of 13 row(s) selected.