| image-captioning-on-coco-captions | LEMON | – | BLEU-4: 42.6CIDER: 145.5METEOR: 31.4SPICE: 25.5 |
| image-captioning-on-nocaps-val-in-domain | LEMON_base | – | CIDEr: 107.7SPICE: 14.7Pre-train (#images): 200M |
| image-captioning-on-nocaps-val-in-domain | LEMON_large | – | CIDEr: 116.9SPICE: 15.8Pre-train (#images): 200M |
| image-captioning-on-nocaps-val-near-domain | LEMON_large | – | CIDEr: 113.3SPICE: 15.1Pre-train (#images): 200M |
| image-captioning-on-nocaps-val-out-domain | LEMON_large | – | CIDEr: 111.3SPICE: 14.0Pretrain (#images): 200M |
| image-captioning-on-nocaps-val-overall | LEMON_large | – | CIDEr: 113.4SPICE: 15.0Pretrain (#images): 200M |
| image-captioning-on-nocaps-xd-entire | Microsoft Cognitive Services team | – | CIDEr: 114.25B1: 85.62B2: 71.36B3: 53.62B4: 34.65… |