Image-to-Recipe Retrieval on Recipe1M 10k setup (test)
65.5Recall@1SIMMER (V1-7B)
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| SIMMER (V1-7B)Venue=-2026.04 | 65.5 | 1 | 87.4 | 92.5 | |
| SIMMERModel Version=V1, Parameter Count=7B2026.04 | 65.5 | 1 | 87.4 | 92.5 | |
| SIMMER (V1-2B)Venue=-2026.04 | 59.7 | 1 | 83.5 | 89.9 | |
| SIMMERModel Version=V1, Parameter Count=2B2026.04 | 59.7 | 1 | 83.5 | 89.9 | |
| SIMMER (V2)Venue=-2026.04 | 59.1 | 1 | 83.3 | 89.8 | |
| SIMMERModel Version=V22026.04 | 59.1 | 1 | 83.3 | 89.8 | |
| TNLBTVenue=MMM’232026.04 | 56.5 | 1 | 80.7 | 87.1 | |
| Yang et al.Venue=ICMRW’242026.04 | 56.5 | 1 | 81 | 87.6 | |
| TNLBT2026.04 | 56.5 | 1 | 80.7 | 87.1 | |
| Yang et al.2026.04 | 56.5 | 1 | 81 | 87.6 | |
| Wang et al.Venue=MM’252026.04 | 51.7 | 1 | 78.2 | 85.9 | |
| Wang et al.Venue=MM'252026.04 | 51.7 | 1 | 78.2 | 85.9 | |
| EOMA2026.04 | 50.6 | 1 | 77.1 | 84.8 | |
| FMIVenue=Scientific Reports’252026.04 | 48.4 | 1 | 76.3 | 81.9 | |
| FMI2026.04 | 48.4 | 1 | 76.3 | 81.9 | |
| DARVenue=ECCV’242026.04 | 47.8 | 2 | 75.9 | 84.3 | |
| DAR2026.04 | 47.8 | 2 | 75.9 | 84.3 | |
| VLPCookBackbone=ViT-B/16, Pre-training Data=Recipe1M+2022.12 | 46.7 | — | 73.3 | 83.3 | |
| VLPCook (R1M+)Training Dataset=Recipe1M+2022.12 | 46.7 | 2 | 73.3 | 83.3 | |
| IR-CLIP2026.04 | 46.5 | 2 | 74.3 | 83.1 | |
| MALM2026.04 | 45.9 | 2 | 72.3 | 80.5 | |
| VLPCookBackbone=ViT-B/162022.12 | 45.3 | — | 72.4 | 80.8 | |
| VLPCook2022.12 | 45.3 | 2 | 72.4 | 80.8 | |
| VLPCookVenue=CVIU’242026.04 | 45.3 | 2 | 72.4 | 80.8 | |
| VLPCook2026.04 | 45.3 | 2 | 72.4 | 80.8 | |
| CIPVenue=MM’232026.04 | 44.9 | 2 | 72.8 | 82 | |
| FARMVenue=WACV’242026.04 | 44.9 | 2 | 71.8 | 80 | |
| CIP2026.04 | 44.9 | 2 | 72.8 | 82 | |
| FARM2026.04 | 44.9 | 2 | 71.8 | 80 | |
| CREAMYVenue=IEEE Access’242026.04 | 44.6 | 2 | 71.6 | 80.4 | |
| CREAMY2026.04 | 44.6 | 2 | 71.6 | 80.4 | |
| T-Foodbackbone=CLIP-ViT2022.04 | 43.4 | 2 | 70.7 | 79.7 | |
| T-Food (CLIP-ViT)Backbone=CLIP-ViT2022.12 | 43.4 | — | 70.7 | 79.7 | |
| T-Food (CLIP-ViT)Backbone=CLIP-ViT2022.12 | 43.4 | 2 | 70.7 | 79.7 | |
| T-FoodVenue=CVPRW’222026.04 | 43.4 | 2 | 70.7 | 79.7 | |
| T-Food2026.04 | 43.4 | 2 | 70.7 | 79.7 | |
| DCA-Food2026.04 | 42.7 | 2 | 68.9 | 77.6 | |
| T-Foodbackbone=ViT2022.04 | 40 | 2 | 67 | 75.9 | |
| T-Food (ViT)Backbone=ViT2022.12 | 40 | — | 67 | 75.9 | |
| T-Food (ViT)Backbone=ViT2022.12 | 40 | 2 | 67 | 75.9 | |
| MMACMR2026.04 | 38.1 | 2.1 | 65.8 | 75.9 | |
| UTE-FCLVenue=Knowledge-Based Systems’242026.04 | 37.4 | 2.7 | 65.4 | 75.4 | |
| UTE-FCL2026.04 | 37.4 | 2.7 | 65.4 | 75.4 | |
| RDE-GANVenue=MM’212026.04 | 36 | 3.5 | 56.1 | 64.4 | |
| RDE-GAN2026.04 | 36 | 3.5 | 56.1 | 64.4 | |
| LMF-CSF2026.04 | 34.6 | 3 | 62.7 | 73.2 | |
| H-Tbackbone=ViT2022.04 | 33.5 | 3 | 62.1 | 72.8 | |
| H-T (ViT)Backbone=ViT2022.12 | 33.5 | — | 62.1 | 72.8 | |
| H-T (ViT)Backbone=ViT2022.12 | 33.5 | 3 | 62.1 | 72.8 | |
| X-MRS2022.04 | 32.9 | 3 | 60.6 | 71.2 | |
| X-MRS2022.12 | 32.9 | — | 60.6 | 71.2 | |
| X-MRS2022.12 | 32.9 | 3 | 60.6 | 71.2 | |
| X-MRSVenue=MM’212026.04 | 32.9 | 3 | 60.6 | 71.2 | |
| X-MRS2026.04 | 32.9 | 3 | 60.6 | 71.2 | |
| MFRF2026.04 | 31.2 | 5 | 56.5 | 67.3 | |
| DaC2022.04 | 30 | 4 | 56.5 | 67 | |
| DaC2022.12 | 30 | — | 56.5 | 67 | |
| DaC2022.12 | 30 | 4 | 56.5 | 67 | |
| DaC2026.04 | 30 | 4 | 56.5 | 67 | |
| M-SIA2022.04 | 29.2 | 4 | 55 | 66.2 | |
| M-SIA2022.12 | 29.2 | — | 55 | 66.2 | |
| M-SIA2022.12 | 29.2 | 4 | 55 | 66.2 | |
| M-SIA2026.04 | 29.2 | 4 | 55 | 66.2 | |
| Wang et al.Venue=MM'222026.04 | 28.6 | — | 57.1 | 68.6 | |
| H-T2022.04 | 27.9 | 4 | 56.4 | 68.1 | |
| H-TVenue=CVPR’212026.04 | 27.9 | 4 | 56.4 | 68.1 | |
| H-T2026.04 | 27.9 | 4 | 56.4 | 68.1 | |
| LCWF-GI2026.04 | 27.9 | 4 | 56 | 67.8 | |
| SEJE2022.04 | 26.9 | 4.2 | 54 | 65.6 | |
| SEJE2022.12 | 26.9 | — | 54 | 65.6 | |
| SEJE2022.12 | 26.9 | 4.2 | 54 | 65.6 | |
| JEMA2026.04 | 26.9 | 4.2 | 54 | 65.6 | |
| SEJE2026.04 | 26.9 | 4.2 | 54 | 65.6 | |
| MSJE2022.04 | 25.6 | 5 | 52.1 | 63.8 | |
| MSJE2022.12 | 25.6 | — | 52.1 | 63.8 | |
| MSJE2022.12 | 25.6 | 5 | 52.1 | 63.8 | |
| MSJE2026.04 | 25.6 | 5 | 52.1 | 63.8 | |
| HF-ICMA2022.04 | 24 | 5 | 51.6 | 65.4 | |
| HF-ICMA2022.12 | 24 | — | 51.6 | 65.4 | |
| HF-ICMA2022.12 | 24 | 5 | 51.6 | 65.4 | |
| HF-ICMA2026.04 | 24 | 5 | 51.6 | 65.4 | |
| SCAN2022.04 | 23.7 | 5.9 | 49.3 | 60.6 | |
| SCAN2022.12 | 23.7 | — | 49.3 | 60.6 | |
| SCAN2022.12 | 23.7 | 5.9 | 49.3 | 60.6 | |
| SCAN2020.03 | 23.7 | 5.9 | 49.3 | 60.6 | |
| SCAN2026.04 | 23.7 | 5.9 | 49.3 | 60.6 | |
| IMHF2022.04 | 23.4 | 6.2 | 48.2 | 58.4 | |
| Wang et al.2022.04 | 23.4 | 6 | 48.8 | 60.1 | |
| IMHF2022.12 | 23.4 | — | 48.2 | 58.4 | |
| Wang et. al2022.12 | 23.4 | — | 48.8 | 60.1 | |
| IMHF2022.12 | 23.4 | 6.2 | 48.2 | 58.4 | |
| Wang et al.2022.12 | 23.4 | 6 | 48.8 | 60.1 | |
| IMHF2026.04 | 23.4 | 6.2 | 48.2 | 58.4 | |
| Wang et al.Venue=IEEE TPAMI'232026.04 | 23.4 | 6 | 48.8 | 60.1 | |
| ACME2022.04 | 22.9 | 6.7 | 46.8 | 57.9 | |
| ACME2022.12 | 22.9 | — | 46.8 | 57.9 | |
| ACME2022.12 | 22.9 | 6.7 | 46.8 | 57.9 | |
| ACME2020.03 | 22.9 | 6.7 | 46.8 | 57.9 | |
| ACMEVenue=CVPR’192026.04 | 22.9 | 6.7 | 46.8 | 57.9 | |
| ACME2026.04 | 22.9 | 6.7 | 46.8 | 57.9 |