List your company

Image Captioning on SARVLM-1M (test)

26.1BLEU-1SARCap*
8.05612.740517.42522.1095Oct 26, 2025

Evaluation results

MethodLinks
SARCap*Image Encoder=ViT-L-14, Pretrain Data=LAION+HQRS, Tune On=SARVLM-1M2025.1026.117.1311.938.4722.1826.1529.5888.73
SARCapImage Encoder=ViT-L-14, Pretrain Data=–, Tune On=SARVLM-1M2025.1022.4214.4410.457.7919.2321.7624.3288.11
CoCa-HQRSImage Encoder=ViT-L-14, Pretrain Data=LAION, Tune On=HQRS2025.1010.794.021.140.398.2113.117.4784
CoCa-VanillaImage Encoder=ViT-L-14, Pretrain Data=LAION, Tune On=–2025.108.753.211.140.3210.5410.674.1782.23