List your company

Image Captioning on UCM Captions

79.92BLEU-4MF-RSVLM
6.485625.550344.61563.6797Dec 17, 2025Dec 19, 2025Dec 21, 2025Dec 23, 2025Dec 25, 2025Dec 27, 2025Dec 30, 2025

Evaluation results

MethodLinks
MF-RSVLMCategory=Open-source Remote Sensing Vision-Language Models2025.1279.92—88.5189.47—387.9
SkyEyeGPTTotal Params=7B2025.1278.4———90.72.368
Aware-Trans.Total Params=28M*2025.1278.1———90.13.779
GeoMELTTotal Params=271M2025.1277.2———89.83.917
HCNetTotal Params=25M*2025.1274.5———88.33.518
BITATotal Params=3B2025.1271.9———88.93.845
MC-NetTotal Params=138M*2025.1267.9———84.53.355
Def. Trans.Total Params=90M*2025.1267.9———82.33.463
MLCA-NETTotal Params=138M*2025.1266.8———82.63.24
RSGPTTotal Params=13B2025.1265.7———86.13.332
RS-CapRetTotal Params=7B2025.1264.5———83.33.429
EarthDialCategory=Open-source Remote Sensing Vision-Language Models2025.1259.77—32.4344.08—127.7
VHMCategory=Open-source Remote Sensing Vision-Language Models2025.1242.08—25.1727.86—66.12
SkySenseGPTCategory=Open-source Remote Sensing Vision-Language Models2025.1239.04—22.6323.52—49.8
GPT-5Category=Closed-source Commercial Vision-Language Models2025.1228.49—17.8225.56—40.95
Qwen2.5-VLCategory=Open-source Vision-Language Models2025.1227.87—17.2321.48—35.36
MiniGPT-v2Category=Open-source Vision-Language Models2025.1225.46—13.8219.62—30.94
Claude-sonnet-4Category=Closed-source Commercial Vision-Language Models2025.1220.12—13.3520.99—30.04
Gemini-2.0Category=Closed-source Commercial Vision-Language Models2025.129.31—5.486.72—13.23