RS-MoE: A Vision–Language Model With Mixture of Experts for Remote Sensing Image Captioning and Visual Question Answering
Hui Lin, Danfeng Hong, Shuhang Ge, Chuyao Luo, Kai Jiang, Hao Jin, Congcong Wen
De quem é
- China Electronics Technology Group Corporationafiliação declarada pelos autores, segundo o OpenAlex
Outros papers das mesmas organizações
- FAST-LIVO2: Fast, Direct LiDAR–Inertial–Visual OdometryChina Electronics Technology Group Corporation · 357 citações
- Generative Diffusion Models for High Dimensional Channel EstimationChina Electronics Technology Group Corporation · 115 citações