More precisely, our dataset has 4,364 image frames with semantic and instance annotations along with 58,689 unlabelled image frames. We validate our new dataset through a large and comprehensive range ...

Consequently, numerous researchers have focused on fine-tuning SAM for particular segmentation tasks. For example, MedSAM is a SAM-based model fine-tuned using over 1 million image-mask pairs spanning ...

Remote sensing image-text retrieval (RSITR) is becoming increasingly essential for the efficient utilization of remote sensing (RS) data. Nevertheless, current approaches primarily focus on individual ...