Shiwen Xue

PatternCIR Benchmark and TisCIR: Advancing Zero-Shot Composed Image Retrieval in Remote Sensing

Remote sensing composed image retrieval (RSCIR) is a new vision-language task that takes a composed query of an image and text, aiming to search for a target remote sensing image satisfying two conditions from intricate remote sensing imagery. However, the existing attribute-based benchmark Patternc