
The Pyramid of Captions (PoCa) method leverages a hierarchical approach to generate detailed and informative image captions by fusing local and global visual information using large language models.


coremsg

enhancing-image-captioning-with-pyramid-of-captions-leveraging-local-and-global-visual-cues-for-informative-and-coherent-descriptions


Enhancing Image Captioning with Pyramid of Captions: Leveraging Local and Global Visual Cues for Informative and Coherent Descriptions
