World to Code: Multi-modal Data Generation via Self-Instructed Compositional Captioning and Filtering

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Jiacong, Wu, Bohong, Jiang, Haiyong, Zhou, Xun, Xiao, Xin, Guo, Haoyuan, Xiao, Jun
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2409.20424