UCSG

Universal Chart Structural Multimodal Generation and Extraction via One Classification Token.

bar

line

pie

line_bar

line_bar2

Refs.

Haoran Wei, Lingyu Kong, et al. Vary: Scaling up the Vision Vocabulary for Large Vision-Language Models

Jinyue Chen, Lingyu Kong, et al. OneChart: Purify the Chart Structural Extraction via One Auxiliary Token

Share on: TwitterFacebookEmail

Comments


Related Posts


Published

Category

Projects

Tags

Contact