Separate, Locate, and Align: Determine Context Relation of Scene Text From Multiple Perspectives in TextVQA

Chengyang Fang, Wenhui Jiang, Yuming Fang, Yuxin Peng 0001, Yang Liu 0293. Separate, Locate, and Align: Determine Context Relation of Scene Text From Multiple Perspectives in TextVQA. IEEE Trans. Circuits Syst. Video Techn., 35(11):11172-11185, 2025. [doi]

Authors

Chengyang Fang

This author has not been identified. Look up 'Chengyang Fang' in Google

Wenhui Jiang

This author has not been identified. Look up 'Wenhui Jiang' in Google

Yuming Fang

This author has not been identified. Look up 'Yuming Fang' in Google

Yuxin Peng 0001

This author has not been identified. Look up 'Yuxin Peng 0001' in Google

Yang Liu 0293

This author has not been identified. Look up 'Yang Liu 0293' in Google