method: Baseline TESTR Checkpoint2024-03-26

Authors: Organizers

Affiliation: ICDAR'24 RRC-MapText

Description: TESTR checkpoint is used without any additional modifications or finetuning. The model checkpoint version with polygon prediction head and fine-tuned on TotalText was used.

Xiang Zhang, Yongwen Su, Subarna Tripathi, Zhuowen Tu. Text Spotting Transformers. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 9519-9528.

Source code