- Task 2 - End-to-end Seal Title Recognition - Method: ParSeq with SwinV2
- Method info
- Samples list
- Per sample details
method: ParSeq with SwinV22023-03-21
Authors: Sehwan Joo, Wonho Song
Affiliation: Upstage AI
Email: sehwan.joo@upstage.ai
Description: For text recognition, we use the ParSeq [1] architecture with the visual feature extractor changed to SwinV2 [2].