Advancing WordArt-Oriented Scene Text Recognition: Datasets and Methods
A large-scale synthetic dataset and specialized model architecture are introduced to address the challenges of artistic text recognition by improving data diversity and model flexi…
Hugging Face · Daily Papers
·Xingsong Ye, Yongkun Du
·
·▲ 6 upvotes
Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.
Autores: Xingsong Ye, Yongkun Du, Jiaxin Zhang, Haojie Zhang, Chong Sun, Chen Li
- 6 upvotes da comunidade
- Temas: Scene Text Recognition, WordArt, synthetic dataset, visual encoder, autoregressive decoder, arbitrary-shaped inputs
Resumo
Resumo original (em inglês), extraído do paper:
A large-scale synthetic dataset and specialized model architecture are introduced to address the challenges of artistic text recognition by improving data diversity and model flexibility for irregular text layouts.
