@article{vimtsaunifiedvideoandimagetextspotter,
  title = {VimTS: A Unified Video and Image Text Spotter for Enhancing the Cross-domain Generalization},
  author = {Yuliang Liu and Mingxin Huang and Hao Yan and Linger Deng and Weijia Wu and Hao Lu and Chunhua Shen and Lianwen Jin and Xiang Bai},
  year = {2024},
  eprint = {2404.19652},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2404.19652v4},
}