@article{tracktheanswerextendingtextvqafromimage,
  title = {Track the Answer: Extending TextVQA from Image to Video with Spatio-Temporal Clues},
  author = {Yan Zhang and Gangyan Zeng and Huawen Shen and Daiqing Wu and Yu Zhou and Can Ma},
  year = {2024},
  eprint = {2412.12502},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2412.12502v1},
}