@article{zeroshotcharacteridentificationand,
  title = {Zero-Shot Character Identification and Speaker Prediction in Comics via Iterative Multimodal Fusion},
  author = {Yingxuan Li and Ryota Hinami and Kiyoharu Aizawa and Yusuke Matsui},
  year = {2024},
  eprint = {2404.13993},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2404.13993v4},
}