@article{achallengingmultimodalvideosummary,
  title = {A Challenging Multimodal Video Summary: Simultaneously Extracting and Generating Keyframe-Caption Pairs from Video},
  author = {Keito Kudo and Haruki Nagasawa and Jun Suzuki and Nobuyuki Shimizu},
  year = {2023},
  eprint = {2312.01575},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2312.01575v1},
}