@article{leveragingmultimodalexplanatoryannotatio,
  title = {Leveraging multimodal explanatory annotations for video interpretation with Modality Specific Dataset},
  author = {Elisa Ancarani and Julie Tores and Lucile Sassatelli and Rémy Sun and Hui-Yin Wu and Frédéric Precioso},
  year = {2025},
  eprint = {2504.11232},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2504.11232v1},
}