@article{learningtounifyaudiovisualandtextfor,
  title = {Learning to Unify Audio, Visual and Text for Audio-Enhanced Multilingual Visual Answer Localization},
  author = {Zhibin Wen and Bin Li},
  year = {2024},
  eprint = {2411.02851},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2411.02851v1},
}