@article{textaudiovisualconditioneddiffusionmodel,
  title = {Text-Audio-Visual-conditioned Diffusion Model for Video Saliency Prediction},
  author = {Li Yu and Xuanzhe Sun and Wei Zhou and Moncef Gabbouj},
  year = {2025},
  eprint = {2504.14267},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2504.14267v1},
}