@article{thedevilisinthedistributionsexplicit,
  title = {The Devil is in the Distributions: Explicit Modeling of Scene Content is Key in Zero-Shot Video Captioning},
  author = {Mingkai Tian and Guorong Li and Yuankai Qi and Amin Beheshti and Javen Qinfeng Shi and Anton Van Den Hengel and Qingming Huang},
  year = {2025},
  eprint = {2503.23679},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2503.23679v1},
}