@article{exploringpretrainedtexttovideodiffusion,
  title = {Exploring Pre-trained Text-to-Video Diffusion Models for Referring Video Object Segmentation},
  author = {Zixin Zhu and Xuelu Feng and Dongdong Chen and Junsong Yuan and Chunming Qiao and Gang Hua},
  year = {2024},
  eprint = {2403.12042},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2403.12042v2},
}