@article{gvdiffgroundedtexttovideogenerationwith,
  title = {GVDIFF: Grounded Text-to-Video Generation with Diffusion Models},
  author = {Huanzhang Dou and Ruixiang Li and Wei Su and Xi Li},
  year = {2024},
  eprint = {2407.01921},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2407.01921v2},
}