@article{250111653v3,
  title = {Dynamic Scene Understanding from Vision-Language Representations},
  author = {Shahaf Pruss and Morris Alper and Hadar Averbuch-Elor},
  year = {2025},
  eprint = {2501.11653},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2501.11653v3},
}