@article{unleashingthetemporalspatialreasoning,
  title = {Unleashing the Temporal-Spatial Reasoning Capacity of GPT for Training-Free Audio and Language Referenced Video Object Segmentation},
  author = {Shaofei Huang and Rui Ling and Hongyu Li and Tianrui Hui and Zongheng Tang and Xiaoming Wei and Jizhong Han and Si Liu},
  year = {2024},
  eprint = {2408.15876},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2408.15876v2},
}