@article{visareasoningvideoobjectsegmentationvia,
  title = {VISA: Reasoning Video Object Segmentation via Large Language Models},
  author = {Cilin Yan and Haochen Wang and Shilin Yan and XiaoLong Jiang and Yao Hu and Guoliang Kang and Weidi Xie and Efstratios Gavves},
  year = {2024},
  eprint = {2407.11325},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2407.11325v1},
}