@article{villavideoreasoningsegmentationwithlarge,
  title = {ViLLa: Video Reasoning Segmentation with Large Language Model},
  author = {Rongkun Zheng and Lu Qi and Xi Chen and Yi Wang and Kun Wang and Yu Qiao and Hengshuang Zhao},
  year = {2024},
  eprint = {2407.14500},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2407.14500v2},
}