@article{captionformerunifiedsegmentationtracking,
  title = {CaptionFormer: Unified Segmentation, Tracking, and Captioning for Spatio-Temporal Objects},
  author = {Gabriel Fiastre and Antoine Yang and Cordelia Schmid},
  year = {2025},
  eprint = {2510.14904},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2510.14904},
}