@article{m3tmultiscalememorymatchingforvideo,
  title = {TAM-VT: Transformation-Aware Multi-scale Video Transformer for Segmentation and Tracking},
  author = {Raghav Goyal and Wan-Cyuan Fan and Mennatullah Siam and Leonid Sigal},
  year = {2023},
  eprint = {2312.08514},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2312.08514v2},
}