@article{track2actpredictingpointtracksfrom,
  title = {Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation},
  author = {Homanga Bharadhwaj and Roozbeh Mottaghi and Abhinav Gupta and Shubham Tulsiani},
  year = {2024},
  eprint = {2405.01527},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2405.01527v2},
}