@article{whatwhenandwhereselfsupervisedspatio,
  title = {What, when, and where? -- Self-Supervised Spatio-Temporal Grounding in Untrimmed Multi-Action Videos from Narrated Instructions},
  author = {Brian Chen and Nina Shvetsova and Andrew Rouditchenko and Daniel Kondermann and Samuel Thomas and Shih-Fu Chang and Rogerio Feris and James Glass and Hilde Kuehne},
  year = {2023},
  eprint = {2303.16990},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2303.16990v2},
}