@article{embodiedimagecaptioningselfsupervised,
  title = {Embodied Image Captioning: Self-supervised Learning Agents for Spatially Coherent Image Descriptions},
  author = {Tommaso Galliena and Tommaso Apicella and Stefano Rosa and Pietro Morerio and Alessio Del Bue and Lorenzo Natale},
  year = {2025},
  eprint = {2504.08531},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2504.08531v1},
}