@article{doegocentricvideolanguagemodelscapturebo,
  title = {Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?},
  author = {Masatoshi Tateno and Alexandros Stergiou and Risa Shinoda and Yoichi Sato and Dima Damen},
  year = {2026},
  eprint = {2607.08514},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2607.08514},
}