@article{canlocalvisionlanguagemodelsimproveactiv,
  title = {Can Local Vision-Language Models improve Activity Recognition over Vision Transformers? -- Case Study on Newborn Resuscitation},
  author = {Enrico Guerriero and Kjersti Engan and Øyvind Meinich-Bache},
  year = {2026},
  eprint = {2602.12002},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.12002},
}