@article{vocabularyfreefinegrainedvisualrecogniti,
  title = {Vocabulary-free Fine-grained Visual Recognition via Enriched Contextually Grounded Vision-Language Model},
  author = {Dmitry Demidov and Zaigham Zaheer and Omkar Thawakar and Salman Khan and Fahad Shahbaz Khan},
  year = {2025},
  eprint = {2507.23070},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2507.23070},
}