@inproceedings{HaghighatMetzlerThodukaetal.2025,
  author    = {Haghighat, Sogol and Metzler, Tim Daniel and Thoduka, Santosh and Houben, Sebastian},
  title     = {Visual Latent Captioning - Towards Verbalizing Vision Transformer Encoders},
  booktitle = {Hauff, Macdonald et al. (Eds.): Advances in Information Retrieval. 47th European Conference on Infor},
  isbn      = {978-3-031-88710-9},
  doi       = {10.1007/978-3-031-88711-6_25},
  institution = {Fachbereich Informatik},
  pages     = {393 -- 406},
  year      = {2025},
  language  = {en}
}