Metraipolis › archive › dc_efcd7e0624fb

A vision explainability method for image captioning using transformer decoder attention maps — Europe PMC PMID:41438405

Source: Europe PMC (en)
Original: https://europepmc.org/article/MED/41438405
DOI: 10.1016/j.mex.2025.103744
License (as archived): solo-consultazione
Archived: 2026-10-08T02:01:58.058Z
SHA-256 of the archived text: ffd54bb68a393c556a84c6f11ed475708f70a5e3d82f674e0e561401882bb7e6
Stable URL of this page: https://metraipolis.com/documento/dc_efcd7e0624fb

How to cite

A vision explainability method for image captioning using transformer decoder attention maps — Europe PMC PMID:41438405 — Europe PMC (en), https://europepmc.org/article/MED/41438405 (solo-consultazione); archived copy: https://metraipolis.com/documento/dc_efcd7e0624fb (Metraipolis archive dc_efcd7e0624fb, sha256 ffd54bb68a393c556a84c6f11ed475708f70a5e3d82f674e0e561401882bb7e6)

BibTeX

@misc{dcefcd7e0624fb,
  title = {A vision explainability method for image captioning using transformer decoder attention maps — Europe PMC PMID:41438405},
  howpublished = {Europe PMC (en)},
  url = {https://europepmc.org/article/MED/41438405},
  note = {License solo-consultazione; archived copy https://metraipolis.com/documento/dc_efcd7e0624fb; sha256 ffd54bb68a393c556a84c6f11ed475708f70a5e3d82f674e0e561401882bb7e6},
  year = {2026}
}

Archived text

The text is not reproduced here: the archive holds it as solo-consultazione (consultation only, no republication). Read it at the original source: https://europepmc.org/article/MED/41438405. Agents can read the archived copy with the MCP tool read_document.