Inserting faces inside captions: image captioning with attention guided merging - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2024

Inserting faces inside captions: image captioning with attention guided merging

Khalil Guetari
  • Fonction : Auteur
Marine Tassel
  • Fonction : Auteur
Erwan Kerleroux
  • Fonction : Auteur
Frédéric Petitpont
  • Fonction : Auteur

Résumé

Image captioning models are widely used to describe recent and archived pictures with the objective of improving their accessibility and retrieval. Yet, these approaches tend to be inefficient and biased at retrieving people's names. In this work we introduce AstroCaptions, a dataset for the image captioning task. This dataset specifically contains thousands of public fig-ures that are complex to identify for a traditional model. We also propose a novel post-processing method to insert identified people’s names inside the caption using explainable AI tools and the grounding capabilities of vi-sion-language models. The results obtained with this method show signifi-cant improvements of captions quality and a potential of reducing halluci-nations. Up to 93.2% of the persons detected can be inserted in the image captions leading to improvements in the BLEU, ROUGE, CIDEr and METEOR scores of each captioning model.
Fichier principal
Vignette du fichier
paper_astrocaptions_arxiv.pdf (7.89 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Licence : CC BY NC - Paternité - Pas d'utilisation commerciale

Dates et versions

hal-04511236 , version 1 (19-03-2024)

Licence

Paternité - Pas d'utilisation commerciale

Identifiants

  • HAL Id : hal-04511236 , version 1

Citer

Yannis Tevissen, Khalil Guetari, Marine Tassel, Erwan Kerleroux, Frédéric Petitpont. Inserting faces inside captions: image captioning with attention guided merging. 2024. ⟨hal-04511236⟩
11 Consultations
2 Téléchargements

Partager

Gmail Facebook X LinkedIn More