EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

EADIC: Entity Aware and Diverse Image Captioning Utilizing a Fusion Transformer

Sharmila Kharat, Sunita Barve

Engineering, Technology & Applied Science Research · 11.08.2026 · 16 (4) · 37487-37493

DOI: 10.48084/etasr.18013 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Engineering, Technology & Applied Science Research, online erschienen am 11.08.2026. Verfasst von Sharmila Kharat und 1 weiteren Autor:innen. Die Arbeit nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Image captioning is a significant vision language task that supports accessibility, human-AI interaction, and image retrieval. Despite the field's continuous progress, the generated captions remain generic, repetitive, and uninformative. To address these issues, this study proposes Entity Aware and Diverse Image Captioning (EADIC), a multimodal image captioning model. The proposed model generates accurate, diverse, and entity-aware image descriptions by incorporating named entities such as persons, locations, and organizations whenever sufficient context is available. The proposed framework includes three information streams: visual feature tokens from a caption-oriented novel Convolutional Neural Network (CNN) encoder, object tokens, and named entity information tokens, fused using a fusion transformer, which utilizes multi-head attention. The caption-generating transformer decoder is first trained employing cross-entropy loss, which is later fine-tuned using reinforcement learning to maximize accuracy, entity coverage, and diversity. Experiments on benchmark datasets demonstrate that the proposed EADIC model outperforms state-of-the-art captioning methods, achieving an Entity F1-score (EF1) of 31.1 for entity-aware captions and CIDErBtw of 52 for diversity, without compromising fluency and accuracy as reflected by a CIDEr score of 71.

Zitieren

APA

Kharat, S., & Barve, S. (2026). EADIC: Entity Aware and Diverse Image Captioning Utilizing a Fusion Transformer. Engineering, Technology & Applied Science Research, 16(4), 37487-37493. https://doi.org/10.48084/etasr.18013

Vancouver

Kharat S, Barve S. EADIC: Entity Aware and Diverse Image Captioning Utilizing a Fusion Transformer. Engineering, Technology & Applied Science Research. 2026;16(4):37487-37493. doi:10.48084/etasr.18013

BibTeX
@article{Kharat2026,
  author = {Kharat, Sharmila and Barve, Sunita},
  title = {EADIC: Entity Aware and Diverse Image Captioning Utilizing a Fusion Transformer},
  journal = {Engineering, Technology & Applied Science Research},
  year = {2026},
  volume = {16},
  number = {4},
  pages = {37487--37493},
  doi = {10.48084/etasr.18013}
}
Kostenlos starten →