EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Enhanced Image Captioning with Adaptive Vision Transformer and GPT-2 Integration: A Multi-Scale Feature Extraction Approach

A. Ezil Sam Leni, Akey Sungheetha, Indra Kumar R

Procedia Computer Science · 2026 · 292 · 8126-8136

DOI: 10.1016/j.procs.2026.10.382 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Procedia Computer Science, 2026. Verfasst von A. Ezil Sam Leni und 2 weiteren Autor:innen. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Kein Abstract verfügbar.

Zitieren

APA

Leni, A. E. S., Sungheetha, A., & R, I. K. (2026). Enhanced Image Captioning with Adaptive Vision Transformer and GPT-2 Integration: A Multi-Scale Feature Extraction Approach. Procedia Computer Science, 292, 8126-8136. https://doi.org/10.1016/j.procs.2026.10.382

Vancouver

Leni AES, Sungheetha A, R IK. Enhanced Image Captioning with Adaptive Vision Transformer and GPT-2 Integration: A Multi-Scale Feature Extraction Approach. Procedia Computer Science. 2026;292:8126-8136. doi:10.1016/j.procs.2026.10.382

BibTeX
@article{Leni2026,
  author = {Leni, A. Ezil Sam and Sungheetha, Akey and R, Indra Kumar},
  title = {Enhanced Image Captioning with Adaptive Vision Transformer and GPT-2 Integration: A Multi-Scale Feature Extraction Approach},
  journal = {Procedia Computer Science},
  year = {2026},
  volume = {292},
  pages = {8126--8136},
  doi = {10.1016/j.procs.2026.10.382}
}
Kostenlos starten →