VividGAC: Visually Informed and Grounded Audio Captioning for Audio-Visual Question Answering
IEEE Access · 2026 · 1-1
DOI: 10.1109/access.2026.3752937 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Minchol Kwon und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) [Artificial Intelligence Graduate…, National Research Foundation of Korea (NRF) grant funded by the Korea government.
Abstract (Originalsprache)
Kein Abstract verfügbar.
Förderung
- Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) [Artificial Intelligence Graduate…
- National Research Foundation of Korea (NRF) grant funded by the Korea government
Zitieren
APA
Kwon, M., Kim, M., Pham, T. X., & Kim, J. (2026). VividGAC: Visually Informed and Grounded Audio Captioning for Audio-Visual Question Answering. IEEE Access, 1-1. https://doi.org/10.1109/access.2026.3752937
Vancouver
Kwon M, Kim M, Pham TX, Kim J. VividGAC: Visually Informed and Grounded Audio Captioning for Audio-Visual Question Answering. IEEE Access. 2026:1-1. doi:10.1109/access.2026.3752937
BibTeX
@article{Kwon2026,
author = {Kwon, Minchol and Kim, Mingi and Pham, Trung X. and Kim, Junyeong},
title = {VividGAC: Visually Informed and Grounded Audio Captioning for Audio-Visual Question Answering},
journal = {IEEE Access},
year = {2026},
pages = {1--1},
doi = {10.1109/access.2026.3752937}
}
EUVIMED