3VL: Using Trees to Improve Vision-Language Models’ Interpretability
IEEE Transactions on Image Processing · 2025 · 34 · 495-509
DOI: 10.1109/tip.2024.3523801 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2025. Verfasst von Nir Yellinek und 2 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 104 Literaturangaben. Gefördert von: Tel Aviv University Center for AI and Data Science.
Abstract (Originalsprache)
Kein Abstract verfügbar.
Förderung
- Tel Aviv University Center for AI and Data Science
Zitieren
APA
Yellinek, N., Karlinsky, L., & Giryes, R. (2025). 3VL: Using Trees to Improve Vision-Language Models’ Interpretability. IEEE Transactions on Image Processing, 34, 495-509. https://doi.org/10.1109/tip.2024.3523801
Vancouver
Yellinek N, Karlinsky L, Giryes R. 3VL: Using Trees to Improve Vision-Language Models’ Interpretability. IEEE Transactions on Image Processing. 2025;34:495-509. doi:10.1109/tip.2024.3523801
BibTeX
@article{Yellinek2025,
author = {Yellinek, Nir and Karlinsky, Leonid and Giryes, Raja},
title = {3VL: Using Trees to Improve Vision-Language Models’ Interpretability},
journal = {IEEE Transactions on Image Processing},
year = {2025},
volume = {34},
pages = {495--509},
doi = {10.1109/tip.2024.3523801}
}
EUVIMED