HDG-CLIP: Hierarchical Dual-Granularity Vision-Semantic Alignment for Open-Vocabulary Multi-Label Image Classification
IEEE Transactions on Image Processing · 2026 · 35 · 7871-7882
DOI: 10.1109/tip.2026.3709489 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2026. Verfasst von Beiyan Liu und 6 weiteren Autor:innen. Die Arbeit nennt 58 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Key Projects of the Special Program for Technological Innovation and Applied Development in Chongqing Municipality.
Abstract (Originalsprache)
Kein Abstract verfügbar.
Förderung
- National Natural Science Foundation of China
- Key Projects of the Special Program for Technological Innovation and Applied Development in Chongqing Municipality
Zitieren
APA
Liu, B., Huang, S., Liu, B., Huang, X., Mu, N., Hong, R., & Wang, M. (2026). HDG-CLIP: Hierarchical Dual-Granularity Vision-Semantic Alignment for Open-Vocabulary Multi-Label Image Classification. IEEE Transactions on Image Processing, 35, 7871-7882. https://doi.org/10.1109/tip.2026.3709489
Vancouver
Liu B, Huang S, Liu B, Huang X, Mu N, Hong R, et al. HDG-CLIP: Hierarchical Dual-Granularity Vision-Semantic Alignment for Open-Vocabulary Multi-Label Image Classification. IEEE Transactions on Image Processing. 2026;35:7871-7882. doi:10.1109/tip.2026.3709489
BibTeX
@article{Liu2026,
author = {Liu, Beiyan and Huang, Sheng and Liu, Bo and Huang, Xiaobin and Mu, Nankun and Hong, Richang and Wang, Meng},
title = {HDG-CLIP: Hierarchical Dual-Granularity Vision-Semantic Alignment for Open-Vocabulary Multi-Label Image Classification},
journal = {IEEE Transactions on Image Processing},
year = {2026},
volume = {35},
pages = {7871--7882},
doi = {10.1109/tip.2026.3709489}
}
EUVIMED