HMAST: structure-preserving masked autoencoding with swin transformers for long-tailed visual recognition
The Visual Computer · 2026-11 · 42 (14)
DOI: 10.1007/s00371-026-04820-4 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Visual Computer, online erschienen am 31.10.2026. Verfasst von Qiangkui Leng und 1 weiteren Autor:innen. Die Arbeit nennt 32 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Foundation of Liaoning Province Education Administration,China, PhD Startup Foundation of Liaoning Technical University.
Abstract (Originalsprache)
Kein Abstract verfügbar.
Förderung
- National Natural Science Foundation of China
- Foundation of Liaoning Province Education Administration,China
- PhD Startup Foundation of Liaoning Technical University
Zitieren
APA
Leng, Q., & Gong, Y. (2026). HMAST: structure-preserving masked autoencoding with swin transformers for long-tailed visual recognition. The Visual Computer, 42(14). https://doi.org/10.1007/s00371-026-04820-4
Vancouver
Leng Q, Gong Y. HMAST: structure-preserving masked autoencoding with swin transformers for long-tailed visual recognition. The Visual Computer. 2026;42(14). doi:10.1007/s00371-026-04820-4
BibTeX
@article{Leng2026,
author = {Leng, Qiangkui and Gong, Yuan},
title = {HMAST: structure-preserving masked autoencoding with swin transformers for long-tailed visual recognition},
journal = {The Visual Computer},
year = {2026},
volume = {42},
number = {14},
doi = {10.1007/s00371-026-04820-4}
}
EUVIMED