EUVIMEDEUVIMED entdecken
Crossref

Scalable and Generalizable Correspondence Pruning via Geometry-Consistent Pre-Training

Tangfei Liao, Xiaoqin Zhang, Tao Wang, Hao Ye, Min Li, Guobao Xiao, Mang Ye

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-08 · 48 (8) · 10048-10065

DOI: 10.1109/tpami.2026.3682079 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-08. Verfasst von Tangfei Liao und 6 weiteren Autor:innen. Die Arbeit nennt 103 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Key Research and Development Program of China, Major Project of Science and Technology Innovation of Hubei Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Kein Abstract verfügbar.

Förderung

  • National Natural Science Foundation of China
  • National Key Research and Development Program of China
  • Major Project of Science and Technology Innovation of Hubei Province

Zitieren

APA

Liao, T., Zhang, X., Wang, T., Ye, H., Li, M., Xiao, G., & Ye, M. (2026). Scalable and Generalizable Correspondence Pruning via Geometry-Consistent Pre-Training. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(8), 10048-10065. https://doi.org/10.1109/tpami.2026.3682079

Vancouver

Liao T, Zhang X, Wang T, Ye H, Li M, Xiao G, et al. Scalable and Generalizable Correspondence Pruning via Geometry-Consistent Pre-Training. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(8):10048-10065. doi:10.1109/tpami.2026.3682079

BibTeX
@article{Liao2026,
  author = {Liao, Tangfei and Zhang, Xiaoqin and Wang, Tao and Ye, Hao and Li, Min and Xiao, Guobao and Ye, Mang},
  title = {Scalable and Generalizable Correspondence Pruning via Geometry-Consistent Pre-Training},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2026},
  volume = {48},
  number = {8},
  pages = {10048--10065},
  doi = {10.1109/tpami.2026.3682079}
}
Kostenlos starten →