Multi-Directional Tensor Average Rank Regularization for High-Order Tensor Completion

Recently, the high-order tensor Singular Value Decomposition (t-SVD) and the t-SVD rank has achieved great success in tensor completion. However, the t-SVD rank lacks the flexibility to capture the correlations between different modes of a high-order tensor. In addition, the Tensor Nuclear Norm (TNN...

Полное описание

Библиографические подробности

Главные авторы:	Zixuan Han, Mingjian Gu, Yong Hu
Формат:	Artigo
Язык:	Inglês
Опубликовано:	IEEE 2026-01-01
Серии:	IEEE Access
Предметы:	Low-rank high-order tensor completion (LRHOTC) multi-directional tensor average rank multi-directional tensor φ Norm (MDTN) alternating direction method of multipliers (ADMM)
Online-ссылка:	https://ieeexplore.ieee.org/document/11370855/
Метки:	Добавить метку Нет меток, Требуется 1-ая метка записи!