.png){kind=icon}
.png){kind=icon}
Return
High-order tensor completion via learnable nonlinear transformation and sparse regularization
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2026.113901.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• We propose a nonlinear transform-based higher-order tensor nuclear norm. • We propose an LTHTCSR method by using learnable NHTNN for tensor completion. • A proximal Gauss-Seidel algorithm is designed to solve the resulting model. • Numerical examples demonstrate the superior performance of the proposed method.
Keywords:
tensor completion
nonlinear transform
higher-order tensor
sparse regularization
learnable nuclear norm
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W