Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Multi-Dimensional Visual Data Recovery: Scale-Aware Tensor Modeling and Accelerated Randomized Computation
Wenjin Qin, Hailin Wang, Jiangjun Peng +2
The recently proposed fully-connected tensor network (FCTN) decomposition has demonstrated significant advantages in correlation characterization and transpositional invariance, an…
cs.LG2025
Accelerating Large-Scale Regularized High-Order Tensor Recovery
Wenjin Qin, Hailin Wang, Jingyao Hou +1
Currently, existing tensor recovery methods fail to recognize the impact of tensor scale variations on their structural characteristics. Furthermore, existing studies face prohibit…