AI Paper Atlas

Research map / Learning theory and algorithms / Matrix and tensor methods

Tensor Robust Principal Component Analysis with a New Tensor Nuclear Norm

Canyi Lu, Jiashi Feng, Yudong Chen, Wei Liu, Zhouchen Lin, Shuicheng Yan

TPAMI 2019 · Learning theory and algorithms › Matrix and tensor methods · approach: Low-rank approximation theory · 1,188 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use tensor nuclear norm TRPCA instead of channel-wise RPCATRPCA · BSD 100 images, 10% pixel corruptionPSNRImproved
use TRPCA (tensor nuclear norm) instead of SNNTRPCA · BSD 100 images, 10% pixel corruptionPSNRImproved
use TRPCA instead of SNN with fast tensor SVTTRPCA · BSD 100 imagesrunning timeImproved
use TRPCA instead of RPCA/SNN for video background separationTRPCA · Hall, WaterSurface, ShoppingMall, ShopCorridorseparation qualityImproved
use TRPCA instead of SNN in running time on videosTRPCA · four color video sequencesrunning timeImproved
increase tubal rank from 0.05n to 0.1n and sparsity from 0.1n^3 to 0.2n^3 (ablation)TRPCA · Synthetic n=100relative error of L: 4.1e-7 -> 7.7e-7Hurt
use random-sign versus coherent-sign sparse errors (ablation)TRPCA · Phase transition n=100, n3=50fraction of correct recoveryNo clear effect
use SNN with theory-suggested lambda_i instead of empirically tuned values (ablation)SNN · BSD imagesPSNRHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy