EUVIMEDEUVIMED entdecken
Crossref

Incomplete Multi-View Kernel Subspace Clustering via Tensor Correlated Total Variation Regularization

Liu Feng, Jian-Li Wang, Danyang Zheng, Jiashu Zhang, Yong-Guo Shi

IEEE Signal Processing Letters · 2026 · 33 · 1921-1925

DOI: 10.1109/lsp.2026.3687746 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Signal Processing Letters, 2026. Verfasst von Liu Feng und 4 weiteren Autor:innen. Die Arbeit nennt 32 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Sichuan Province, Postdoctoral Fellowship Program of CPSF.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Incomplete multi-view clustering (IMVC) has recently attracted increasing attention and achieved notable progress in computer vision. However, existing IMVC approaches still face several critical challenges. First, most methods fail to capture the inherent nonlinear structures of real-world data. Second, they fail to sufficiently exploit low-rankness and smoothness of multiple views. To overcome these limitations, we propose a novel method, termed Incomplete Multi-View Kernel Subspace Clustering with Tensor-Correlated Total Variation Regularization (KSC-TCTV), which integrates the ability of kernels to capture nonlinear separability with the strength of tensors in characterizing high-order correlations. Specifically, KSC-TCTV effectively models nonlinear structures by embedding data into a kernel Hilbert space. In addition, we introduce a log-based tensor-correlated total variation (Logt-CTV) regularizer in the kernel space, which jointly enforces global low-rankness for inter-view dependency modeling and local smoothness for intra-view structure preservation. Moreover, we incorporate a logarithmic non-convex relaxation into Logt-CTV to mitigate the bias induced by conventional convex surrogates. Experiments on several public benchmark datasets demonstrate that KSC-TCTV outperforms the state-of-the-art IMVC methods.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Sichuan Province
  • Postdoctoral Fellowship Program of CPSF
  • Open Research Fund Program of Data Recovery Key Laboratory of Sichuan Province

Zitieren

APA

Feng, L., Wang, J., Zheng, D., Zhang, J., & Shi, Y. (2026). Incomplete Multi-View Kernel Subspace Clustering via Tensor Correlated Total Variation Regularization. IEEE Signal Processing Letters, 33, 1921-1925. https://doi.org/10.1109/lsp.2026.3687746

Vancouver

Feng L, Wang J, Zheng D, Zhang J, Shi Y. Incomplete Multi-View Kernel Subspace Clustering via Tensor Correlated Total Variation Regularization. IEEE Signal Processing Letters. 2026;33:1921-1925. doi:10.1109/lsp.2026.3687746

BibTeX
@article{Feng2026,
  author = {Feng, Liu and Wang, Jian-Li and Zheng, Danyang and Zhang, Jiashu and Shi, Yong-Guo},
  title = {Incomplete Multi-View Kernel Subspace Clustering via Tensor Correlated Total Variation Regularization},
  journal = {IEEE Signal Processing Letters},
  year = {2026},
  volume = {33},
  pages = {1921--1925},
  doi = {10.1109/lsp.2026.3687746}
}
Kostenlos starten →