EUVIMEDEUVIMED entdecken
Crossref

Dynamic Low-Rank Tensor Decomposition for Video Applications

Wen-Jie Zheng, Xi-Le Zhao, Yu-Bang Zheng, Teng-Yu Ji, Ben-Zheng Li

IEEE Transactions on Circuits and Systems for Video Technology · 2026-01 · 36 (1) · 449-462

DOI: 10.1109/tcsvt.2025.3595950 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2026-01. Verfasst von Wen-Jie Zheng und 4 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 46 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Sichuan Science and Technology Program, National Key Research and Development Program of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Tensor decompositions are powerful tools for capturing the low-rank structure of dynamic videos. However, existing tensor decompositions primarily consider pixel-wise interactions, thus capturing solely global spatio-temporal correlations and struggling to handle the complex patterns that are inherent to dynamic videos in real-world applications. To overcome this limitation, we propose a dynamic Bhattacharya-Mesner (DyBM) decomposition, which represents the dynamic video as a sum of terms, with each term being the convolution of a BM-rank 1 tensor and a learnable three-dimensional filter. The newly constructed filters enable DyBM decomposition to establish patch-wise interactions in BM-rank 1 tensors, effectively capturing both global and local spatio-temporal correlations in dynamic videos. We further provide a physical interpretation of the factors in DyBM decomposition and offer an in-depth discussion of its relationship to the original BM decomposition. To evaluate the effectiveness of DyBM decomposition, we build a dynamic video recovery model. To solve the model, we develop a corresponding optimization algorithm with a theoretical convergence guarantee. Extensive experiments verify that DyBM decomposition-based method performs more favorably than the state-of-the-art tensor decomposition-based methods especially for dynamic videos.

Förderung

  • National Natural Science Foundation of China
  • Sichuan Science and Technology Program
  • National Key Research and Development Program of China
  • China Postdoctoral Science Foundation
  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Zheng, W., Zhao, X., Zheng, Y., Ji, T., & Li, B. (2026). Dynamic Low-Rank Tensor Decomposition for Video Applications. IEEE Transactions on Circuits and Systems for Video Technology, 36(1), 449-462. https://doi.org/10.1109/tcsvt.2025.3595950

Vancouver

Zheng W, Zhao X, Zheng Y, Ji T, Li B. Dynamic Low-Rank Tensor Decomposition for Video Applications. IEEE Transactions on Circuits and Systems for Video Technology. 2026;36(1):449-462. doi:10.1109/tcsvt.2025.3595950

BibTeX
@article{Zheng2026,
  author = {Zheng, Wen-Jie and Zhao, Xi-Le and Zheng, Yu-Bang and Ji, Teng-Yu and Li, Ben-Zheng},
  title = {Dynamic Low-Rank Tensor Decomposition for Video Applications},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2026},
  volume = {36},
  number = {1},
  pages = {449--462},
  doi = {10.1109/tcsvt.2025.3595950}
}
Kostenlos starten →