Dynamic Low-Rank Tensor Decomposition for Video Applications
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.
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}
}
EUVIMED