SEVMark: Spatio-Temporally Enhanced Video Watermarking via Invertible Neural Networks
IEEE Transactions on Circuits and Systems for Video Technology · 2026-06 · 36 (6) · 8787-8801
DOI: 10.1109/tcsvt.2026.3662438 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2026-06. Verfasst von Songhan He und 4 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 36 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Zhejiang Provincial Natural Science Foundation of China, Ningbo Natural Science Foundation.
Abstract (Originalsprache)
Deep learning-based video watermarking algorithms perform well in terms of robustness and perceptual quality. However, their resistance to HEVC compression remains a major limitation, especially under high compression ratios, where watermark extraction accuracy significantly degrades. To address this issue, this paper proposes a Spatio-temporally Enhanced Video Watermarking (SEVMark) based on invertible neural networks (INNs). SEVMark introduces a channel attention mechanism in the temporal domain to adaptively focus on keyframes, and employs spatial pyramid pooling module in the spatial domain to capture multi-scale features. These two modules work in tandem to enhance the spatio-temporal feature representation, achieving high robustness and imperceptibility. Furthermore, based on the HEVC encoding process, a HEVC video compression simulator (DiffH265) is designed and incorporated as a key component of the noise layer, guiding the encoder-decoder network to maintain high extraction accuracy under HEVC compression. Experimental results demonstrate that SEVMark outperforms state-of-the-art methods in both quantitative and qualitative evaluations, particularly demonstrating excellent robustness against HEVC compression attacks under high compression ratios.
Förderung
- National Natural Science Foundation of China
- Zhejiang Provincial Natural Science Foundation of China
- Ningbo Natural Science Foundation
Zitieren
APA
He, S., Xu, D., Yang, L., Dai, H., & Ji, J. (2026). SEVMark: Spatio-Temporally Enhanced Video Watermarking via Invertible Neural Networks. IEEE Transactions on Circuits and Systems for Video Technology, 36(6), 8787-8801. https://doi.org/10.1109/tcsvt.2026.3662438
Vancouver
He S, Xu D, Yang L, Dai H, Ji J. SEVMark: Spatio-Temporally Enhanced Video Watermarking via Invertible Neural Networks. IEEE Transactions on Circuits and Systems for Video Technology. 2026;36(6):8787-8801. doi:10.1109/tcsvt.2026.3662438
BibTeX
@article{He2026,
author = {He, Songhan and Xu, Dawen and Yang, Lin and Dai, Haojun and Ji, Jianbin},
title = {SEVMark: Spatio-Temporally Enhanced Video Watermarking via Invertible Neural Networks},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2026},
volume = {36},
number = {6},
pages = {8787--8801},
doi = {10.1109/tcsvt.2026.3662438}
}
EUVIMED