An MSDCNN-LSTM framework for video frame deletion forensics
Multimedia Tools and Applications · 12.02.2024 · 83 (29) · 72745-72764
DOI: 10.1007/s11042-024-18324-7 ↗Kurz gefasst
Fachartikel in der Zeitschrift Multimedia Tools and Applications, online erschienen am 12.02.2024. Verfasst von Chunhui Feng und 3 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 51 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Frame deletion detection is a challenging task in the field of digital video forensics. This paper proposes a deep-learning-based frame deletion detection method for single-shot videos. We capture traces of frame deletion forgery from both adjacent and long-range continuous frames. Specifically, we propose a novel multi-scale difference convolutional neural network (MSDCNN) structure, which models different levels of inter-frame variations. Then, we use the long-short-term memory network (LSTM) to capture the long-term variation pattern of multi-scale differential features. The proposed method is a simple and principled frame deletion detection framework with a small computational cost. According to the experiments, the proposed framework can achieve a more advanced performance of frame deletion detection than traditional methods and methods based on 3D convolutions.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Feng, C., Wu, D., Wu, T., & Wei, L. (2024). An MSDCNN-LSTM framework for video frame deletion forensics. Multimedia Tools and Applications, 83(29), 72745-72764. https://doi.org/10.1007/s11042-024-18324-7
Vancouver
Feng C, Wu D, Wu T, Wei L. An MSDCNN-LSTM framework for video frame deletion forensics. Multimedia Tools and Applications. 2024;83(29):72745-72764. doi:10.1007/s11042-024-18324-7
BibTeX
@article{Feng2024,
author = {Feng, Chunhui and Wu, Dawei and Wu, Tianle and Wei, Lifang},
title = {An MSDCNN-LSTM framework for video frame deletion forensics},
journal = {Multimedia Tools and Applications},
year = {2024},
volume = {83},
number = {29},
pages = {72745--72764},
doi = {10.1007/s11042-024-18324-7}
}
EUVIMED