Hybrid deep-learning framework for object-based forgery detection in video

作者：

Highlights：

• We have proposed a full end-to-end network for object-based video forgery detection.

• The extensive experiments show that our framework achieves superior performance.

• Moreover, the experiments show our framework is more robust on degraded videos.

摘要

•We have proposed a full end-to-end network for object-based video forgery detection.•The extensive experiments show that our framework achieves superior performance.•Moreover, the experiments show our framework is more robust on degraded videos.

论文关键词：Object-based video forgery,Hybrid deep learning,Video forensics,3D convolution,Bi-directional LSTM

论文评审过程：Received 24 December 2020, Revised 26 January 2022, Accepted 23 March 2022, Available online 5 April 2022, Version of Record 27 April 2022.

论文官网地址：https://doi.org/10.1016/j.image.2022.116695