Video Manipulation Detection using Sequence Learning and Convolution Networks: A Comparative Study

Abstract

Nowadays, the accessible and technologically advanced edit- ing tools, coupled with the surge in photo and video content pose a great risk to content authenticity. Manipulated content can be used to spread misinformation, cause harassment and infringe human rights. In this article, we compare the effectiveness of two approaches for video manipulation detection using micro and macro information, i.e., a Long Short-Term Memory (LSTM) architecture with frame-level features of videos and their respective ground truths as inputs and a Graph Con- volutional Network (GCN) with frame-level video scene graphs con- catenated using temporal edges. While the LSTM-based model cap- tures frame-level micro-information, the GCN model captures high-level macro-information inside a video.