AI-Generated Video Detection via Spatio-Temporal Anomaly Learning
This addresses the issue of malicious use of realistic AI-generated videos for spreading false information, representing an incremental improvement in detection methods.
The paper tackles the problem of detecting AI-generated videos to combat misinformation by proposing a two-branch spatio-temporal CNN that identifies anomalies in spatial and optical flow domains, achieving high generalization and robustness as verified on a new large-scale dataset.
The advancement of generation models has led to the emergence of highly realistic artificial intelligence (AI)-generated videos. Malicious users can easily create non-existent videos to spread false information. This letter proposes an effective AI-generated video detection (AIGVDet) scheme by capturing the forensic traces with a two-branch spatio-temporal convolutional neural network (CNN). Specifically, two ResNet sub-detectors are learned separately for identifying the anomalies in spatical and optical flow domains, respectively. Results of such sub-detectors are fused to further enhance the discrimination ability. A large-scale generated video dataset (GVD) is constructed as a benchmark for model training and evaluation. Extensive experimental results verify the high generalization and robustness of our AIGVDet scheme. Code and dataset will be available at https://github.com/multimediaFor/AIGVDet.