AI-Generated Video Detection via Spatio-Temporal Anomaly Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913282050228224 |
|---|---|
| author | Bai, Jianfa Lin, Man Cao, Gang |
| author_facet | Bai, Jianfa Lin, Man Cao, Gang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_16638 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AI-Generated Video Detection via Spatio-Temporal Anomaly Learning Bai, Jianfa Lin, Man Cao, Gang Computer Vision and Pattern Recognition Cryptography and Security 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. |
| title | AI-Generated Video Detection via Spatio-Temporal Anomaly Learning |
| topic | Computer Vision and Pattern Recognition Cryptography and Security |
| url | https://arxiv.org/abs/2403.16638 |