# Spatio-temporal Features for Generalized Detection of Deepfake Videos

arXiv: https://arxiv.org/abs/2010.11844 · HTML: https://mlsanity.com/paper/2010.11844/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Oct 2020.

## Built on by (most cited first, 12 of 12)

- [Exploring Temporal Coherence for More General Video Face Forgery Detection](https://mlsanity.com/paper/2108.06693/) (2021)
- [Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detection](https://mlsanity.com/paper/2201.07131/) (2022)
- [Countering Malicious DeepFakes: Survey, Battleground, and Horizon](https://mlsanity.com/paper/2103.00218/) (2021)
- [FedForgery: Generalized Face Forgery Detection with Residual Federated Learning](https://mlsanity.com/paper/2210.09563/) (2022)
- [Vulnerability-Aware Spatio-Temporal Learning for Generalizable Deepfake Video Detection](https://mlsanity.com/paper/2501.01184/) (2025)
- [Spatial-Temporal Frequency Forgery Clue for Video Forgery Detection in VIS and NIR Scenario](https://mlsanity.com/paper/2207.01906/) (2022)
- [Passive Deepfake Detection Across Multi-modalities: A Comprehensive Survey](https://mlsanity.com/paper/2411.17911/) (2024)
- [Detecting Deepfake by Creating Spatio-Temporal Regularity Disruption](https://mlsanity.com/paper/2207.10402/) (2022)
- [CapST: Leveraging Capsule Networks and Temporal Attention for Accurate Model Attribution in Deep-fake Videos](https://mlsanity.com/paper/2311.03782/) (2023)
- [Learning Expressive And Generalizable Motion Features For Face Forgery Detection](https://mlsanity.com/paper/2403.05172/) (2024)
- [Federated Face Forgery Detection Learning with Personalized Representation](https://mlsanity.com/paper/2406.11145/) (2024)
- [A Hybrid Quantum-Classical AI-Based Detection Strategy for Generative Adversarial Network-Based Deepfake Attacks on an Autonomous Vehicle Traffic Sign Classification System](https://mlsanity.com/paper/2409.17311/) (2024)

## Abstract (arXiv)

For deepfake detection, video-level detectors have not been explored as extensively as image-level detectors, which do not exploit temporal data. In this paper, we empirically show that existing approaches on image and sequence classifiers generalize poorly to new manipulation techniques. To this end, we propose spatio-temporal features, modeled by 3D CNNs, to extend the generalization capabilities to detect new sorts of deepfake videos. We show that spatial features learn distinct deepfake-method-specific attributes, while spatio-temporal features capture shared attributes between deepfake methods. We provide an in-depth analysis of how the sequential and spatio-temporal video encoders are utilizing temporal information using DFDC dataset arXiv:2006.07397. Thus, we unravel that our approach captures local spatio-temporal relations and inconsistencies in the deepfake videos while existing sequence encoders are indifferent to it. Through large scale experiments conducted on the FaceForensics++ arXiv:1901.08971 and Deeper Forensics arXiv:2001.03024 datasets, we show that our approach outperforms existing methods in terms of generalization capabilities.