mlsanityData to 14 Oct 2026

Efficient Temporally-Aware DeepFake Detection using H.264 Motion Vectors

arXiv 2311.10788 ↗First posted 17 Nov 2023cs.CV cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

Video DeepFakes are fake media created with Deep Learning (DL) that manipulate a person's expression or identity. Most current DeepFake detection methods analyze each frame independently, ignoring inconsistencies and unnatural movements between frames. Some newer methods employ optical flow models to capture this temporal aspect, but they are computationally expensive. In contrast, we propose using the related but often ignored Motion Vectors (MVs) and Information Masks (IMs) from the H.264 video codec, to detect temporal inconsistencies in DeepFakes. Our experiments show that this approach is effective and has minimal computational costs, compared with per-frame RGB-only methods. This could lead to new, real-time temporally-aware DeepFake detection methods for video calls and streaming.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 21 of its 46 references that are in the map. First posted on arXiv 17 Nov 2023.

Builds on

21 of 46 references.

References · 21

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  3. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
  4. 2019Searching for MobileNetV3cited by 1,994
  5. 2019FaceForensics++: Learning to Detect Manipulated Facial Imagescited by 1,101
  6. 2014Two-Stream Convolutional Networks for Action Recognition in Videoscited by 1,068
  7. 2020Face2Face: Real-time Face Capture and Reenactment of RGB Videoscited by 632
  8. 2018Albumentations: fast and flexible image augmentationscited by 560
  9. 2019Face X-ray for More General Face Forgery Detectioncited by 470
  10. 2022Detecting Deepfakes with Self-Blended Imagescited by 338
  11. 2020Media Forensics and DeepFakes: an overviewcited by 209
  12. 2021E-RAFT: Dense Optical Flow from Event Camerascited by 152
9 more
  1. 2019FakeCatcher: Detection of Synthetic Portrait Videos using Biological Signalscited by 145
  2. 2020GridMask Data Augmentationcited by 123
  3. 2018FaceForensics: A Large-scale Video Dataset for Forgery Detection in Human Facescited by 119
  4. 2017Compressed Video Action Recognitioncited by 106
  5. 2016Fast Optical Flow using Dense Inverse Searchcited by 71
  6. 2020DeepRhythm: Exposing DeepFakes with Attentional Visual Heartbeat Rhythmscited by 65
  7. 2017Recasting Residual-based Local Descriptors as Convolutional Neural Networks: an Application to Image Forgery Detectioncited by 56
  8. 2020How Do the Hearts of Deep Fakes Beat? Deep Fake Source Detection via Interpreting Residuals with Biological Signalscited by 29
  9. 2022Deepfake Video Detection with Spatiotemporal Dropout Transformercited by 19

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025Zero-Shot Visual Deepfake Detection: Can AI Predict and Prevent Fake Content Before It's Created?cited by 1
  2. 2026Detect Early, Escalate Rarely: Anytime Detection of AI-Generated Video from the Compressed Bitstreamcited by 0
  3. 2026MVTrack: Ultrafast Appearance-Free Moving Object Tracking from Compressed Bitstreamscited by 0