mlsanityData to 7 Oct 2026

Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Clues

arXiv 2007.09355 ↗First posted 18 Jul 2020cs.CVcited by 518

Not on the map. Why?

Cited by 42 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

As realistic facial manipulation technologies have achieved remarkable progress, social concerns about potential malicious abuse of these technologies bring out an emerging research topic of face forgery detection. However, it is extremely challenging since recent advances are able to forge faces beyond the perception ability of human eyes, especially in compressed images and videos. We find that mining forgery patterns with the awareness of frequency could be a cure, as frequency provides a complementary viewpoint where either subtle forgery artifacts or compression errors could be well described. To introduce frequency into the face forgery detection, we propose a novel Frequency in Face Forgery Network (F3-Net), taking advantages of two different but complementary frequency-aware clues, 1) frequency-aware decomposed image components, and 2) local frequency statistics, to deeply mine the forgery patterns via our two-stream collaborative learning framework. We apply DCT as the applied frequency-domain transformation. Through comprehensive studies, we show that the proposed F3-Net significantly outperforms competing state-of-the-art methods on all compression qualities in the challenging FaceForensics++ dataset, especially wins a big lead upon low-quality media.

Key facts. Cited by 518 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 31; 2022: 52; 2023: 87; 2024: 93; 2025: 142; 2026: 113.

518 papers.

Sort:

By area:

  1. 2022MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessmentcited by 514
  2. 2023DIRE for Diffusion-Generated Image Detectioncited by 386
  3. 2021Multi-attentional Deepfake Detectioncited by 339
  4. 2022Detecting Deepfakes with Self-Blended Imagescited by 332
  5. 2023GenImage: A Million-Scale Benchmark for Detecting AI-Generated Imagecited by 318
  6. 2021Generalizing Face Forgery Detection with High-frequency Featurescited by 261
  7. 2021Spatial-Phase Shallow Learning: Rethinking Face Forgery Detection in Frequency Domaincited by 241
  8. 2024A Sanity Check for AI-generated Image Detectioncited by 187
  9. 2023Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detectioncited by 180
  10. 2021FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Datasetcited by 179
  11. 2023UCF: Uncovering Common Features for Generalizable Deepfake Detectioncited by 177
  12. 2022Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detectioncited by 172
38 more
  1. 2023DeepfakeBench: A Comprehensive Benchmark of Deepfake Detectioncited by 162
  2. 2021Exploring Temporal Coherence for More General Video Face Forgery Detectioncited by 158
  3. 2022Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detectioncited by 130
  4. 2023Transcending Forgery Specificity with Latent Space Augmentation for Generalizable Deepfake Detectioncited by 126
  5. 2024DF40: Toward Next-Generation Deepfake Detectioncited by 126
  6. 2021ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysiscited by 124
  7. 2022Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalizationcited by 122
  8. 2021M2TR: Multi-modal Multi-scale Transformers for Deepfake Detectioncited by 114
  9. 2024C2P-CLIP: Injecting Category Common Prompt in CLIP to Enhance Generalization in Deepfake Detectioncited by 111
  10. 2024Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detectioncited by 102
  11. 2021Local Relation Learning for Face Forgery Detectioncited by 100
  12. 2021Dual Contrastive Learning for General Face Forgery Detectioncited by 100
  13. 2023TALL: Thumbnail Layout for Deepfake Video Detectioncited by 100
  14. 2023Detecting and Grounding Multi-Modal Media Manipulationcited by 98
  15. 2022Protecting Celebrities from DeepFake with Identity Consistency Transformercited by 95
  16. 2021Spatiotemporal Inconsistency Learning for DeepFake Video Detectioncited by 88
  17. 2024Leveraging Representations from Intermediate Encoder-blocks for Synthetic Image Detectioncited by 88
  18. 2024Improving Synthetic Image Detection Towards Generalization: An Image Transformation Perspectivecited by 88
  19. 2021Face Forensics in the Wildcited by 87
  20. 2024DeMamba: AI-Generated Video Detection on Million-Scale GenVideo Benchmarkcited by 85
  21. 2023Self-Supervised Video Forensics by Audio-Visual Anomaly Detectioncited by 84
  22. 2023AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Datasetcited by 79
  23. 2021WaveFake: A Data Set to Facilitate Audio Deepfake Detectioncited by 78
  24. 2022ObjectFormer for Image Manipulation Detection and Localizationcited by 78
  25. 2023AltFreezing for More General Video Face Forgery Detectioncited by 78
  26. 2022CORE: Consistent Representation Learning for Face Forgery Detectioncited by 73
  27. 2024Preserving Fairness Generalization in Deepfake Detectioncited by 70
  28. 2022UIA-ViT: Unsupervised Inconsistency-Aware Method based on Vision Transformer for Face Forgery Detectioncited by 69
  29. 2024Deepfake Generation and Detection: A Benchmark and Surveycited by 66
  30. 2023Seeing is not always believing: Benchmarking Human and Model Perception of AI-Generated Imagescited by 65
  31. 2021Exploiting Fine-grained Face Forgery Clues via Progressive Enhancement Learningcited by 60
  32. 2024Generalizing Deepfake Video Detection with Plug-and-Play: Video-Level Blending and Spatiotemporal Adapter Tuningcited by 57
  33. 2021Countering Malicious DeepFakes: Survey, Battleground, and Horizoncited by 56
  34. 2022MARLIN: Masked Autoencoder for facial video Representation LearnINgcited by 55
  35. 2023Detecting and Grounding Multi-Modal Media Manipulation and Beyondcited by 55
  36. 2023Beyond the Prior Forgery Knowledge: Mining Critical Clues for General Face Forgery Detectioncited by 50
  37. 2022SeeABLE: Soft Discrepancies and Bounded Contrastive Learning for Exposing Deepfakescited by 49
  38. 2021ADD: Frequency Attention and Multi-View based Knowledge Distillation to Detect Low-Quality Compressed Deepfake Imagescited by 48

50 most cited of 518 All 518 (JSON)