mlsanityData to 7 Oct 2026

Spatial-Temporal Frequency Forgery Clue for Video Forgery Detection in VIS and NIR Scenario

arXiv 2207.01906 ↗First posted 5 Jul 2022cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

In recent years, with the rapid development of face editing and generation, more and more fake videos are circulating on social media, which has caused extreme public concerns. Existing face forgery detection methods based on frequency domain find that the GAN forged images have obvious grid-like visual artifacts in the frequency spectrum compared to the real images. But for synthesized videos, these methods only confine to single frame and pay little attention to the most discriminative part and temporal frequency clue among different frames. To take full advantage of the rich information in video sequences, this paper performs video forgery detection on both spatial and temporal frequency domains and proposes a Discrete Cosine Transform-based Forgery Clue Augmentation Network (FCAN-DCT) to achieve a more comprehensive spatial-temporal feature representation. FCAN-DCT consists of a backbone network and two branches: Compact Feature Extraction (CFE) module and Frequency Temporal Attention (FTA) module. We conduct thorough experimental assessments on two visible light (VIS) based datasets WildDeepfake and Celeb-DF (v2), and our self-built video forgery dataset DeepfakeNIR, which is the first video forgery dataset on near-infrared modality. The experimental results demonstrate the effectiveness of our method on detecting forgery videos in both VIS and NIR scenarios.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 55 of its 89 references that are in the map. First posted on arXiv 5 Jul 2022.

Builds on

55 of 89 references.

References · 55

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  3. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  4. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  5. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  6. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
  7. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  8. 2017A Closer Look at Spatiotemporal Convolutions for Action Recognitioncited by 1,139
  9. 2019FaceForensics++: Learning to Detect Manipulated Facial Imagescited by 1,095
  10. 2019CNN-generated images are surprisingly easy to spot... for nowcited by 842
  11. 2020Contrastive Learning for Unpaired Image-to-Image Translationcited by 637
  12. 2019Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensicscited by 573
38 more
  1. 2020Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Cluescited by 518
  2. 2020Leveraging Frequency Analysis for Deep Fake Image Recognitioncited by 501
  3. 2019Face X-ray for More General Face Forgery Detectioncited by 469
  4. 2018MesoNet: a Compact Facial Video Forgery Detection Networkcited by 409
  5. 2021Multi-attentional Deepfake Detectioncited by 339
  6. 2022Detecting Deepfakes with Self-Blended Imagescited by 332
  7. 2018Exposing Deep Fakes Using Inconsistent Head Posescited by 294
  8. 2020Lips Don't Lie: A Generalisable and Robust Approach to Face Forgery Detectioncited by 286
  9. 2021Generalizing Face Forgery Detection with High-frequency Featurescited by 261
  10. 2020DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detectioncited by 251
  11. 2021SimSwap: An Efficient Framework For High Fidelity Face Swappingcited by 243
  12. 2021Spatial-Phase Shallow Learning: Rethinking Face Forgery Detection in Frequency Domaincited by 241
  13. 2021WildDeepfake: A Challenging Real-World Dataset for Deepfake Detectioncited by 207
  14. 2018Capsule-Forensics: Using Capsule Networks to Detect Forged Images and Videoscited by 180
  15. 2020Learning Self-Consistency for Deepfake Detectioncited by 179
  16. 2017Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognitioncited by 178
  17. 2021Exploring Temporal Coherence for More General Video Face Forgery Detectioncited by 158
  18. 2020Adversarial Latent Autoencoderscited by 155
  19. 2017S3FD: Single Shot Scale-invariant Face Detectorcited by 142
  20. 2019Fourier Spectrum Discrepancies in Deep Network Generated Imagescited by 138
  21. 2021Frequency-aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery Detectioncited by 133
  22. 2020DeepFaceLab: Integrated, flexible and extensible face-swapping frameworkcited by 129
  23. 2021Representative Forgery Mining for Fake Face Detectioncited by 108
  24. 2020Neural Head Reenactment with Latent Pose Descriptorscited by 106
  25. 2021One Shot Face Swapping on Megapixelscited by 105
  26. 2020Not made for each other- Audio-Visual Dissonance-based Deepfake Detection and Localizationcited by 89
  27. 2021Spatiotemporal Inconsistency Learning for DeepFake Video Detectioncited by 88
  28. 2021A Closer Look at Fourier Spectrum Discrepancies for CNN-generated Images Detectioncited by 68
  29. 2020HistoGAN: Controlling Colors of GAN-Generated and Real Images via Color Histogramscited by 64
  30. 2021Exploiting Fine-grained Face Forgery Clues via Progressive Enhancement Learningcited by 60
  31. 2021Improving the Efficiency and Robustness of Deepfakes Detection through Precise Geometric Featurescited by 57
  32. 2020Sharp Multiple Instance Learning for DeepFake Video Detectioncited by 54
  33. 2021ADD: Frequency Attention and Multi-View based Knowledge Distillation to Detect Low-Quality Compressed Deepfake Imagescited by 48
  34. 2021FReTAL: Generalizing Deepfake Detection using Knowledge Distillation and Representation Learningcited by 43
  35. 2021High-Fidelity and Arbitrary Face Editingcited by 35
  36. 2020Mesh Guided One-shot Face Reenactment using Graph Convolutional Networkscited by 30
  37. 2021FaceController: Controllable Attribute Editing for Face in the Wildcited by 22
  38. 2021Learning to Disentangle GAN Fingerprint for Fake Image Attributioncited by 19

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 2; 2025: 1.

5 papers.

  1. 2025Beyond Spatial Frequency: Pixel-wise Temporal Frequency-based Deepfake Video Detectioncited by 12
  2. 2023Multi-spectral Class Center Network for Face Manipulation Detection and Localizationcited by 11
  3. 2024Open-Set Deepfake Detection: A Parameter-Efficient Adaptation Method with Forgery Style Mixturecited by 7
  4. 2023Exploiting Facial Relationships and Feature Aggregation for Multi-Face Forgery Detectioncited by 5
  5. 2024Band-Attention Modulation Network for Robust Face Forgery Detectioncited by 1