mlsanityData to 7 Oct 2026

Human Action CLIPs: Detecting AI-generated Human Motion

arXiv 2412.00526 ↗First posted 30 Nov 2024cs.CV cs.AI cs.GRcited by 4

Not on the map. Why?

Abstract (arXiv)

AI-generated video generation continues its journey through the uncanny valley to produce content that is increasingly perceptually indistinguishable from reality. To better protect individuals, organizations, and societies from its malicious applications, we describe an effective and robust technique for distinguishing real from AI-generated human motion using multi-modal semantic embeddings. Our method is robust to the types of laundering that typically confound more low- to mid-level approaches, including resolution and compression attacks. This method is evaluated against DeepAction, a custom-built, open-sourced dataset of video clips with human actions generated by seven text-to-video AI models and matching real footage. The dataset is available under an academic license at https://www.huggingface.co/datasets/faridlab/deepaction_v1.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 32 of its 52 references that are in the map. First posted on arXiv 30 Nov 2024.

Builds on

32 of 52 references.

References · 32

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  3. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,048
  4. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
  5. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformercited by 2,198
  6. 2021LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairscited by 1,544
  7. 2022PaLI: A Jointly-Scaled Multilingual Language-Image Modelcited by 762
  8. 2023VideoPoet: A Large Language Model for Zero-Shot Video Generationcited by 479
  9. 2024Lumiere: A Space-Time Diffusion Model for Video Generationcited by 450
  10. 2021How Much Can CLIP Benefit Vision-and-Language Tasks?cited by 321
  11. 2019FSGAN: Subject Agnostic Face Swapping and Reenactmentcited by 319
  12. 2023Raising the Bar of AI-generated Image Detection with CLIPcited by 163
20 more
  1. 2024Vidu: a Highly Consistent, Dynamic and Skilled Text-to-Video Generator with Diffusion Modelscited by 159
  2. 2022CLIP Models are Few-shot Learners: Empirical Studies on VQA and Visual Entailmentcited by 113
  3. 2024From Audio to Photoreal Embodiment: Synthesizing Humans in Conversationscited by 82
  4. 2020Evading Deepfake-Image Detectors with White- and Black-Box Attackscited by 80
  5. 2024Can ChatGPT Detect DeepFakes? A Study of Using Multimodal Large Language Models for Media Forensicscited by 68
  6. 2020Detecting Deep-Fake Videos from Appearance and Behaviorcited by 66
  7. 20244Real: Towards Photorealistic 4D Scene Generation via Video Diffusion Modelscited by 64
  8. 2021Playing for 3D Human Recoverycited by 63
  9. 2020DeepFake Detection Based on the Discrepancy Between the Face and its Contextcited by 56
  10. 2024CLIPping the Deception: Adapting Vision-Language Models for Universal Deepfake Detectioncited by 47
  11. 2024AnimateDiff-Lightning: Cross-Model Diffusion Distillationcited by 47
  12. 2024Jina CLIP: Your CLIP Model Is Also Your Text Retrievercited by 46
  13. 2024Beyond Deepfake Images: Detecting AI-Generated Videoscited by 22
  14. 2022Model Attribution of Face-swap Deepfake Videoscited by 17
  15. 2024DeCLIP: Decoding CLIP representations for deepfake localizationcited by 17
  16. 2024Exposing Lip-syncing Deepfakes from Mouth Inconsistenciescited by 15
  17. 2024People are poorly equipped to detect AI-powered voice clonescited by 12
  18. 2022Deepfake audio detection by speaker verificationcited by 11
  19. 2024Exploring the Adversarial Robustness of CLIP for AI-generated Image Detectioncited by 11
  20. 2023Single and Multi-Speaker Cloned Voice Detection: From Perceptual to Learned Featurescited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 1.

4 papers.

  1. 2025Seeing What Matters: Generalizable AI-generated Video Detection with Forensic-Oriented Augmentationcited by 23
  2. 2025Survey on AI-Generated Media Detection: From Non-MLLM to MLLMcited by 12
  3. 2025Advance Fake Video Detection via Vision Transformerscited by 1
  4. 2026CAM-VFD: Cross-Attention Multimodal Video Forgery Detectioncited by 0