mlsanityData to 14 Oct 2026

CelebV-HQ: A Large-Scale Video Facial Attributes Dataset

arXiv 2207.12393 ↗First posted 25 Jul 2022cs.CVcited by 250

Not on the map. Why?

Cited by 49 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Large-scale datasets have played indispensable roles in the recent success of face generation/editing and significantly facilitated the advances of emerging research fields. However, the academic community still lacks a video dataset with diverse facial attribute annotations, which is crucial for the research on face-related videos. In this work, we propose a large-scale, high-quality, and diverse video dataset with rich facial attribute annotations, named the High-Quality Celebrity Video Dataset (CelebV-HQ). CelebV-HQ contains 35,666 video clips with the resolution of 512x512 at least, involving 15,653 identities. All clips are labeled manually with 83 facial attributes, covering appearance, action, and emotion. We conduct a comprehensive analysis in terms of age, ethnicity, brightness stability, motion smoothness, head pose diversity, and data quality to demonstrate the diversity and temporal coherence of CelebV-HQ. Besides, its versatility and potential are validated on two representative tasks, i.e., unconditional video generation and video facial attribute editing. Furthermore, we envision the future potential of CelebV-HQ, as well as the new opportunities and challenges it would bring to related research directions. Data, code, and models are publicly available. Project page: https://celebv-hq.github.io.

Key facts. Cited by 250 papers in the map (data through 14 Oct 2026). Builds on 78 of its 102 references that are in the map. First posted on arXiv 25 Jul 2022.

Builds on

78 of 102 references.

References · 78

  1. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  2. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  3. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  4. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  5. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  6. 2022Video Diffusion Modelscited by 2,305
  7. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,054
  8. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,465
  9. 2018Towards Accurate Generative Models of Video: A New Metric & Challengescited by 1,234
  10. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,205
  11. 2021Alias-Free Generative Adversarial Networkscited by 1,184
  12. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,098
38 more
  1. 2022CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformerscited by 985
  2. 2018VoxCeleb2: Deep Speaker Recognitioncited by 875
  3. 2016Simple Online and Realtime Trackingcited by 868
  4. 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
  5. 2017VoxCeleb: a large-scale speaker identification datasetcited by 732
  6. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  7. 2020First Order Motion Model for Image Animationcited by 704
  8. 2021VideoGPT: Video Generation using VQ-VAE and Transformerscited by 658
  9. 2019MaskGAN: Towards Diverse and Interactive Facial Image Manipulationcited by 628
  10. 2021Designing an Encoder for StyleGAN Image Manipulationcited by 544
  11. 2017MoCoGAN: Decomposing Motion and Content for Video Generationcited by 524
  12. 2021StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesiscited by 477
  13. 2019Face X-ray for More General Face Forgery Detectioncited by 470
  14. 2020Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstructioncited by 467
  15. 2020One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencingcited by 444
  16. 2020InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANscited by 394
  17. 2016Generating Videos with Scene Dynamicscited by 376
  18. 2021Animatable Neural Radiance Fields for Modeling Dynamic Human Bodiescited by 361
  19. 2021AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesiscited by 339
  20. 2019FSGAN: Subject Agnostic Face Swapping and Reenactmentcited by 320
  21. 2018Adversarially Robust Generalization Requires More Datacited by 318
  22. 2022Text2LIVE: Text-Driven Layered Image and Video Editingcited by 312
  23. 2019A Short Note on the Kinetics-700 Human Action Datasetcited by 310
  24. 2021StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2cited by 301
  25. 2021StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generationcited by 289
  26. 2021Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representationcited by 288
  27. 2020Lips Don't Lie: A Generalisable and Robust Approach to Face Forgery Detectioncited by 287
  28. 2021Motion Representations for Articulated Animationcited by 255
  29. 2021N"UWA: Visual Synthesis Pre-training for Neural visUal World creAtioncited by 253
  30. 2019Hierarchical Cross-Modal Talking Face Generationwith Dynamic Pixel-Wise Losscited by 252
  31. 2021HeadNeRF: A Real-time NeRF-based Parametric Head Modelcited by 228
  32. 2019FaceShifter: Towards High Fidelity And Occlusion Aware Face Swappingcited by 221
  33. 2018Talking Face Generation by Adversarially Disentangled Audio-Visual Representationcited by 212
  34. 2016Temporal Generative Adversarial Nets with Singular Value Clippingcited by 198
  35. 2022Generating Videos with Dynamics-aware Implicit Generative Adversarial Networkscited by 186
  36. 2021Audio-Driven Emotional Video Portraitscited by 180
  37. 2019Quality Assessment of In-the-Wild Videoscited by 164
  38. 2021A Good Image Generator Is What You Need for High-Resolution Video Synthesiscited by 163

50 most cited of 78 All 78 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 5; 2023: 32; 2024: 62; 2025: 101; 2026: 50.

250 papers.

Sort:

By area:

  1. 2024OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generationcited by 341
  2. 2024EMO: Emote Portrait Alive -- Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditionscited by 235
  3. 2024EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditionscited by 196
  4. 2024AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animationcited by 194
  5. 2024Identity-Preserving Text-to-Video Generation by Frequency Decompositioncited by 158
  6. 2025OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Modelscited by 129
  7. 2024Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformercited by 122
  8. 2023Parameter-Efficient Orthogonal Finetuning via Butterfly Factorizationcited by 114
  9. 2023CelebV-Text: A Large-Scale Facial Text-Video Datasetcited by 104
  10. 2024Loopy: Taming Audio-Driven Portrait Avatar with Long-Term Motion Dependencycited by 102
  11. 2023Emotional Speech-Driven Animation with Content-Emotion Disentanglementcited by 98
  12. 2025Controllable Video Generation: A Surveycited by 98
38 more
  1. 2024Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesiscited by 97
  2. 2025FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesiscited by 77
  3. 2025OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generationcited by 73
  4. 2024Sonic: Shifting Focus to Global Audio Perception in Portrait Animationcited by 72
  5. 2025HunyuanVideo-Avatar: High-Fidelity Audio-Driven Human Animation for Multiple Characterscited by 69
  6. 2025ConceptMaster: Multi-Concept Video Customization on Diffusion Transformer Models Without Test-Time Tuningcited by 68
  7. 2024Deepfake Generation and Detection: A Benchmark and Surveycited by 67
  8. 2025Let Them Talk: Audio-Driven Multi-Person Conversational Video Generationcited by 66
  9. 2024Portrait4D-v2: Pseudo Multi-View Data Creates Better 4D Head Synthesizercited by 64
  10. 2024Embodied Understanding of Driving Scenarioscited by 63
  11. 2024AVFF: Audio-Visual Feature Fusion for Video Deepfake Detectioncited by 59
  12. 2025HunyuanPortrait: Implicit Condition Control for Enhanced Portrait Animationcited by 59
  13. 2022MARLIN: Masked Autoencoder for facial video Representation LearnINgcited by 57
  14. 2023NOFA: NeRF-based One-shot Facial Avatar Reconstructioncited by 53
  15. 2024GGHead: Fast and Generalizable 3D Gaussian Headscited by 51
  16. 2023HyperReenact: One-Shot Reenactment via Jointly Learning to Refine and Retarget Facescited by 48
  17. 2023RenderMe-360: A Large Digital Asset Library and Benchmarks Towards High-fidelity Head Avatarscited by 45
  18. 2025StableAvatar: Infinite-Length Audio-Driven Avatar Video Generationcited by 44
  19. 2023High-Fidelity and Freely Controllable Talking Head Video Generationcited by 42
  20. 2025VideoAnydoor: High-fidelity Video Object Insertion with Precise Motion Controlcited by 42
  21. 2025InfiniteTalk: Audio-driven Video Generation for Sparse-Frame Video Dubbingcited by 41
  22. 2023LEO: Generative Latent Image Animator for Human Video Synthesiscited by 40
  23. 2024CyberHost: Taming Audio-driven Avatar Diffusion Model with Region Codebook Attentioncited by 39
  24. 2024MEMO: Memory-Guided Diffusion for Expressive Talking Video Generationcited by 38
  25. 2023Non-Contrastive Unsupervised Learning of Physiological Signals from Videocited by 37
  26. 2023MoStGAN-V: Video Generation with Temporal Motion Stylescited by 37
  27. 2024Stable-Hair: Real-World Hair Transfer via Diffusion Modelcited by 35
  28. 2025InfiniteYou: Flexible Photo Recrafting While Preserving Your Identitycited by 35
  29. 2024SimGen: Simulator-conditioned Driving Scene Generationcited by 34
  30. 2023VOODOO 3D: Volumetric Portrait Disentanglement for One-Shot 3D Head Reenactmentcited by 33
  31. 2023TalkCLIP: Talking Head Generation with Text-Guided Expressive Speaking Stylescited by 32
  32. 2025OmniHuman-1.5: Instilling an Active Mind in Avatars via Cognitive Simulationcited by 32
  33. 2022State of the Art in Dense Monocular Non-Rigid 3D Reconstructioncited by 30
  34. 2025SpeakerVid-5M: A Large-Scale High-Quality Dataset for Audio-Visual Dyadic Interactive Human Generationcited by 30
  35. 2023STPrivacy: Spatio-Temporal Privacy-Preserving Action Recognitioncited by 29
  36. 2025EchoShot: Multi-Shot Portrait Video Generationcited by 29
  37. 2024MegActor: Harness the Power of Raw Video for Vivid Portrait Animationcited by 28
  38. 2023LaughTalk: Expressive 3D Talking Head Generation with Laughtercited by 27

50 most cited of 250 All 250 (JSON)