TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/VideoGPT

VideoGPT

Reported on 14 benchmarks across 2 tasks · 2 papers · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision7 results

  • VideoonCelebV-HQ
    FID· 2022-07-25
    52.95
    best: 17.95 (StyleGAN-V)
    SOTA
    CelebV-HQ: A Large-Scale Video Facial Attributes DatasetarXiv:2207.12393
  • VideoonCelebV-HQ
    FVD· 2022-07-25
    177.89
    best: 212.41 (MoCoGAN-HD)
    CelebV-HQ: A Large-Scale Video Facial Attributes DatasetarXiv:2207.12393
  • VideoonUCF-101 16 frames, 128x128, Unconditional
    Inception Score· 2021-04-20
    24.69
    best: 28.87 (TGANv2 (2020))
    VideoGPT: Video Generation using VQ-VAE and TransformersarXiv:2104.10157
  • VideoonBAIR Robot Pushing
    Cond· 2021-04-20
    1
    best: 4 (MoCoGAN)
    VideoGPT: Video Generation using VQ-VAE and TransformersarXiv:2104.10157
  • VideoonBAIR Robot Pushing
    FVD score· 2021-04-20
    103.3
    best: 503 (MoCoGAN)
    VideoGPT: Video Generation using VQ-VAE and TransformersarXiv:2104.10157
  • VideoonBAIR Robot Pushing
    Pred· 2021-04-20
    15
    best: 28 (MCVD : c2t5p28)
    VideoGPT: Video Generation using VQ-VAE and TransformersarXiv:2104.10157
  • VideoonBAIR Robot Pushing
    Train· 2021-04-20
    15
    best: 20 (RaMViD)
    VideoGPT: Video Generation using VQ-VAE and TransformersarXiv:2104.10157

Natural Language Processing7 results

  • Video GenerationonCelebV-HQ
    FID· 2022-07-25
    52.95
    best: 17.95 (StyleGAN-V)
    SOTA
    CelebV-HQ: A Large-Scale Video Facial Attributes DatasetarXiv:2207.12393
  • Video GenerationonCelebV-HQ
    FVD· 2022-07-25
    177.89
    best: 212.41 (MoCoGAN-HD)
    CelebV-HQ: A Large-Scale Video Facial Attributes DatasetarXiv:2207.12393
  • Video GenerationonUCF-101 16 frames, 128x128, Unconditional
    Inception Score· 2021-04-20
    24.69
    best: 28.87 (TGANv2 (2020))
    VideoGPT: Video Generation using VQ-VAE and TransformersarXiv:2104.10157
  • Video GenerationonBAIR Robot Pushing
    Cond· 2021-04-20
    1
    best: 4 (MoCoGAN)
    VideoGPT: Video Generation using VQ-VAE and TransformersarXiv:2104.10157
  • Video GenerationonBAIR Robot Pushing
    FVD score· 2021-04-20
    103.3
    best: 503 (MoCoGAN)
    VideoGPT: Video Generation using VQ-VAE and TransformersarXiv:2104.10157
  • Video GenerationonBAIR Robot Pushing
    Pred· 2021-04-20
    15
    best: 28 (MCVD : c2t5p28)
    VideoGPT: Video Generation using VQ-VAE and TransformersarXiv:2104.10157
  • Video GenerationonBAIR Robot Pushing
    Train· 2021-04-20
    15
    best: 20 (RaMViD)
    VideoGPT: Video Generation using VQ-VAE and TransformersarXiv:2104.10157