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/PlayItBackX3

PlayItBackX3

Reported on 24 benchmarks across 2 tasks · 1 paper · 18 SOTA

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

Audio12 results

  • Audio ClassificationonEPIC-KITCHENS-100
    Top-1 Action· 2022-10-20
    15.9
    best: 46 (Audiovisual Masked Autoencoder (Audiovisual, Single))
    SOTA
    Play It Back: Iterative Attention for Audio RecognitionarXiv:2210.11328
  • Audio ClassificationonEPIC-KITCHENS-100
    Top-1 Noun· 2022-10-20
    23.1
    best: 56.4 (Audiovisual Masked Autoencoder (Audiovisual, Single))
    SOTA
    Play It Back: Iterative Attention for Audio RecognitionarXiv:2210.11328
  • Audio ClassificationonEPIC-KITCHENS-100
    Top-1 Verb· 2022-10-20
    47
    best: 71.4 (Audiovisual Masked Autoencoder (Audiovisual, Single))
    SOTA
    Play It Back: Iterative Attention for Audio RecognitionarXiv:2210.11328
  • Audio ClassificationonEPIC-KITCHENS-100
    Top-5 Action· 2022-10-20
    29.2
    SOTA
    Play It Back: Iterative Attention for Audio RecognitionarXiv:2210.11328
  • Audio ClassificationonEPIC-KITCHENS-100
    Top-5 Noun· 2022-10-20
    45.1
    SOTA
    Play It Back: Iterative Attention for Audio RecognitionarXiv:2210.11328
  • Audio ClassificationonEPIC-KITCHENS-100
    Top-5 Verb· 2022-10-20
    78.7
    SOTA
    Play It Back: Iterative Attention for Audio RecognitionarXiv:2210.11328
  • Audio ClassificationonVGGSound
    AUC· 2022-10-20
    97.8
    SOTA
    Play It Back: Iterative Attention for Audio RecognitionarXiv:2210.11328
  • Audio ClassificationonVGGSound
    Mean AP· 2022-10-20
    56.1
    SOTA
    Play It Back: Iterative Attention for Audio RecognitionarXiv:2210.11328
  • Audio ClassificationonVGGSound
    d-prime· 2022-10-20
    2.846
    SOTA
    Play It Back: Iterative Attention for Audio RecognitionarXiv:2210.11328
  • Audio ClassificationonAudioSet
    Test mAP· 2022-10-20
    0.477
    best: 0.558 (OmniVec2)
    Play It Back: Iterative Attention for Audio RecognitionarXiv:2210.11328
  • Audio ClassificationonVGGSound
    Top 1 Accuracy· 2022-10-20
    53.7
    best: 69.8 (Mirasol3B)
    Play It Back: Iterative Attention for Audio RecognitionarXiv:2210.11328
  • Audio ClassificationonVGGSound
    Top 5 Accuracy· 2022-10-20
    79.2
    best: 85.7 (MMT (Audio-Visual))
    Play It Back: Iterative Attention for Audio RecognitionarXiv:2210.11328

Methodology12 results

  • ClassificationonEPIC-KITCHENS-100
    Top-1 Action· 2022-10-20
    15.9
    best: 46 (Audiovisual Masked Autoencoder (Audiovisual, Single))
    SOTA
    Play It Back: Iterative Attention for Audio RecognitionarXiv:2210.11328
  • ClassificationonEPIC-KITCHENS-100
    Top-1 Noun· 2022-10-20
    23.1
    best: 56.4 (Audiovisual Masked Autoencoder (Audiovisual, Single))
    SOTA
    Play It Back: Iterative Attention for Audio RecognitionarXiv:2210.11328
  • ClassificationonEPIC-KITCHENS-100
    Top-1 Verb· 2022-10-20
    47
    best: 71.4 (Audiovisual Masked Autoencoder (Audiovisual, Single))
    SOTA
    Play It Back: Iterative Attention for Audio RecognitionarXiv:2210.11328
  • ClassificationonEPIC-KITCHENS-100
    Top-5 Action· 2022-10-20
    29.2
    SOTA
    Play It Back: Iterative Attention for Audio RecognitionarXiv:2210.11328
  • ClassificationonEPIC-KITCHENS-100
    Top-5 Noun· 2022-10-20
    45.1
    SOTA
    Play It Back: Iterative Attention for Audio RecognitionarXiv:2210.11328
  • ClassificationonEPIC-KITCHENS-100
    Top-5 Verb· 2022-10-20
    78.7
    SOTA
    Play It Back: Iterative Attention for Audio RecognitionarXiv:2210.11328
  • ClassificationonVGGSound
    AUC· 2022-10-20
    97.8
    SOTA
    Play It Back: Iterative Attention for Audio RecognitionarXiv:2210.11328
  • ClassificationonVGGSound
    Mean AP· 2022-10-20
    56.1
    SOTA
    Play It Back: Iterative Attention for Audio RecognitionarXiv:2210.11328
  • ClassificationonVGGSound
    d-prime· 2022-10-20
    2.846
    SOTA
    Play It Back: Iterative Attention for Audio RecognitionarXiv:2210.11328
  • ClassificationonAudioSet
    Test mAP· 2022-10-20
    0.477
    best: 0.558 (OmniVec2)
    Play It Back: Iterative Attention for Audio RecognitionarXiv:2210.11328
  • ClassificationonVGGSound
    Top 1 Accuracy· 2022-10-20
    53.7
    best: 69.8 (Mirasol3B)
    Play It Back: Iterative Attention for Audio RecognitionarXiv:2210.11328
  • ClassificationonVGGSound
    Top 5 Accuracy· 2022-10-20
    79.2
    best: 85.7 (MMT (Audio-Visual))
    Play It Back: Iterative Attention for Audio RecognitionarXiv:2210.11328