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/DeciWatch

DeciWatch

Reported on 14 benchmarks across 5 tasks · 1 paper · 14 SOTA

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

Computer Vision5 results

  • 3D Human Pose EstimationonAIST++
    MPJPE· 2022-03-16
    67.2
    best: 69.2 (SPIN + HANet (T=101))
    SOTA
    DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose EstimationarXiv:2203.08713
  • Pose EstimationonJ-HMDB
    Mean PCK@0.05· 2022-03-16
    80.6
    best: 91.9 (SimpleBaseline + HANet)
    SOTA
    DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose EstimationarXiv:2203.08713
  • Pose EstimationonJ-HMDB
    Mean PCK@0.1· 2022-03-16
    94.6
    best: 98.3 (SimpleBaseline + HANet)
    SOTA
    DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose EstimationarXiv:2203.08713
  • Pose EstimationonJ-HMDB
    Mean PCK@0.2· 2022-03-16
    99
    best: 99.6 (SimpleBaseline + HANet)
    SOTA
    DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose EstimationarXiv:2203.08713
  • Pose EstimationonAIST++
    MPJPE· 2022-03-16
    67.2
    best: 69.2 (SPIN + HANet (T=101))
    SOTA
    DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose EstimationarXiv:2203.08713

Methodology4 results

  • 3DonJ-HMDB
    Mean PCK@0.05· 2022-03-16
    80.6
    best: 91.9 (SimpleBaseline + HANet)
    SOTA
    DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose EstimationarXiv:2203.08713
  • 3DonJ-HMDB
    Mean PCK@0.1· 2022-03-16
    94.6
    best: 98.3 (SimpleBaseline + HANet)
    SOTA
    DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose EstimationarXiv:2203.08713
  • 3DonJ-HMDB
    Mean PCK@0.2· 2022-03-16
    99
    best: 99.6 (SimpleBaseline + HANet)
    SOTA
    DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose EstimationarXiv:2203.08713
  • 3DonAIST++
    MPJPE· 2022-03-16
    67.2
    best: 69.2 (SPIN + HANet (T=101))
    SOTA
    DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose EstimationarXiv:2203.08713

Audio4 results

  • 1 Image, 2*2 StitchionJ-HMDB
    Mean PCK@0.05· 2022-03-16
    80.6
    best: 91.9 (SimpleBaseline + HANet)
    SOTA
    DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose EstimationarXiv:2203.08713
  • 1 Image, 2*2 StitchionJ-HMDB
    Mean PCK@0.1· 2022-03-16
    94.6
    best: 98.3 (SimpleBaseline + HANet)
    SOTA
    DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose EstimationarXiv:2203.08713
  • 1 Image, 2*2 StitchionJ-HMDB
    Mean PCK@0.2· 2022-03-16
    99
    best: 99.6 (SimpleBaseline + HANet)
    SOTA
    DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose EstimationarXiv:2203.08713
  • 1 Image, 2*2 StitchionAIST++
    MPJPE· 2022-03-16
    67.2
    best: 69.2 (SPIN + HANet (T=101))
    SOTA
    DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose EstimationarXiv:2203.08713

Knowledge Base1 result

  • 2D Human Pose EstimationonJHMDB (2D poses only)
    PCK· 2022-03-16
    98.8
    SOTA
    DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose EstimationarXiv:2203.08713