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/RepNet

RepNet

Reported on 22 benchmarks across 5 tasks · 3 papers · 6 SOTA

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

Computer Vision19 results

  • Repetitive Action CountingonCountix
    OBO· 2024-11-13
    0.7047
    SOTA
    A Short Note on Evaluating RepNet for Temporal Repetition Counting in VideosarXiv:2411.08878
  • Repetitive Action CountingonUCFRep
    MAE· 2024-11-13
    0.2088
    SOTA
    A Short Note on Evaluating RepNet for Temporal Repetition Counting in VideosarXiv:2411.08878
  • Repetitive Action CountingonUCFRep
    OBO· 2024-11-13
    0.7333
    SOTA
    A Short Note on Evaluating RepNet for Temporal Repetition Counting in VideosarXiv:2411.08878
  • Repetitive Action CountingonCountix
    MAE· 2020-06-27
    0.3641
    best: 0.276 (ESCounts)
    SOTA
    Counting Out Time: Class Agnostic Video Repetition Counting in the WildarXiv:2006.15418
  • Repetitive Action CountingonCountix
    OBO· 2020-06-27
    0.3034
    best: 0.7047
    SOTA
    Counting Out Time: Class Agnostic Video Repetition Counting in the WildarXiv:2006.15418
  • Repetitive Action CountingonRepCount
    OBO· 2020-06-27
    0.013
    best: 0.563 (ESCounts)
    SOTA
    Counting Out Time: Class Agnostic Video Repetition Counting in the WildarXiv:2006.15418
  • Repetitive Action CountingonCountix
    MAE· 2024-11-13
    0.3002
    best: 0.276 (ESCounts)
    A Short Note on Evaluating RepNet for Temporal Repetition Counting in VideosarXiv:2411.08878
  • Repetitive Action CountingonRepCount
    MAE· 2024-11-13
    0.3308
    best: 0.213 (ESCounts)
    A Short Note on Evaluating RepNet for Temporal Repetition Counting in VideosarXiv:2411.08878
  • Repetitive Action CountingonRepCount
    OBO· 2024-11-13
    0.5329
    best: 0.563 (ESCounts)
    A Short Note on Evaluating RepNet for Temporal Repetition Counting in VideosarXiv:2411.08878
  • 3D Human Pose EstimationonHuman3.6M
    Average MPJPE (mm)· 2019-02-26
    89.9
    best: 131.7 (Rhodin et al.)
    RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose EstimationarXiv:1902.09868
  • 3D Human Pose EstimationonHuman3.6M
    Frames Needed· 2019-02-26
    1
    best: 300 (Sparseness Meets Deepness)
    RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose EstimationarXiv:1902.09868
  • 3D Human Pose EstimationonHuman3.6M
    Average MPJPE (mm)· 2019-02-26
    89.9
    best: 131.7 (Rhodin et al.)
    RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose EstimationarXiv:1902.09868
  • 3D Human Pose EstimationonHuman3.6M
    Number of Frames Per View· 2019-02-26
    1
    best: 243 (VideoPose3D (T=243))
    RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose EstimationarXiv:1902.09868
  • 3D Human Pose EstimationonHuman3.6M
    Number of Views· 2019-02-26
    1
    best: 2 (Kocabas et al.)
    RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose EstimationarXiv:1902.09868
  • Pose EstimationonHuman3.6M
    Average MPJPE (mm)· 2019-02-26
    89.9
    best: 131.7 (Rhodin et al.)
    RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose EstimationarXiv:1902.09868
  • Pose EstimationonHuman3.6M
    Frames Needed· 2019-02-26
    1
    best: 300 (Sparseness Meets Deepness)
    RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose EstimationarXiv:1902.09868
  • Pose EstimationonHuman3.6M
    Average MPJPE (mm)· 2019-02-26
    89.9
    best: 131.7 (Rhodin et al.)
    RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose EstimationarXiv:1902.09868
  • Pose EstimationonHuman3.6M
    Number of Frames Per View· 2019-02-26
    1
    best: 243 (VideoPose3D (T=243))
    RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose EstimationarXiv:1902.09868
  • Pose EstimationonHuman3.6M
    Number of Views· 2019-02-26
    1
    best: 2 (Kocabas et al.)
    RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose EstimationarXiv:1902.09868

Methodology5 results

  • 3DonHuman3.6M
    Average MPJPE (mm)· 2019-02-26
    89.9
    best: 131.7 (Rhodin et al.)
    RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose EstimationarXiv:1902.09868
  • 3DonHuman3.6M
    Frames Needed· 2019-02-26
    1
    best: 300 (Sparseness Meets Deepness)
    RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose EstimationarXiv:1902.09868
  • 3DonHuman3.6M
    Average MPJPE (mm)· 2019-02-26
    89.9
    best: 131.7 (Rhodin et al.)
    RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose EstimationarXiv:1902.09868
  • 3DonHuman3.6M
    Number of Frames Per View· 2019-02-26
    1
    best: 243 (VideoPose3D (T=243))
    RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose EstimationarXiv:1902.09868
  • 3DonHuman3.6M
    Number of Views· 2019-02-26
    1
    best: 2 (Kocabas et al.)
    RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose EstimationarXiv:1902.09868

Audio5 results

  • 1 Image, 2*2 StitchionHuman3.6M
    Average MPJPE (mm)· 2019-02-26
    89.9
    best: 131.7 (Rhodin et al.)
    RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose EstimationarXiv:1902.09868
  • 1 Image, 2*2 StitchionHuman3.6M
    Frames Needed· 2019-02-26
    1
    best: 300 (Sparseness Meets Deepness)
    RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose EstimationarXiv:1902.09868
  • 1 Image, 2*2 StitchionHuman3.6M
    Average MPJPE (mm)· 2019-02-26
    89.9
    best: 131.7 (Rhodin et al.)
    RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose EstimationarXiv:1902.09868
  • 1 Image, 2*2 StitchionHuman3.6M
    Number of Frames Per View· 2019-02-26
    1
    best: 243 (VideoPose3D (T=243))
    RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose EstimationarXiv:1902.09868
  • 1 Image, 2*2 StitchionHuman3.6M
    Number of Views· 2019-02-26
    1
    best: 2 (Kocabas et al.)
    RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose EstimationarXiv:1902.09868