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/CrowdDet

CrowdDet

Reported on 26 benchmarks across 7 tasks · 1 paper · 5 SOTA

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

Computer Vision10 results

  • Object DetectiononCrowdHuman (full body)
    AP· 2020-03-20
    90.7
    best: 97.2 (InternImage-H)
    SOTA
    Detection in Crowded Scenes: One Proposal, Multiple PredictionsarXiv:2003.09163
  • Object DetectiononCrowdHuman (full body)
    mMR· 2020-03-20
    41.4
    best: 50.49 (Faster RCNN (ResNet50))
    Detection in Crowded Scenes: One Proposal, Multiple PredictionsarXiv:2003.09163
  • Pedestrian DetectiononTJU-Ped-traffic
    ALL (miss rate)· 2020-03-20
    36.94
    best: 41.4 (RetinaNet)
    Detection in Crowded Scenes: One Proposal, Multiple PredictionsarXiv:2003.09163
  • Pedestrian DetectiononTJU-Ped-traffic
    HO (miss rate)· 2020-03-20
    61.22
    best: 63.73 (FCOS)
    Detection in Crowded Scenes: One Proposal, Multiple PredictionsarXiv:2003.09163
  • Pedestrian DetectiononTJU-Ped-traffic
    R (miss rate)· 2020-03-20
    20.82
    best: 24.35 (FCOS)
    Detection in Crowded Scenes: One Proposal, Multiple PredictionsarXiv:2003.09163
  • Pedestrian DetectiononTJU-Ped-traffic
    R+HO (miss rate)· 2020-03-20
    25.28
    best: 28.86 (FCOS)
    Detection in Crowded Scenes: One Proposal, Multiple PredictionsarXiv:2003.09163
  • Pedestrian DetectiononTJU-Ped-campus
    ALL (miss rate)· 2020-03-20
    35.9
    best: 44.34 (RetinaNet)
    Detection in Crowded Scenes: One Proposal, Multiple PredictionsarXiv:2003.09163
  • Pedestrian DetectiononTJU-Ped-campus
    HO (miss rate)· 2020-03-20
    66.38
    best: 81.28 (FCOS)
    Detection in Crowded Scenes: One Proposal, Multiple PredictionsarXiv:2003.09163
  • Pedestrian DetectiononTJU-Ped-campus
    R (miss rate)· 2020-03-20
    25.73
    best: 34.73 (RetinaNet)
    Detection in Crowded Scenes: One Proposal, Multiple PredictionsarXiv:2003.09163
  • Pedestrian DetectiononTJU-Ped-campus
    R+HO (miss rate)· 2020-03-20
    33.63
    best: 42.26 (RetinaNet)
    Detection in Crowded Scenes: One Proposal, Multiple PredictionsarXiv:2003.09163

Methodology8 results

  • 3DonCrowdHuman (full body)
    AP· 2020-03-20
    90.7
    best: 97.2 (InternImage-H)
    SOTA
    Detection in Crowded Scenes: One Proposal, Multiple PredictionsarXiv:2003.09163
  • 2D ClassificationonCrowdHuman (full body)
    AP· 2020-03-20
    90.7
    best: 97.2 (InternImage-H)
    SOTA
    Detection in Crowded Scenes: One Proposal, Multiple PredictionsarXiv:2003.09163
  • 2D Object DetectiononCrowdHuman (full body)
    AP· 2020-03-20
    90.7
    best: 97.2 (InternImage-H)
    SOTA
    Detection in Crowded Scenes: One Proposal, Multiple PredictionsarXiv:2003.09163
  • 16konCrowdHuman (full body)
    AP· 2020-03-20
    90.7
    best: 97.2 (InternImage-H)
    SOTA
    Detection in Crowded Scenes: One Proposal, Multiple PredictionsarXiv:2003.09163
  • 3DonCrowdHuman (full body)
    mMR· 2020-03-20
    41.4
    best: 50.49 (Faster RCNN (ResNet50))
    Detection in Crowded Scenes: One Proposal, Multiple PredictionsarXiv:2003.09163
  • 2D ClassificationonCrowdHuman (full body)
    mMR· 2020-03-20
    41.4
    best: 50.49 (Faster RCNN (ResNet50))
    Detection in Crowded Scenes: One Proposal, Multiple PredictionsarXiv:2003.09163
  • 2D Object DetectiononCrowdHuman (full body)
    mMR· 2020-03-20
    41.4
    best: 50.49 (Faster RCNN (ResNet50))
    Detection in Crowded Scenes: One Proposal, Multiple PredictionsarXiv:2003.09163
  • 16konCrowdHuman (full body)
    mMR· 2020-03-20
    41.4
    best: 50.49 (Faster RCNN (ResNet50))
    Detection in Crowded Scenes: One Proposal, Multiple PredictionsarXiv:2003.09163

Robots8 results

  • Autonomous VehiclesonTJU-Ped-traffic
    ALL (miss rate)· 2020-03-20
    36.94
    best: 41.4 (RetinaNet)
    Detection in Crowded Scenes: One Proposal, Multiple PredictionsarXiv:2003.09163
  • Autonomous VehiclesonTJU-Ped-traffic
    HO (miss rate)· 2020-03-20
    61.22
    best: 63.73 (FCOS)
    Detection in Crowded Scenes: One Proposal, Multiple PredictionsarXiv:2003.09163
  • Autonomous VehiclesonTJU-Ped-traffic
    R (miss rate)· 2020-03-20
    20.82
    best: 24.35 (FCOS)
    Detection in Crowded Scenes: One Proposal, Multiple PredictionsarXiv:2003.09163
  • Autonomous VehiclesonTJU-Ped-traffic
    R+HO (miss rate)· 2020-03-20
    25.28
    best: 28.86 (FCOS)
    Detection in Crowded Scenes: One Proposal, Multiple PredictionsarXiv:2003.09163
  • Autonomous VehiclesonTJU-Ped-campus
    ALL (miss rate)· 2020-03-20
    35.9
    best: 44.34 (RetinaNet)
    Detection in Crowded Scenes: One Proposal, Multiple PredictionsarXiv:2003.09163
  • Autonomous VehiclesonTJU-Ped-campus
    HO (miss rate)· 2020-03-20
    66.38
    best: 81.28 (FCOS)
    Detection in Crowded Scenes: One Proposal, Multiple PredictionsarXiv:2003.09163
  • Autonomous VehiclesonTJU-Ped-campus
    R (miss rate)· 2020-03-20
    25.73
    best: 34.73 (RetinaNet)
    Detection in Crowded Scenes: One Proposal, Multiple PredictionsarXiv:2003.09163
  • Autonomous VehiclesonTJU-Ped-campus
    R+HO (miss rate)· 2020-03-20
    33.63
    best: 42.26 (RetinaNet)
    Detection in Crowded Scenes: One Proposal, Multiple PredictionsarXiv:2003.09163