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/MBNET

MBNET

Reported on 10 benchmarks across 3 tasks

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

Computer Vision9 results

  • Person Re-IdentificationonMarket-1501
    Rank-1
    94.77
    best: 98 (st-ReID(RE, RK))
  • Person Re-IdentificationonMarket-1501
    mAP
    92.64
    best: 96.21 (Unsupervised Pre-training (ResNet101+RK))
  • Person Re-IdentificationonDukeMTMC-reID
    Rank-1
    94.39
  • Person Re-IdentificationonDukeMTMC-reID
    Rank-5
    96.45
  • Person Re-IdentificationonDukeMTMC-reID
    Rank-1
    94.39
    best: 95.6 (CTL Model (ResNet50, 256x128))
  • Person Re-IdentificationonDukeMTMC-reID
    Rank-10
    96.9
    best: 97.9 (CTL Model (ResNet50, 256x128))
  • Person Re-IdentificationonDukeMTMC-reID
    Rank-5
    96.45
    best: 96.5 (Viewpoint-Aware Loss(RK))
  • Person Re-IdentificationonDukeMTMC-reID
    mAP
    83.58
    best: 97.1 (DenseIL)
  • Pedestrian Attribute RecognitiononDukeMTMC-attribute
    Accuracy
    91.13

Robots1 result

  • Autonomous VehiclesonDukeMTMC-attribute
    Accuracy
    91.13