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/DiMP-NCE+

DiMP-NCE+

Reported on 16 benchmarks across 2 tasks · 1 paper · 6 SOTA

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

Computer Vision16 results

  • Object TrackingonNeedForSpeed
    AUC· 2020-05-04
    0.65
    best: 0.692 (SAMURAI-L)
    SOTA
    How to Train Your Energy-Based Model for RegressionarXiv:2005.01698
  • Object TrackingonOTB-100
    AUC· 2020-05-04
    0.707
    SOTA
    How to Train Your Energy-Based Model for RegressionarXiv:2005.01698
  • Object TrackingonTrackingNet
    AUC· 2020-05-04
    0.787
    best: 0.841 (DropTrack)
    SOTA
    How to Train Your Energy-Based Model for RegressionarXiv:2005.01698
  • Visual Object TrackingonNeedForSpeed
    AUC· 2020-05-04
    0.65
    best: 0.692 (SAMURAI-L)
    SOTA
    How to Train Your Energy-Based Model for RegressionarXiv:2005.01698
  • Visual Object TrackingonOTB-100
    AUC· 2020-05-04
    0.707
    SOTA
    How to Train Your Energy-Based Model for RegressionarXiv:2005.01698
  • Visual Object TrackingonTrackingNet
    AUC· 2020-05-04
    0.787
    best: 0.841 (DropTrack)
    SOTA
    How to Train Your Energy-Based Model for RegressionarXiv:2005.01698
  • Object TrackingonUAV123
    AUC· 2020-05-04
    0.672
    best: 0.739 (LoRAT-g-378)
    How to Train Your Energy-Based Model for RegressionarXiv:2005.01698
  • Object TrackingonLaSOT
    AUC· 2020-05-04
    63.7
    best: 77.4 (SPMTrack-G)
    How to Train Your Energy-Based Model for RegressionarXiv:2005.01698
  • Object TrackingonTrackingNet
    Normalized Precision· 2020-05-04
    83.7
    best: 92.1 (MCITrack-L384)
    How to Train Your Energy-Based Model for RegressionarXiv:2005.01698
  • Object TrackingonTrackingNet
    Precision· 2020-05-04
    73.7
    best: 89.2 (MCITrack-L384)
    How to Train Your Energy-Based Model for RegressionarXiv:2005.01698
  • Object TrackingonTrackingNet
    Success Rate· 2020-05-04
    0.787
    best: 74.5 (ATOM(Resnet18)+EnergyRegression)
    How to Train Your Energy-Based Model for RegressionarXiv:2005.01698
  • Visual Object TrackingonUAV123
    AUC· 2020-05-04
    0.672
    best: 0.739 (LoRAT-g-378)
    How to Train Your Energy-Based Model for RegressionarXiv:2005.01698
  • Visual Object TrackingonLaSOT
    AUC· 2020-05-04
    63.7
    best: 77.4 (SPMTrack-G)
    How to Train Your Energy-Based Model for RegressionarXiv:2005.01698
  • Visual Object TrackingonTrackingNet
    Normalized Precision· 2020-05-04
    83.7
    best: 92.1 (MCITrack-L384)
    How to Train Your Energy-Based Model for RegressionarXiv:2005.01698
  • Visual Object TrackingonTrackingNet
    Precision· 2020-05-04
    73.7
    best: 89.2 (MCITrack-L384)
    How to Train Your Energy-Based Model for RegressionarXiv:2005.01698
  • Visual Object TrackingonTrackingNet
    Success Rate· 2020-05-04
    0.787
    best: 74.5 (ATOM(Resnet18)+EnergyRegression)
    How to Train Your Energy-Based Model for RegressionarXiv:2005.01698