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/CSRNet

CSRNet

Reported on 12 benchmarks across 1 task · 2 papers · 8 SOTA

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

Computer Vision12 results

  • CrowdsonDLR-ACD
    MAE· 2019-09-27
    3388.8
    best: 833.3 (Liu et al)
    SOTA
    MRCNet: Crowd Counting and Density Map Estimation in Aerial and Ground ImageryarXiv:1909.12743
  • CrowdsonDLR-ACD
    RMSE· 2019-09-27
    4456.5
    best: 1085.9 (Liu et al)
    SOTA
    MRCNet: Crowd Counting and Density Map Estimation in Aerial and Ground ImageryarXiv:1909.12743
  • CrowdsonShanghaiTech B
    MAE· 2018-02-27
    10.6
    best: 5.51 (EBC-ZIP-B)
    SOTA
    CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested ScenesarXiv:1802.10062
  • CrowdsonTRANCOS
    MAE· 2018-02-27
    3.56
    best: 2.22 (M-SFANet+M-SegNet)
    SOTA
    CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested ScenesarXiv:1802.10062
  • CrowdsonShanghaiTech A
    MAE· 2018-02-27
    68.2
    best: 47.81 (EBC-ZIP-B)
    SOTA
    CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested ScenesarXiv:1802.10062
  • CrowdsonVenice
    MAE· 2018-02-27
    35.8
    best: 20.5 (ECAN)
    SOTA
    CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested ScenesarXiv:1802.10062
  • CrowdsonUCF CC 50
    MAE· 2018-02-27
    266.1
    best: 154.8 (APGCC)
    SOTA
    CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested ScenesarXiv:1802.10062
  • CrowdsonWorldExpo’10
    Average MAE· 2018-02-27
    8.6
    best: 7.2 (ECAN)
    SOTA
    CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested ScenesarXiv:1802.10062
  • CrowdsonDLR-ACD
    F1-score· 2019-09-27
    0.24
    best: 0.49 (MRCNet (ours))
    MRCNet: Crowd Counting and Density Map Estimation in Aerial and Ground ImageryarXiv:1909.12743
  • CrowdsonDLR-ACD
    MNAE· 2019-09-27
    0.71
    best: 0.87 (MCNN)
    MRCNet: Crowd Counting and Density Map Estimation in Aerial and Ground ImageryarXiv:1909.12743
  • CrowdsonDLR-ACD
    Precision· 2019-09-27
    0.2
    best: 45 (Liu et al)
    MRCNet: Crowd Counting and Density Map Estimation in Aerial and Ground ImageryarXiv:1909.12743
  • CrowdsonDLR-ACD
    Recall· 2019-09-27
    0.33
    best: 0.52 (ic-CNN)
    MRCNet: Crowd Counting and Density Map Estimation in Aerial and Ground ImageryarXiv:1909.12743