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/CLIP-EBC (ResNet50)

CLIP-EBC (ResNet50)

Reported on 8 benchmarks across 1 task · 1 paper · 6 SOTA

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

Computer Vision8 results

  • CrowdsonShanghaiTech B
    RMSE· uses extra data· 2024-03-14
    10.1
    best: 8.63 (EBC-ZIP-B)
    SOTA
    CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise ClassificationarXiv:2403.09281
  • CrowdsonNWPU-Crowd (Val)
    MAE· 2024-03-14
    38.6
    best: 28.26 (EBC-ZIP-B)
    SOTA
    CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise ClassificationarXiv:2403.09281
  • CrowdsonNWPU-Crowd (Val)
    RMSE· 2024-03-14
    90.3
    best: 64.84 (EBC-ZIP-B)
    SOTA
    CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise ClassificationarXiv:2403.09281
  • CrowdsonUCF-QNRF
    MAE· 2024-03-14
    80.5
    best: 69.46 (EBC-ZIP-B)
    SOTA
    CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise ClassificationarXiv:2403.09281
  • CrowdsonUCF-QNRF
    RMSE· 2024-03-14
    136.6
    best: 121.88 (EBC-ZIP-B)
    SOTA
    CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise ClassificationarXiv:2403.09281
  • CrowdsonShanghaiTech A
    RMSE· 2024-03-14
    83.2
    best: 75.04 (EBC-ZIP-B)
    SOTA
    CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise ClassificationarXiv:2403.09281
  • CrowdsonShanghaiTech B
    MAE· uses extra data· 2024-03-14
    6
    best: 5.51 (EBC-ZIP-B)
    CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise ClassificationarXiv:2403.09281
  • CrowdsonShanghaiTech A
    MAE· 2024-03-14
    54
    best: 47.81 (EBC-ZIP-B)
    CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise ClassificationarXiv:2403.09281