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/PVT (Pyramid Vision Transformer)

PVT (Pyramid Vision Transformer)

Reported on 15 benchmarks across 5 tasks · 1 paper

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

Methodology12 results

  • 3DonPeopleArt
    mAP· 2023-01-12
    46.5
    best: 49.7 (PVT (Pyramid Vision Transformer; trained on PeopleArt and PopArt))
    Poses of People in Art: A Data Set for Human Pose Estimation in Digital Art HistoryarXiv:2301.05124
  • 3DonPeopleArt
    mAP@0.5· 2023-01-12
    76
    best: 80.5 (PVT (Pyramid Vision Transformer; trained on PeopleArt and PopArt))
    Poses of People in Art: A Data Set for Human Pose Estimation in Digital Art HistoryarXiv:2301.05124
  • 3DonPeopleArt
    mAP@0.75· 2023-01-12
    48.4
    best: 51.8 (PVT (Pyramid Vision Transformer; trained on PeopleArt and PopArt))
    Poses of People in Art: A Data Set for Human Pose Estimation in Digital Art HistoryarXiv:2301.05124
  • 2D ClassificationonPeopleArt
    mAP· 2023-01-12
    46.5
    best: 49.7 (PVT (Pyramid Vision Transformer; trained on PeopleArt and PopArt))
    Poses of People in Art: A Data Set for Human Pose Estimation in Digital Art HistoryarXiv:2301.05124
  • 2D ClassificationonPeopleArt
    mAP@0.5· 2023-01-12
    76
    best: 80.5 (PVT (Pyramid Vision Transformer; trained on PeopleArt and PopArt))
    Poses of People in Art: A Data Set for Human Pose Estimation in Digital Art HistoryarXiv:2301.05124
  • 2D ClassificationonPeopleArt
    mAP@0.75· 2023-01-12
    48.4
    best: 51.8 (PVT (Pyramid Vision Transformer; trained on PeopleArt and PopArt))
    Poses of People in Art: A Data Set for Human Pose Estimation in Digital Art HistoryarXiv:2301.05124
  • 2D Object DetectiononPeopleArt
    mAP· 2023-01-12
    46.5
    best: 49.7 (PVT (Pyramid Vision Transformer; trained on PeopleArt and PopArt))
    Poses of People in Art: A Data Set for Human Pose Estimation in Digital Art HistoryarXiv:2301.05124
  • 2D Object DetectiononPeopleArt
    mAP@0.5· 2023-01-12
    76
    best: 80.5 (PVT (Pyramid Vision Transformer; trained on PeopleArt and PopArt))
    Poses of People in Art: A Data Set for Human Pose Estimation in Digital Art HistoryarXiv:2301.05124
  • 2D Object DetectiononPeopleArt
    mAP@0.75· 2023-01-12
    48.4
    best: 51.8 (PVT (Pyramid Vision Transformer; trained on PeopleArt and PopArt))
    Poses of People in Art: A Data Set for Human Pose Estimation in Digital Art HistoryarXiv:2301.05124
  • 16konPeopleArt
    mAP· 2023-01-12
    46.5
    best: 49.7 (PVT (Pyramid Vision Transformer; trained on PeopleArt and PopArt))
    Poses of People in Art: A Data Set for Human Pose Estimation in Digital Art HistoryarXiv:2301.05124
  • 16konPeopleArt
    mAP@0.5· 2023-01-12
    76
    best: 80.5 (PVT (Pyramid Vision Transformer; trained on PeopleArt and PopArt))
    Poses of People in Art: A Data Set for Human Pose Estimation in Digital Art HistoryarXiv:2301.05124
  • 16konPeopleArt
    mAP@0.75· 2023-01-12
    48.4
    best: 51.8 (PVT (Pyramid Vision Transformer; trained on PeopleArt and PopArt))
    Poses of People in Art: A Data Set for Human Pose Estimation in Digital Art HistoryarXiv:2301.05124

Computer Vision3 results

  • Object DetectiononPeopleArt
    mAP· 2023-01-12
    46.5
    best: 49.7 (PVT (Pyramid Vision Transformer; trained on PeopleArt and PopArt))
    Poses of People in Art: A Data Set for Human Pose Estimation in Digital Art HistoryarXiv:2301.05124
  • Object DetectiononPeopleArt
    mAP@0.5· 2023-01-12
    76
    best: 80.5 (PVT (Pyramid Vision Transformer; trained on PeopleArt and PopArt))
    Poses of People in Art: A Data Set for Human Pose Estimation in Digital Art HistoryarXiv:2301.05124
  • Object DetectiononPeopleArt
    mAP@0.75· 2023-01-12
    48.4
    best: 51.8 (PVT (Pyramid Vision Transformer; trained on PeopleArt and PopArt))
    Poses of People in Art: A Data Set for Human Pose Estimation in Digital Art HistoryarXiv:2301.05124