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/YOWO

YOWO

Reported on 7 benchmarks across 1 task · 1 paper

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

Time Series7 results

  • Action DetectiononUCF101-24
    Frame-mAP 0.5· 2019-11-15
    80.4
    best: 90.3 (STAR/L)
    You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action LocalizationarXiv:1911.06644
  • Action DetectiononUCF101-24
    Video-mAP 0.1· 2019-11-15
    82.5
    best: 86.1 (YOWO + LFB)
    You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action LocalizationarXiv:1911.06644
  • Action DetectiononUCF101-24
    Video-mAP 0.2· 2019-11-15
    75.8
    best: 88.8 (HIT)
    You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action LocalizationarXiv:1911.06644
  • Action DetectiononUCF101-24
    Video-mAP 0.5· 2019-11-15
    48.8
    best: 76.3 (Stable Mean Teacher (I3D))
    You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action LocalizationarXiv:1911.06644
  • Action DetectiononJ-HMDB
    Frame-mAP 0.5· 2019-11-15
    74.4
    best: 88.5 (SiA)
    You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action LocalizationarXiv:1911.06644
  • Action DetectiononJ-HMDB
    Video-mAP 0.2· 2019-11-15
    87.8
    best: 89.7 (HIT)
    You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action LocalizationarXiv:1911.06644
  • Action DetectiononJ-HMDB
    Video-mAP 0.5· 2019-11-15
    85.7
    best: 88.1 (HIT)
    You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action LocalizationarXiv:1911.06644