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/STEP

STEP

Reported on 7 benchmarks across 2 tasks · 2 papers · 5 SOTA

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

Time Series7 results

  • Traffic PredictiononPEMS-BAY
    MAE @ 12 step· uses extra data· 2022-06-18
    1.79
    best: 1.63 (T-Graphormer)
    SOTA
    Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series ForecastingarXiv:2206.09113
  • Traffic PredictiononPEMS-BAY
    RMSE · uses extra data· 2022-06-18
    4.2
    best: 3.2 (T-Graphormer)
    SOTA
    Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series ForecastingarXiv:2206.09113
  • Traffic PredictiononMETR-LA
    MAE @ 12 step· 2022-06-18
    3.37
    best: 3.08 (TITAN)
    SOTA
    Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series ForecastingarXiv:2206.09113
  • Traffic PredictiononMETR-LA
    MAE @ 3 step· 2022-06-18
    2.61
    best: 2.41 (TITAN)
    SOTA
    Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series ForecastingarXiv:2206.09113
  • Action DetectiononUCF101-24
    Video-mAP 0.1· 2019-04-19
    83.1
    best: 86.1 (YOWO + LFB)
    SOTA
    STEP: Spatio-Temporal Progressive Learning for Video Action DetectionarXiv:1904.09288
  • Action DetectiononUCF101-24
    Frame-mAP 0.5· 2019-04-19
    75
    best: 90.3 (STAR/L)
    STEP: Spatio-Temporal Progressive Learning for Video Action DetectionarXiv:1904.09288
  • Action DetectiononUCF101-24
    Video-mAP 0.2· 2019-04-19
    76.6
    best: 88.8 (HIT)
    STEP: Spatio-Temporal Progressive Learning for Video Action DetectionarXiv:1904.09288