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/STAR-Net

STAR-Net

Reported on 18 benchmarks across 11 tasks · 1 paper

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

Computer Vision9 results

  • VideoonJ-HMDB
    Accuracy (RGB+pose)· 2019-02-26
    64.3
    best: 90.4 (Potion)
    STAR-Net: Action Recognition using Spatio-Temporal Activation ReprojectionarXiv:1902.10024
  • Temporal Action LocalizationonJ-HMDB
    Accuracy (RGB+pose)· 2019-02-26
    64.3
    best: 90.4 (Potion)
    STAR-Net: Action Recognition using Spatio-Temporal Activation ReprojectionarXiv:1902.10024
  • Action LocalizationonJ-HMDB
    Accuracy (RGB+pose)· 2019-02-26
    64.3
    best: 90.4 (Potion)
    STAR-Net: Action Recognition using Spatio-Temporal Activation ReprojectionarXiv:1902.10024
  • Scene ParsingonSVT
    Accuracy
    83.6
    best: 99.1 (CLIP4STR-H (DFN-5B))
  • Scene ParsingonICDAR 2003
    Accuracy
    89.9
    best: 97.1 (Yet Another Text Recognizer)
  • Scene ParsingonICDAR2013
    Accuracy
    89.1
    best: 99.42 (CLIP4STR-L*)
  • Scene Text RecognitiononSVT
    Accuracy
    83.6
    best: 99.1 (CLIP4STR-H (DFN-5B))
  • Scene Text RecognitiononICDAR 2003
    Accuracy
    89.9
    best: 97.1 (Yet Another Text Recognizer)
  • Scene Text RecognitiononICDAR2013
    Accuracy
    89.1
    best: 99.42 (CLIP4STR-L*)

Audio3 results

  • 2D Semantic SegmentationonSVT
    Accuracy
    83.6
    best: 99.1 (CLIP4STR-H (DFN-5B))
  • 2D Semantic SegmentationonICDAR 2003
    Accuracy
    89.9
    best: 97.1 (Yet Another Text Recognizer)
  • 2D Semantic SegmentationonICDAR2013
    Accuracy
    89.1
    best: 99.42 (CLIP4STR-L*)

Robots2 results

  • Activity RecognitiononJ-HMDB
    Accuracy (RGB+pose)· 2019-02-26
    64.3
    best: 90.4 (Potion)
    STAR-Net: Action Recognition using Spatio-Temporal Activation ReprojectionarXiv:1902.10024
  • Activity RecognitiononUTD-MHAD
    Accuracy (CS)· 2019-02-26
    90
    best: 94.5 (PoseMap)
    STAR-Net: Action Recognition using Spatio-Temporal Activation ReprojectionarXiv:1902.10024

Time Series2 results

  • Action DetectiononJ-HMDB
    Accuracy (RGB+pose)· 2019-02-26
    64.3
    best: 90.4 (Potion)
    STAR-Net: Action Recognition using Spatio-Temporal Activation ReprojectionarXiv:1902.10024
  • Action RecognitiononJ-HMDB
    Accuracy (RGB+pose)· 2019-02-26
    64.3
    best: 90.4 (Potion)
    STAR-Net: Action Recognition using Spatio-Temporal Activation ReprojectionarXiv:1902.10024

Methodology1 result

  • Zero-Shot LearningonJ-HMDB
    Accuracy (RGB+pose)· 2019-02-26
    64.3
    best: 90.4 (Potion)
    STAR-Net: Action Recognition using Spatio-Temporal Activation ReprojectionarXiv:1902.10024

Natural Language Processing1 result

  • 3D Action RecognitiononJ-HMDB
    Accuracy (RGB+pose)· 2019-02-26
    64.3
    best: 90.4 (Potion)
    STAR-Net: Action Recognition using Spatio-Temporal Activation ReprojectionarXiv:1902.10024