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/MR Two-Sream R-CNN

MR Two-Sream R-CNN

Reported on 10 benchmarks across 8 tasks

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

Computer Vision3 results

  • VideoonJ-HMDB
    Accuracy (RGB+pose)
    71.1
    best: 90.4 (Potion)
  • Temporal Action LocalizationonJ-HMDB
    Accuracy (RGB+pose)
    71.1
    best: 90.4 (Potion)
  • Action LocalizationonJ-HMDB
    Accuracy (RGB+pose)
    71.1
    best: 90.4 (Potion)

Time Series3 results

  • Action DetectiononJ-HMDB
    Accuracy (RGB+pose)
    71.1
    best: 90.4 (Potion)
  • Action RecognitiononUCF101
    3-fold Accuracy
    91.1
    best: 99.7 (FTP-UniFormerV2-L/14)
  • Action RecognitiononJ-HMDB
    Accuracy (RGB+pose)
    71.1
    best: 90.4 (Potion)

Robots2 results

  • Activity RecognitiononUCF101
    3-fold Accuracy
    91.1
    best: 99.7 (FTP-UniFormerV2-L/14)
  • Activity RecognitiononJ-HMDB
    Accuracy (RGB+pose)
    71.1
    best: 90.4 (Potion)

Methodology1 result

  • Zero-Shot LearningonJ-HMDB
    Accuracy (RGB+pose)
    71.1
    best: 90.4 (Potion)

Natural Language Processing1 result

  • 3D Action RecognitiononJ-HMDB
    Accuracy (RGB+pose)
    71.1
    best: 90.4 (Potion)