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/CVPR22

CVPR22

Reported on 11 benchmarks across 2 tasks

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

Computer Vision6 results

  • Object LocalizationonREVERIE
    Nav-Length
    21.3
    best: 48.61 (SIA)
  • Object LocalizationonREVERIE
    Nav-OSucc
    56.91
    best: 57.12 (OSMaN)
  • Object LocalizationonREVERIE
    Nav-SPL
    36.06
    best: 47.78 (OSMaN)
  • Object LocalizationonREVERIE
    Nav-Succ
    52.51
    best: 54.39 (SUSA)
  • Object LocalizationonREVERIE
    RGS
    31.88
    best: 36.11 (SUSA)
  • Object LocalizationonREVERIE
    RGSPL
    22.06
    best: 32.99 (OSMaN)

Robots5 results

  • Vision and Language NavigationonVLN Challenge
    error
    3.65
    best: 1.61 (human)
  • Vision and Language NavigationonVLN Challenge
    length
    14.73
    best: 1257.38 (Speaker-Follower)
  • Vision and Language NavigationonVLN Challenge
    oracle success
    0.76
    best: 1 (FOAM-Beam Search)
  • Vision and Language NavigationonVLN Challenge
    spl
    0.59
    best: 0.76 (human)
  • Vision and Language NavigationonVLN Challenge
    success
    0.69
    best: 0.86 (human)