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/ORViT Mformer-L (ORViT blocks)

ORViT Mformer-L (ORViT blocks)

Reported on 10 benchmarks across 2 tasks · 1 paper · 2 SOTA

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

Robots5 results

  • Activity RecognitiononEPIC-KITCHENS-100
    Noun@1· 2021-10-13
    58.7
    best: 69 (LLaVAction)
    SOTA
    Object-Region Video TransformersarXiv:2110.06915
  • Activity RecognitiononEPIC-KITCHENS-100
    Action@1· 2021-10-13
    45.7
    best: 58.3 (LLaVAction)
    Object-Region Video TransformersarXiv:2110.06915
  • Activity RecognitiononEPIC-KITCHENS-100
    Verb@1· 2021-10-13
    68.4
    best: 76.2 (TIM)
    Object-Region Video TransformersarXiv:2110.06915
  • Activity RecognitiononSomething-Something V2
    Top-1 Accuracy· uses extra data· 2021-10-13
    69.5
    best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
    Object-Region Video TransformersarXiv:2110.06915
  • Activity RecognitiononSomething-Something V2
    Top-5 Accuracy· uses extra data· 2021-10-13
    91.5
    best: 96.3 (DejaVid)
    Object-Region Video TransformersarXiv:2110.06915

Time Series5 results

  • Action RecognitiononEPIC-KITCHENS-100
    Noun@1· 2021-10-13
    58.7
    best: 69 (LLaVAction)
    SOTA
    Object-Region Video TransformersarXiv:2110.06915
  • Action RecognitiononEPIC-KITCHENS-100
    Action@1· 2021-10-13
    45.7
    best: 58.3 (LLaVAction)
    Object-Region Video TransformersarXiv:2110.06915
  • Action RecognitiononEPIC-KITCHENS-100
    Verb@1· 2021-10-13
    68.4
    best: 76.2 (TIM)
    Object-Region Video TransformersarXiv:2110.06915
  • Action RecognitiononSomething-Something V2
    Top-1 Accuracy· uses extra data· 2021-10-13
    69.5
    best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
    Object-Region Video TransformersarXiv:2110.06915
  • Action RecognitiononSomething-Something V2
    Top-5 Accuracy· uses extra data· 2021-10-13
    91.5
    best: 96.3 (DejaVid)
    Object-Region Video TransformersarXiv:2110.06915