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/DIN

DIN

Reported on 8 benchmarks across 4 tasks · 2 papers

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

Robots2 results

  • Activity RecognitiononJester (Gesture Recognition)
    Val· 2018-05-19
    95.31
    best: 98.15 (DirecFormer)
    DenseImage Network: Video Spatial-Temporal Evolution Encoding and UnderstandingarXiv:1805.07550
  • Activity RecognitiononSomething-Something V2
    Top-1 Accuracy· 2018-05-19
    34.11
    best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
    DenseImage Network: Video Spatial-Temporal Evolution Encoding and UnderstandingarXiv:1805.07550

Time Series2 results

  • Action RecognitiononJester (Gesture Recognition)
    Val· 2018-05-19
    95.31
    best: 98.15 (DirecFormer)
    DenseImage Network: Video Spatial-Temporal Evolution Encoding and UnderstandingarXiv:1805.07550
  • Action RecognitiononSomething-Something V2
    Top-1 Accuracy· 2018-05-19
    34.11
    best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
    DenseImage Network: Video Spatial-Temporal Evolution Encoding and UnderstandingarXiv:1805.07550

Computer Vision2 results

  • Action Recognition In VideosonJester (Gesture Recognition)
    Val· 2018-05-19
    95.31
    best: 96.7 (CPNet Res34, 5 CP)
    DenseImage Network: Video Spatial-Temporal Evolution Encoding and UnderstandingarXiv:1805.07550
  • Action Recognition In VideosonSomething-Something V2
    Top-1 Accuracy· 2018-05-19
    34.11
    best: 64.2 (STM (16 frames, ImageNet pretraining))
    DenseImage Network: Video Spatial-Temporal Evolution Encoding and UnderstandingarXiv:1805.07550

Miscellaneous2 results

  • Click-Through Rate PredictiononMovieLens 20M
    AUC· 2017-06-21
    0.7337
    best: 0.79 (github.com/guotong1988/movielens_dataset)
    Deep Interest Network for Click-Through Rate PredictionarXiv:1706.06978
  • Click-Through Rate PredictiononAmazon
    AUC· 2017-06-21
    0.8818
    best: 0.8871 (DIN + Dice Activation)
    Deep Interest Network for Click-Through Rate PredictionarXiv:1706.06978