[
  {
    "Average accuracy of 3 splits": 82.48,
    "code_links": [],
    "date": "2019-06-13",
    "date2": 20190613,
    "model": "HAF+BoW/FV halluc",
    "paper": {
      "title": "Hallucinating IDT Descriptors and I3D Optical Flow Features for Action Recognition with CNNs",
      "url": "https://cknow.io/lib/45901c51dd6467aa"
    },
    "paper_data_uoa": "45901c51dd6467aa"
  },
  {
    "Average accuracy of 3 splits": 82.1,
    "code_links": [
      {
        "title": "piergiaj/evanet-iccv19",
        "url": "https://github.com/piergiaj/evanet-iccv19"
      }
    ],
    "date": "2018-11-26",
    "date2": 20181126,
    "model": "EvaNet",
    "paper": {
      "title": "Evolving Space-Time Neural Architectures for Videos",
      "url": "https://cknow.io/lib/a44e4af3371c9b83"
    },
    "paper_data_uoa": "a44e4af3371c9b83"
  },
  {
    "Average accuracy of 3 splits": 81.9,
    "code_links": [],
    "date": "2019-08-27",
    "date2": 20190827,
    "model": "CCS + TSN (ImageNet+Kinetics pretrained)",
    "paper": {
      "title": "Cooperative Cross-Stream Network for Discriminative Action Representation",
      "url": "https://cknow.io/lib/09a74f888e9817da"
    },
    "paper_data_uoa": "09a74f888e9817da"
  },
  {
    "Average accuracy of 3 splits": 81.1,
    "code_links": [
      {
        "title": "piergiaj/representation-flow-cvpr19",
        "url": "https://github.com/piergiaj/representation-flow-cvpr19"
      }
    ],
    "date": "2018-10-02",
    "date2": 20181002,
    "model": "RepFlow-50",
    "paper": {
      "title": "Representation Flow for Action Recognition",
      "url": "https://cknow.io/lib/5354d908b72741e5"
    },
    "paper_data_uoa": "5354d908b72741e5"
  },
  {
    "Average accuracy of 3 splits": 80.92,
    "code_links": [],
    "date": "2019-03-20",
    "date2": 20190320,
    "model": "Multi-stream I3D ",
    "paper": {
      "title": "Contextual Action Cues from Camera Sensor for Multi-Stream Action Recognition",
      "url": "https://cknow.io/lib/e85e30290a1982be"
    },
    "paper_data_uoa": "e85e30290a1982be"
  },
  {
    "Average accuracy of 3 splits": 80.9,
    "code_links": [
      {
        "title": "craston/MARS",
        "url": "https://github.com/craston/MARS"
      }
    ],
    "date": "2019-06-01",
    "date2": 20190601,
    "model": "MARS+RGB+FLow (64 frames, Kinetics pretrained)",
    "paper": {
      "title": "MARS: Motion-Augmented RGB Stream for Action Recognition",
      "url": "https://cknow.io/lib/e917d94a27b04d45"
    },
    "paper_data_uoa": "e917d94a27b04d45"
  },
  {
    "Average accuracy of 3 splits": 78.7,
    "code_links": [
      {
        "title": "bryanyzhu/two-stream-pytorch",
        "url": "https://github.com/bryanyzhu/two-stream-pytorch"
      },
      {
        "title": "bryanyzhu/Hidden-Two-Stream",
        "url": "https://github.com/bryanyzhu/Hidden-Two-Stream"
      },
      {
        "title": "AbdalaDiasse/Video-classification-for-oil-quality-estimation",
        "url": "https://github.com/AbdalaDiasse/Video-classification-for-oil-quality-estimation"
      }
    ],
    "date": "2017-04-02",
    "date2": 20170402,
    "model": "Hidden Two-Stream",
    "paper": {
      "title": "Hidden Two-Stream Convolutional Networks for Action Recognition",
      "url": "https://cknow.io/lib/1b3bdadb4a42b57d"
    },
    "paper_data_uoa": "1b3bdadb4a42b57d"
  },
  {
    "Average accuracy of 3 splits": 76.2,
    "code_links": [
      {
        "title": "holistic-video-understanding/Mini-HVU",
        "url": "https://github.com/holistic-video-understanding/Mini-HVU"
      },
      {
        "title": "holistic-video-understanding/HVU-Dataset",
        "url": "https://github.com/holistic-video-understanding/HVU-Dataset"
      }
    ],
    "date": "2019-04-25",
    "date2": 20190425,
    "model": "HATNet (32 frames, HVU pretrained)",
    "paper": {
      "title": "Large Scale Holistic Video Understanding",
      "url": "https://cknow.io/lib/5b16b09584bdea1a"
    },
    "paper_data_uoa": "5b16b09584bdea1a"
  },
  {
    "Average accuracy of 3 splits": 75.7,
    "code_links": [],
    "date": "2019-06-10",
    "date2": 20190610,
    "model": "FASTER32 (Kinetics pretrain)",
    "paper": {
      "title": "FASTER Recurrent Networks for Efficient Video Classification",
      "url": "https://cknow.io/lib/474ff5967144a33a"
    },
    "paper_data_uoa": "474ff5967144a33a"
  },
  {
    "Average accuracy of 3 splits": 74.3,
    "code_links": [],
    "date": "2018-07-24",
    "date2": 20180724,
    "model": "ADL+ResNet+IDT",
    "paper": {
      "title": "Contrastive Video Representation Learning via Adversarial Perturbations",
      "url": "https://cknow.io/lib/1e9f286c44f46a11"
    },
    "paper_data_uoa": "1e9f286c44f46a11"
  },
  {
    "Average accuracy of 3 splits": 72.2,
    "code_links": [
      {
        "title": "feichtenhofer/st-resnet",
        "url": "https://github.com/feichtenhofer/st-resnet"
      }
    ],
    "date": "2017-07-01",
    "date2": 20170701,
    "model": "STM Network+IDT",
    "paper": {
      "title": "Spatiotemporal Multiplier Networks for Video Action Recognition",
      "url": "https://cknow.io/lib/002d244a408c4574"
    },
    "paper_data_uoa": "002d244a408c4574"
  },
  {
    "Average accuracy of 3 splits": 72.2,
    "code_links": [],
    "date": "2019-08-07",
    "date2": 20190807,
    "model": "STM (ImageNet+Kinetics pretrain)",
    "paper": {
      "title": "STM: SpatioTemporal and Motion Encoding for Action Recognition",
      "url": "https://cknow.io/lib/dbf65072610598a3"
    },
    "paper_data_uoa": "dbf65072610598a3"
  },
  {
    "Average accuracy of 3 splits": 72,
    "code_links": [],
    "date": "2019-04-05",
    "date2": 20190405,
    "model": "Prob-Distill",
    "paper": {
      "title": "Paying More Attention to Motion: Attention Distillation for Learning Video Representations",
      "url": "https://cknow.io/lib/b222433297a9a5c3"
    },
    "paper_data_uoa": "b222433297a9a5c3"
  },
  {
    "Average accuracy of 3 splits": 71.13,
    "code_links": [],
    "date": "2019-05-29",
    "date2": 20190529,
    "model": "HF-ECOLite (ImageNet+Kinetics pretrain)",
    "paper": {
      "title": "Hierarchical Feature Aggregation Networks for Video Action Recognition",
      "url": "https://cknow.io/lib/dd1247b8980e18a8"
    },
    "paper_data_uoa": "dd1247b8980e18a8"
  },
  {
    "Average accuracy of 3 splits": 62.8,
    "code_links": [],
    "date": "2019-06-19",
    "date2": 20190619,
    "model": "R-STAN-50",
    "paper": {
      "title": "R-STAN: Residual Spatial-Temporal Attention Network for Action Recognition",
      "url": "https://cknow.io/lib/1c94b929dfcdb35e"
    },
    "paper_data_uoa": "1c94b929dfcdb35e"
  },
  {
    "Average accuracy of 3 splits": 62.7,
    "code_links": [],
    "date": "2018-12-03",
    "date2": 20181203,
    "model": "SUSiNet (multi, Kinetics pretrained)",
    "paper": {
      "title": "SUSiNet: See, Understand and Summarize it",
      "url": "https://cknow.io/lib/2c70a2a80d451699"
    },
    "paper_data_uoa": "2c70a2a80d451699"
  },
  {
    "Average accuracy of 3 splits": 55.16,
    "code_links": [],
    "date": "2019-06-19",
    "date2": 20190619,
    "model": "R-STAN-152",
    "paper": {
      "title": "R-STAN: Residual Spatial-Temporal Attention Network for Action Recognition",
      "url": "https://cknow.io/lib/1c94b929dfcdb35e"
    },
    "paper_data_uoa": "1c94b929dfcdb35e"
  },
  {
    "Average accuracy of 3 splits": 54.8,
    "code_links": [],
    "date": "2019-01-26",
    "date2": 20190126,
    "model": "R(2+1)D-18 (DistInit pretraining)",
    "paper": {
      "title": "DistInit: Learning Video Representations Without a Single Labeled Video",
      "url": "https://cknow.io/lib/a410b42da91f2d04"
    },
    "paper_data_uoa": "a410b42da91f2d04"
  },
  {
    "Average accuracy of 3 splits": 51.8,
    "code_links": [],
    "date": "2018-03-22",
    "date2": 20180322,
    "model": "CD-UAR",
    "paper": {
      "title": "Towards Universal Representation for Unseen Action Recognition",
      "url": "https://cknow.io/lib/9c5347f4953a03dc"
    },
    "paper_data_uoa": "9c5347f4953a03dc"
  },
  {
    "Average accuracy of 3 splits": 33.4,
    "code_links": [
      {
        "title": "laura-wang/video_repres_mas",
        "url": "https://github.com/laura-wang/video_repres_mas"
      }
    ],
    "date": "2019-04-07",
    "date2": 20190407,
    "model": "Pretrained on Kinetics",
    "paper": {
      "title": "Self-supervised Spatio-temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics",
      "url": "https://cknow.io/lib/510450184304f519"
    },
    "paper_data_uoa": "510450184304f519"
  }
]