[
  {
    "Val": 96.7,
    "code_links": [
      {
        "title": "xingyul/cpnet",
        "url": "https://github.com/xingyul/cpnet"
      },
      {
        "title": "xingyul/meteornet",
        "url": "https://github.com/xingyul/meteornet"
      }
    ],
    "date": "2019-05-20",
    "date2": 20190520,
    "model": "CPNet Res34, 5 CP",
    "paper": {
      "title": "Learning Video Representations from Correspondence Proposals",
      "url": "https://cknow.io/lib/9e742789227dfb82"
    },
    "paper_data_uoa": "9e742789227dfb82"
  },
  {
    "Val": 96.7,
    "code_links": [],
    "date": "2019-08-07",
    "date2": 20190807,
    "model": "STM (Resnet-50, 16 frames)",
    "paper": {
      "title": "STM: SpatioTemporal and Motion Encoding for Action Recognition",
      "url": "https://cknow.io/lib/dbf65072610598a3"
    },
    "paper_data_uoa": "dbf65072610598a3"
  },
  {
    "Val": 95.31,
    "code_links": [
      {
        "title": "metalbubble/TRN-pytorch",
        "url": "https://github.com/metalbubble/TRN-pytorch"
      },
      {
        "title": "okankop/MFF-pytorch",
        "url": "https://github.com/okankop/MFF-pytorch"
      }
    ],
    "date": "2017-11-22",
    "date2": 20171122,
    "model": "MultiScale TRN",
    "paper": {
      "title": "Temporal Relational Reasoning in Videos",
      "url": "https://cknow.io/lib/ab89498599fa31b3"
    },
    "paper_data_uoa": "ab89498599fa31b3"
  },
  {
    "Val": 92.7,
    "code_links": [
      {
        "title": "0zgur0/STAR_Network",
        "url": "https://github.com/0zgur0/STAR_Network"
      }
    ],
    "date": "2019-11-25",
    "date2": 20191125,
    "model": "convSTAR",
    "paper": {
      "title": "Gating Revisited: Deep Multi-layer RNNs That Can Be Trained",
      "url": "https://cknow.io/lib/d1732546142d440f"
    },
    "paper_data_uoa": "d1732546142d440f"
  },
  {
    "Val": 90.77,
    "code_links": [
      {
        "title": "okankop/Efficient-3DCNNs",
        "url": "https://github.com/okankop/Efficient-3DCNNs"
      }
    ],
    "date": "2019-04-04",
    "date2": 20190404,
    "model": "3D-SqueezeNet",
    "paper": {
      "title": "Resource Efficient 3D Convolutional Neural Networks",
      "url": "https://cknow.io/lib/c741b4dba4a608e4"
    },
    "paper_data_uoa": "c741b4dba4a608e4"
  },
  {
    "Val": 86.91,
    "code_links": [
      {
        "title": "okankop/Efficient-3DCNNs",
        "url": "https://github.com/okankop/Efficient-3DCNNs"
      }
    ],
    "date": "2019-04-04",
    "date2": 20190404,
    "model": "3D-ShuffleNetV2 0.25x",
    "paper": {
      "title": "Resource Efficient 3D Convolutional Neural Networks",
      "url": "https://cknow.io/lib/c741b4dba4a608e4"
    },
    "paper_data_uoa": "c741b4dba4a608e4"
  },
  {
    "Val": 86.43,
    "code_links": [
      {
        "title": "okankop/Efficient-3DCNNs",
        "url": "https://github.com/okankop/Efficient-3DCNNs"
      }
    ],
    "date": "2019-04-04",
    "date2": 20190404,
    "model": "3D-MobileNetV2 0.2x",
    "paper": {
      "title": "Resource Efficient 3D Convolutional Neural Networks",
      "url": "https://cknow.io/lib/c741b4dba4a608e4"
    },
    "paper_data_uoa": "c741b4dba4a608e4"
  }
]