[
  {
    "Accuracy": 74.9,
    "code_links": [],
    "date": "2019-04-08",
    "date2": 20190408,
    "model": "IF+MD+RGB-R (ResNet-18)",
    "paper": {
      "title": "SCSampler: Sampling Salient Clips from Video for Efficient Action Recognition",
      "url": "https://cknow.io/lib/2f8c1969584c63ad"
    },
    "paper_data_uoa": "2f8c1969584c63ad"
  },
  {
    "Accuracy": 69.9,
    "code_links": [],
    "date": "2019-04-08",
    "date2": 20190408,
    "model": "IF+MD+RGB-R (ShuffleNet-26 )",
    "paper": {
      "title": "SCSampler: Sampling Salient Clips from Video for Efficient Action Recognition",
      "url": "https://cknow.io/lib/2f8c1969584c63ad"
    },
    "paper_data_uoa": "2f8c1969584c63ad"
  },
  {
    "Clip Hit@1": 49.7,
    "Video hit@1": 62.8,
    "Video hit@5": 85.5,
    "code_links": [],
    "date": "2019-05-29",
    "date2": 20190529,
    "model": "G-Blend",
    "paper": {
      "title": "What Makes Training Multi-Modal Classification Networks Hard?",
      "url": "https://cknow.io/lib/13f9697ace9f430d"
    },
    "paper_data_uoa": "13f9697ace9f430d"
  }
]