[
  {
    "mAP@0.3": 53.9,
    "mAP@0.4": 46.8,
    "mAP@0.5": 37.4,
    "code_links": [],
    "date": "2018-11-28",
    "date2": 20181128,
    "model": "MGG UNet",
    "paper": {
      "title": "Multi-granularity Generator for Temporal Action Proposal",
      "url": "https://cknow.io/lib/df1a942bf582fc83"
    },
    "paper_data_uoa": "df1a942bf582fc83"
  },
  {
    "mAP@0.3": 53.5,
    "mAP@0.4": 45,
    "mAP@0.5": 36.9,
    "code_links": [
      {
        "title": "PaddlePaddle/models",
        "url": "https://github.com/PaddlePaddle/models/tree/develop/PaddleCV/video/models/bsn"
      },
      {
        "title": "wzmsltw/BSN-boundary-sensitive-network",
        "url": "https://github.com/wzmsltw/BSN-boundary-sensitive-network"
      },
      {
        "title": "wzmsltw/BSN-boundary-sensitive-network.pytorch",
        "url": "https://github.com/wzmsltw/BSN-boundary-sensitive-network.pytorch"
      },
      {
        "title": "Frostinassiky/gtad",
        "url": "https://github.com/Frostinassiky/gtad"
      },
      {
        "title": "hyperfraise/end-to-end-BSN.pytorch",
        "url": "https://github.com/hyperfraise/end-to-end-BSN.pytorch"
      },
      {
        "title": "zzy123abc/BSN-boundary-sensitive-network-master",
        "url": "https://github.com/zzy123abc/BSN-boundary-sensitive-network-master"
      },
      {
        "title": "Ontheway361/BSN_pytorch",
        "url": "https://github.com/Ontheway361/BSN_pytorch"
      },
      {
        "title": "ZhangNYG/BSN",
        "url": "https://github.com/ZhangNYG/BSN"
      },
      {
        "title": "guilk/diva",
        "url": "https://github.com/guilk/diva"
      },
      {
        "title": "7m7m7m/BSN",
        "url": "https://github.com/7m7m7m/BSN"
      },
      {
        "title": "Andrew-booler/BSN-ActivityNet",
        "url": "https://github.com/Andrew-booler/BSN-ActivityNet"
      }
    ],
    "date": "2018-06-08",
    "date2": 20180608,
    "model": "BSN",
    "paper": {
      "title": "BSN: Boundary Sensitive Network for Temporal Action Proposal Generation",
      "url": "https://cknow.io/lib/28ce857331f263ba"
    },
    "paper_data_uoa": "28ce857331f263ba"
  },
  {
    "mAP@0.1": 56.9,
    "mAP@0.2": 54.7,
    "mAP@0.3": 51.2,
    "mAP@0.4": 43,
    "mAP@0.5": 36.1,
    "code_links": [],
    "date": "2019-06-05",
    "date2": 20190605,
    "model": "Two-stream R-C3D (Sum) + OHEM",
    "paper": {
      "title": "Two-Stream Region Convolutional 3D Network for Temporal Activity Detection",
      "url": "https://cknow.io/lib/ce1e31502f4410ab"
    },
    "paper_data_uoa": "ce1e31502f4410ab"
  },
  {
    "mAP@0.1": 57.4,
    "mAP@0.2": 54.9,
    "mAP@0.3": 51.1,
    "mAP@0.4": 43.1,
    "mAP@0.5": 35.8,
    "code_links": [],
    "date": "2019-06-05",
    "date2": 20190605,
    "model": "Single-stream R-C3D + OHEM",
    "paper": {
      "title": "Two-Stream Region Convolutional 3D Network for Temporal Activity Detection",
      "url": "https://cknow.io/lib/ce1e31502f4410ab"
    },
    "paper_data_uoa": "ce1e31502f4410ab"
  },
  {
    "mAP@0.1": 66,
    "mAP@0.2": 59.4,
    "mAP@0.3": 51.9,
    "mAP@0.4": 41,
    "mAP@0.5": 29.8,
    "code_links": [
      {
        "title": "open-mmlab/mmaction",
        "url": "https://github.com/open-mmlab/mmaction"
      },
      {
        "title": "yjxiong/action-detection",
        "url": "https://github.com/yjxiong/action-detection"
      },
      {
        "title": "happygds/two_level",
        "url": "https://github.com/happygds/two_level"
      },
      {
        "title": "blueskyM01/TF_AD",
        "url": "https://github.com/blueskyM01/TF_AD"
      }
    ],
    "date": "2017-04-20",
    "date2": 20170420,
    "model": "SSN",
    "paper": {
      "title": "Temporal Action Detection with Structured Segment Networks",
      "url": "https://cknow.io/lib/8f4e86bc5d567487"
    },
    "paper_data_uoa": "8f4e86bc5d567487"
  },
  {
    "mAP@0.1": 54.5,
    "mAP@0.2": 51.5,
    "mAP@0.3": 44.8,
    "mAP@0.4": 35.6,
    "mAP@0.5": 28.9,
    "code_links": [],
    "date": "2017-03-22",
    "date2": 20170322,
    "model": "Single-stream R-C3D  (two-way buffer)",
    "paper": {
      "title": "R-C3D: Region Convolutional 3D Network for Temporal Activity Detection",
      "url": "https://cknow.io/lib/0e0f054d56b1b2ee"
    },
    "paper_data_uoa": "0e0f054d56b1b2ee"
  },
  {
    "mAP@0.1": 51.6,
    "mAP@0.2": 49.2,
    "mAP@0.3": 42.8,
    "mAP@0.4": 33.4,
    "mAP@0.5": 27,
    "code_links": [],
    "date": "2017-03-22",
    "date2": 20170322,
    "model": "Single-stream R-C3D  (one-way buffer)",
    "paper": {
      "title": "R-C3D: Region Convolutional 3D Network for Temporal Activity Detection",
      "url": "https://cknow.io/lib/0e0f054d56b1b2ee"
    },
    "paper_data_uoa": "0e0f054d56b1b2ee"
  },
  {
    "mAP@0.4": 33.3,
    "mAP@0.5": 25.6,
    "code_links": [],
    "date": "2017-08-08",
    "date2": 20170808,
    "model": "Dai et. al.",
    "paper": {
      "title": "Temporal Context Network for Activity Localization in Videos",
      "url": "https://cknow.io/lib/2bebf33d64e3fa6c"
    },
    "paper_data_uoa": "2bebf33d64e3fa6c"
  },
  {
    "mAP@0.3": 46.3,
    "mAP@0.4": 35.3,
    "mAP@0.5": 24.5,
    "code_links": [
      {
        "title": "jiyanggao/TURN-TAP",
        "url": "https://github.com/jiyanggao/TURN-TAP"
      }
    ],
    "date": "2017-03-17",
    "date2": 20170317,
    "model": "TURN",
    "paper": {
      "title": "TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals",
      "url": "https://cknow.io/lib/f56b838370a06c11"
    },
    "paper_data_uoa": "f56b838370a06c11"
  },
  {
    "mAP@0.1": 47.7,
    "mAP@0.2": 43.5,
    "mAP@0.3": 36.3,
    "mAP@0.4": 28.7,
    "mAP@0.5": 19,
    "code_links": [
      {
        "title": "zhengshou/scnn",
        "url": "https://github.com/zhengshou/scnn"
      }
    ],
    "date": "2016-01-09",
    "date2": 20160109,
    "model": "Shou et. al.",
    "paper": {
      "title": "Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs",
      "url": "https://cknow.io/lib/0e774fa0a74c1d1f"
    },
    "paper_data_uoa": "0e774fa0a74c1d1f"
  },
  {
    "mAP@0.1": 48.9,
    "mAP@0.2": 44,
    "mAP@0.3": 36,
    "mAP@0.4": 26.4,
    "mAP@0.5": 17.1,
    "code_links": [],
    "date": "2015-11-22",
    "date2": 20151122,
    "model": "Yeung et. al.",
    "paper": {
      "title": "End-to-end Learning of Action Detection from Frame Glimpses in Videos",
      "url": "https://cknow.io/lib/a6ddd46ce879fb16"
    },
    "paper_data_uoa": "a6ddd46ce879fb16"
  }
]