[
  {
    "Reasonable Miss Rate": 1.76,
    "code_links": [
      {
        "title": "hasanirtiza/Pedestron",
        "url": "https://github.com/hasanirtiza/Pedestron"
      }
    ],
    "date": "2020-03-19",
    "date2": 20200319,
    "model": "Pedestron",
    "paper": {
      "title": "Pedestrian Detection: The Elephant In The Room",
      "url": "https://cknow.io/lib/8485997d9f4247dd"
    },
    "paper_data_uoa": "8485997d9f4247dd"
  },
  {
    "Reasonable Miss Rate": 3.46,
    "code_links": [],
    "date": "2018-04-30",
    "date2": 20180430,
    "model": "FRCNN+FPN-Res50+refined feature map+Crowdhuman",
    "paper": {
      "title": "CrowdHuman: A Benchmark for Detecting Human in a Crowd",
      "url": "https://cknow.io/lib/1bfdee88504a4d4e"
    },
    "paper_data_uoa": "1bfdee88504a4d4e"
  },
  {
    "Reasonable Miss Rate": 3.8,
    "code_links": [],
    "date": "2019-04-05",
    "date2": 20190405,
    "model": "CSP + CityPersons dataset",
    "paper": {
      "title": "Center and Scale Prediction: A Box-free Approach for Pedestrian and Face Detection",
      "url": "https://cknow.io/lib/39e164c71b861131"
    },
    "paper_data_uoa": "39e164c71b861131"
  },
  {
    "Reasonable Miss Rate": 4,
    "code_links": [
      {
        "title": "bailvwangzi/repulsion_loss_ssd",
        "url": "https://github.com/bailvwangzi/repulsion_loss_ssd"
      }
    ],
    "date": "2017-11-21",
    "date2": 20171121,
    "model": "RepLoss + CityPersons dataset",
    "paper": {
      "title": "Repulsion Loss: Detecting Pedestrians in a Crowd",
      "url": "https://cknow.io/lib/6c58b04490e8a102"
    },
    "paper_data_uoa": "6c58b04490e8a102"
  },
  {
    "Reasonable Miss Rate": 4.1,
    "code_links": [],
    "date": "2018-07-23",
    "date2": 20180723,
    "model": "OR-CNN + CityPersons dataset",
    "paper": {
      "title": "Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd",
      "url": "https://cknow.io/lib/7239dd37ee3f49e5"
    },
    "paper_data_uoa": "7239dd37ee3f49e5"
  },
  {
    "Reasonable Miss Rate": 4.5,
    "code_links": [],
    "date": "2019-04-05",
    "date2": 20190405,
    "model": "CSP",
    "paper": {
      "title": "Center and Scale Prediction: A Box-free Approach for Pedestrian and Face Detection",
      "url": "https://cknow.io/lib/39e164c71b861131"
    },
    "paper_data_uoa": "39e164c71b861131"
  },
  {
    "Reasonable Miss Rate": 5,
    "code_links": [
      {
        "title": "bailvwangzi/repulsion_loss_ssd",
        "url": "https://github.com/bailvwangzi/repulsion_loss_ssd"
      }
    ],
    "date": "2017-11-21",
    "date2": 20171121,
    "model": "RepLoss",
    "paper": {
      "title": "Repulsion Loss: Detecting Pedestrians in a Crowd",
      "url": "https://cknow.io/lib/6c58b04490e8a102"
    },
    "paper_data_uoa": "6c58b04490e8a102"
  },
  {
    "Reasonable Miss Rate": 5.5,
    "code_links": [],
    "date": "2017-05-08",
    "date2": 20170508,
    "model": "HyperLearner",
    "paper": {
      "title": "What Can Help Pedestrian Detection?",
      "url": "https://cknow.io/lib/5f898b7b456bf854"
    },
    "paper_data_uoa": "5f898b7b456bf854"
  },
  {
    "Reasonable Miss Rate": 7.3,
    "code_links": [],
    "date": "2016-07-24",
    "date2": 20160724,
    "model": "RPN+BF",
    "paper": {
      "title": "Is Faster R-CNN Doing Well for Pedestrian Detection?",
      "url": "https://cknow.io/lib/596486180e694a36"
    },
    "paper_data_uoa": "596486180e694a36"
  },
  {
    "Reasonable Miss Rate": 7.36,
    "code_links": [
      {
        "title": "Ricardozzf/sdsrcnn",
        "url": "https://github.com/Ricardozzf/sdsrcnn"
      }
    ],
    "date": "2017-06-26",
    "date2": 20170626,
    "model": "SDS-RCNN",
    "paper": {
      "title": "Illuminating Pedestrians via Simultaneous Detection & Segmentation",
      "url": "https://cknow.io/lib/232232604d8b86b9"
    },
    "paper_data_uoa": "232232604d8b86b9"
  },
  {
    "Reasonable Miss Rate": 8.18,
    "code_links": [],
    "date": "2016-10-11",
    "date2": 20161011,
    "model": "F-DNN+SS",
    "paper": {
      "title": "Fused DNN: A deep neural network fusion approach to fast and robust pedestrian detection",
      "url": "https://cknow.io/lib/ba3c6844cd5bed4d"
    },
    "paper_data_uoa": "ba3c6844cd5bed4d"
  },
  {
    "Reasonable Miss Rate": 8.7,
    "code_links": [],
    "date": "2016-07-24",
    "date2": 20160724,
    "model": "FasterRCNN",
    "paper": {
      "title": "Is Faster R-CNN Doing Well for Pedestrian Detection?",
      "url": "https://cknow.io/lib/596486180e694a36"
    },
    "paper_data_uoa": "596486180e694a36"
  },
  {
    "Reasonable Miss Rate": 9.68,
    "code_links": [],
    "date": "2015-10-28",
    "date2": 20151028,
    "model": "SA-FastRCNN",
    "paper": {
      "title": "Scale-aware Fast R-CNN for Pedestrian Detection",
      "url": "https://cknow.io/lib/402587594c8951db"
    },
    "paper_data_uoa": "402587594c8951db"
  },
  {
    "Reasonable Miss Rate": 9.95,
    "code_links": [
      {
        "title": "zhaoweicai/mscnn",
        "url": "https://github.com/zhaoweicai/mscnn"
      }
    ],
    "date": "2016-07-25",
    "date2": 20160725,
    "model": "MS-CNN",
    "paper": {
      "title": "A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection",
      "url": "https://cknow.io/lib/8cebd14c2a92283b"
    },
    "paper_data_uoa": "8cebd14c2a92283b"
  },
  {
    "Reasonable Miss Rate": 11.75,
    "code_links": [],
    "date": "2015-07-19",
    "date2": 20150719,
    "model": "CompACT-Deep",
    "paper": {
      "title": "Learning Complexity-Aware Cascades for Deep Pedestrian Detection",
      "url": "https://cknow.io/lib/1ae7b4c948c4b35f"
    },
    "paper_data_uoa": "1ae7b4c948c4b35f"
  },
  {
    "Reasonable Miss Rate": 12.4,
    "code_links": [
      {
        "title": "iyyun/Part-CNN",
        "url": "https://github.com/iyyun/Part-CNN"
      }
    ],
    "date": "2018-10-01",
    "date2": 20181001,
    "model": "Part-level CNN + saliency and bounding box alignment",
    "paper": {
      "title": "Part-Level Convolutional Neural Networks for Pedestrian Detection Using Saliency and Boundary Box Alignment",
      "url": "https://cknow.io/lib/e47c2a35ee427fcf"
    },
    "paper_data_uoa": "e47c2a35ee427fcf"
  },
  {
    "Reasonable Miss Rate": 17.1,
    "code_links": [],
    "date": "2015-01-23",
    "date2": 20150123,
    "model": "Checkerboards+",
    "paper": {
      "title": "Filtered Channel Features for Pedestrian Detection",
      "url": "https://cknow.io/lib/26a3d731f4128b35"
    },
    "paper_data_uoa": "26a3d731f4128b35"
  },
  {
    "Reasonable Miss Rate": 20.9,
    "code_links": [],
    "date": "2014-11-29",
    "date2": 20141129,
    "model": "TA-CNN",
    "paper": {
      "title": "Pedestrian Detection aided by Deep Learning Semantic Tasks",
      "url": "https://cknow.io/lib/6927b938921ac62f"
    },
    "paper_data_uoa": "6927b938921ac62f"
  },
  {
    "Reasonable Miss Rate": 23.3,
    "code_links": [],
    "date": "2015-01-23",
    "date2": 20150123,
    "model": "AlexNet",
    "paper": {
      "title": "Taking a Deeper Look at Pedestrians",
      "url": "https://cknow.io/lib/48a29ead8c7dc02f"
    },
    "paper_data_uoa": "48a29ead8c7dc02f"
  },
  {
    "Reasonable Miss Rate": 24.8,
    "code_links": [],
    "date": "2014-12-01",
    "date2": 20141201,
    "model": "LDCF",
    "paper": {
      "title": "Local Decorrelation For Improved Pedestrian Detection",
      "url": "https://cknow.io/lib/4788e89382e3b813"
    },
    "paper_data_uoa": "4788e89382e3b813"
  }
]