{
  "id": "1605.06177",
  "version": "v1",
  "published": "2016-05-20T00:03:42.000Z",
  "updated": "2016-05-20T00:03:42.000Z",
  "title": "Fine-Grained Classification of Pedestrians in Video: Benchmark and State of the Art",
  "authors": [
    "David Hall",
    "Pietro Perona"
  ],
  "comment": "CVPR 2015",
  "categories": [
    "cs.CV"
  ],
  "abstract": "A video dataset that is designed to study fine-grained categorisation of pedestrians is introduced. Pedestrians were recorded \"in-the-wild\" from a moving vehicle. Annotations include bounding boxes, tracks, 14 keypoints with occlusion information and the fine-grained categories of age (5 classes), sex (2 classes), weight (3 classes) and clothing style (4 classes). There are a total of 27,454 bounding box and pose labels across 4222 tracks. This dataset is designed to train and test algorithms for fine-grained categorisation of people, it is also useful for benchmarking tracking, detection and pose estimation of pedestrians. State-of-the-art algorithms for fine-grained classification and pose estimation were tested using the dataset and the results are reported as a useful performance baseline.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2016-05-20T00:03:42.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "fine-grained classification",
      "pedestrians",
      "pose estimation",
      "bounding box",
      "test algorithms"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}