{
  "id": "1904.09882",
  "version": "v1",
  "published": "2019-04-22T13:58:49.000Z",
  "updated": "2019-04-22T13:58:49.000Z",
  "title": "You2Me: Inferring Body Pose in Egocentric Video via First and Second Person Interactions",
  "authors": [
    "Evonne Ng",
    "Donglai Xiang",
    "Hanbyul Joo",
    "Kristen Grauman"
  ],
  "categories": [
    "cs.CV"
  ],
  "abstract": "The body pose of a person wearing a camera is of great interest for applications in augmented reality, healthcare, and robotics, yet much of the person's body is out of view for a typical wearable camera. We propose a learning-based approach to estimate the camera wearer's 3D body pose from egocentric video sequences. Our key insight is to leverage interactions with another person---whose body pose we can directly observe---as a signal inherently linked to the body pose of the first-person subject. We show that since interactions between individuals often induce a well-ordered series of back-and-forth responses, it is possible to learn a temporal model of the interlinked poses even though one party is largely out of view. We demonstrate our idea on a variety of domains with dyadic interaction and show the substantial impact on egocentric body pose estimation, which improves the state of the art. Video results are available at http://vision.cs.utexas.edu/projects/you2me/",
  "revisions": [
    {
      "version": "v1",
      "updated": "2019-04-22T13:58:49.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "second person interactions",
      "inferring body pose",
      "camera wearers 3d body pose",
      "egocentric body pose estimation",
      "egocentric video sequences"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}