1 Ocak 2021 Dergi makalesi Açık Erişim

Tanisik, Gokhan; Zalluhoglu, Cemil; Ikizler-Cinbis, Nazli

JSON

{
  "conceptrecid": "236235", 
  "created": "2022-10-07T09:37:14.106603+00:00", 
  "doi": "10.1016/j.image.2021.116265", 
  "files": [
    {
      "bucket": "1265d1d8-2e7f-4bd0-8032-adbd4bc51251", 
      "checksum": "md5:b48b07774aa04357226ee646d239ba37", 
      "key": "bib-a1e33c74-21e3-45ae-b066-1978014ff84e.txt", 
      "links": {
        "self": "https://aperta.ulakbim.gov.tr/api/files/1265d1d8-2e7f-4bd0-8032-adbd4bc51251/bib-a1e33c74-21e3-45ae-b066-1978014ff84e.txt"
      }, 
      "size": 198, 
      "type": "txt"
    }
  ], 
  "id": 236236, 
  "links": {
    "badge": "https://aperta.ulakbim.gov.tr/badge/doi/10.1016/j.image.2021.116265.svg", 
    "bucket": "https://aperta.ulakbim.gov.tr/api/files/1265d1d8-2e7f-4bd0-8032-adbd4bc51251", 
    "doi": "https://doi.org/10.1016/j.image.2021.116265", 
    "html": "https://aperta.ulakbim.gov.tr/record/236236", 
    "latest": "https://aperta.ulakbim.gov.tr/api/records/236236", 
    "latest_html": "https://aperta.ulakbim.gov.tr/record/236236"
  }, 
  "metadata": {
    "access_right": "open", 
    "access_right_category": "success", 
    "communities": [
      {
        "id": "tubitak-destekli-proje-yayinlari"
      }
    ], 
    "creators": [
      {
        "affiliation": "Hacettepe Univ, Dept Comp Engn, Ankara, Turkey", 
        "name": "Tanisik, Gokhan"
      }, 
      {
        "affiliation": "Hacettepe Univ, Dept Comp Engn, Ankara, Turkey", 
        "name": "Zalluhoglu, Cemil"
      }, 
      {
        "affiliation": "Hacettepe Univ, Dept Comp Engn, Ankara, Turkey", 
        "name": "Ikizler-Cinbis, Nazli"
      }
    ], 
    "description": "Recognizing human interactions in still images is quite a challenging task since compared to videos, there is only a glimpse of interaction in a single image. This work investigates the role of human poses in recognizing human-human interactions in still images. To this end, a multi-stream convolutional neural network architecture is proposed, which fuses different levels of human pose information to recognize human interactions better. In this context, several pose-based representations are explored. Experimental evaluations in an extended benchmark dataset show that the proposed multi-stream pose Convolutional Neural Network is successful in discriminating a wide range of human-human interactions and human poses when used in conjunction with the overall context provides discriminative cues about human-human interactions.", 
    "doi": "10.1016/j.image.2021.116265", 
    "has_grant": false, 
    "journal": {
      "title": "SIGNAL PROCESSING-IMAGE COMMUNICATION", 
      "volume": "95"
    }, 
    "license": {
      "id": "cc-by"
    }, 
    "publication_date": "2021-01-01", 
    "relations": {
      "version": [
        {
          "count": 1, 
          "index": 0, 
          "is_last": true, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "236236"
          }, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "236235"
          }
        }
      ]
    }, 
    "resource_type": {
      "subtype": "article", 
      "title": "Dergi makalesi", 
      "type": "publication"
    }, 
    "science_branches": [
      "Di\u011fer"
    ], 
    "title": "Multi-stream pose convolutional neural networks for human interaction recognition in images"
  }, 
  "owners": [
    1
  ], 
  "revision": 1, 
  "stats": {
    "downloads": 6.0, 
    "unique_downloads": 6.0, 
    "unique_views": 29.0, 
    "version_downloads": 6.0, 
    "version_unique_downloads": 6.0, 
    "version_unique_views": 28.0, 
    "version_views": 28.0, 
    "version_volume": 1188.0, 
    "views": 29.0, 
    "volume": 1188.0
  }, 
  "updated": "2022-10-07T09:37:14.150112+00:00"
}