Dergi makalesi Açık Erişim

Data-driven image captioning via salient region discovery

Kilickaya, Mert; Akkus, Burak Kerim; Cakici, Ruket; Erdem, Aykut; Erdem, Erkut; Ikizler-Cinbis, Nazli


JSON

{
  "conceptrecid": "46248", 
  "created": "2021-03-15T21:46:44.448577+00:00", 
  "doi": "10.1049/iet-cvi.2016.0286", 
  "files": [
    {
      "bucket": "c07ca8a9-1add-4680-9f80-ca08e2f8577c", 
      "checksum": "md5:6dea07cf2094b24c43c0bb356282e8c8", 
      "key": "bib-7c78a448-8fcd-44ce-95ce-cf8dbe80af73.txt", 
      "links": {
        "self": "https://aperta.ulakbim.gov.tr/api/files/c07ca8a9-1add-4680-9f80-ca08e2f8577c/bib-7c78a448-8fcd-44ce-95ce-cf8dbe80af73.txt"
      }, 
      "size": 183, 
      "type": "txt"
    }
  ], 
  "id": 46249, 
  "links": {
    "badge": "https://aperta.ulakbim.gov.tr/badge/doi/10.1049/iet-cvi.2016.0286.svg", 
    "bucket": "https://aperta.ulakbim.gov.tr/api/files/c07ca8a9-1add-4680-9f80-ca08e2f8577c", 
    "doi": "https://doi.org/10.1049/iet-cvi.2016.0286", 
    "html": "https://aperta.ulakbim.gov.tr/record/46249", 
    "latest": "https://aperta.ulakbim.gov.tr/api/records/46249", 
    "latest_html": "https://aperta.ulakbim.gov.tr/record/46249"
  }, 
  "metadata": {
    "access_right": "open", 
    "access_right_category": "success", 
    "communities": [
      {
        "id": "tubitak-destekli-proje-yayinlari"
      }
    ], 
    "creators": [
      {
        "affiliation": "Hacettepe Univ, Dept Comp Engn, Ankara, Turkey", 
        "name": "Kilickaya, Mert"
      }, 
      {
        "affiliation": "Middle East Tech Univ, Dept Comp Engn, Ankara, Turkey", 
        "name": "Akkus, Burak Kerim"
      }, 
      {
        "affiliation": "Middle East Tech Univ, Dept Comp Engn, Ankara, Turkey", 
        "name": "Cakici, Ruket"
      }, 
      {
        "affiliation": "Hacettepe Univ, Dept Comp Engn, Ankara, Turkey", 
        "name": "Erdem, Aykut"
      }, 
      {
        "affiliation": "Hacettepe Univ, Dept Comp Engn, Ankara, Turkey", 
        "name": "Erdem, Erkut"
      }, 
      {
        "affiliation": "Hacettepe Univ, Dept Comp Engn, Ankara, Turkey", 
        "name": "Ikizler-Cinbis, Nazli"
      }
    ], 
    "description": "In the past few years, automatically generating descriptions for images has attracted a lot of attention in computer vision and natural language processing research. Among the existing approaches, data-driven methods have been proven to be highly effective. These methods compare the given image against a large set of training images to determine a set of relevant images, then generate a description using the associated captions. In this study, the authors propose to integrate an object-based semantic image representation into a deep features-based retrieval framework to select the relevant images. Moreover, they present a novel phrase selection paradigm and a sentence generation model which depends on a joint analysis of salient regions in the input and retrieved images within a clustering framework. The authors demonstrate the effectiveness of their proposed approach on Flickr8K and Flickr30K benchmark datasets and show that their model gives highly competitive results compared with the state-of-the-art models.", 
    "doi": "10.1049/iet-cvi.2016.0286", 
    "has_grant": false, 
    "journal": {
      "issue": "6", 
      "pages": "398-406", 
      "title": "IET COMPUTER VISION", 
      "volume": "11"
    }, 
    "license": {
      "id": "cc-by"
    }, 
    "publication_date": "2017-01-01", 
    "relations": {
      "version": [
        {
          "count": 1, 
          "index": 0, 
          "is_last": true, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "46249"
          }, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "46248"
          }
        }
      ]
    }, 
    "resource_type": {
      "subtype": "article", 
      "title": "Dergi makalesi", 
      "type": "publication"
    }, 
    "title": "Data-driven image captioning via salient region discovery"
  }, 
  "owners": [
    1
  ], 
  "revision": 1, 
  "stats": {
    "downloads": 8.0, 
    "unique_downloads": 8.0, 
    "unique_views": 38.0, 
    "version_downloads": 8.0, 
    "version_unique_downloads": 8.0, 
    "version_unique_views": 38.0, 
    "version_views": 39.0, 
    "version_volume": 1464.0, 
    "views": 39.0, 
    "volume": 1464.0
  }, 
  "updated": "2021-03-15T21:46:44.491760+00:00"
}
39
8
görüntülenme
indirilme
Görüntülenme 39
İndirme 8
Veri hacmi 1.5 kB
Tekil görüntülenme 38
Tekil indirme 8

Alıntı yap