Dergi makalesi Açık Erişim
Kilickaya, Mert; Akkus, Burak Kerim; Cakici, Ruket; Erdem, Aykut; Erdem, Erkut; Ikizler-Cinbis, Nazli
{ "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" }
Görüntülenme | 39 |
İndirme | 8 |
Veri hacmi | 1.5 kB |
Tekil görüntülenme | 38 |
Tekil indirme | 8 |