Semantic Scene Graph Generation Using RDF Model and Deep Learning
Over the last several years, in parallel with the general global advancement in mobile technology and a rise in social media network content consumption, multimedia content production and reproduction has increased exponentially. Therefore, enabled by the rapid recent advancements in deep learning t...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/2/826 |
| _version_ | 1797410650655293440 |
|---|---|
| author | Seongyong Kim Tae Hyeon Jeon Ilsun Rhiu Jinhyun Ahn Dong-Hyuk Im |
| author_facet | Seongyong Kim Tae Hyeon Jeon Ilsun Rhiu Jinhyun Ahn Dong-Hyuk Im |
| author_sort | Seongyong Kim |
| collection | DOAJ |
| description | Over the last several years, in parallel with the general global advancement in mobile technology and a rise in social media network content consumption, multimedia content production and reproduction has increased exponentially. Therefore, enabled by the rapid recent advancements in deep learning technology, research on scene graph generation is being actively conducted to more efficiently search for and classify images desired by users within a large amount of content. This approach lets users accurately find images they are searching for by expressing meaningful information on image content as nodes and edges of a graph. In this study, we propose a scene graph generation method based on using the Resource Description Framework (RDF) model to clarify semantic relations. Furthermore, we also use convolutional neural network (CNN) and recurrent neural network (RNN) deep learning models to generate a scene graph expressed in a controlled vocabulary of the RDF model to understand the relations between image object tags. Finally, we experimentally demonstrate through testing that our proposed technique can express semantic content more effectively than existing approaches. |
| first_indexed | 2024-03-09T04:33:16Z |
| format | Article |
| id | doaj.art-b9dfb73b826443e2bccb67a20a138d30 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T04:33:16Z |
| publishDate | 2021-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-b9dfb73b826443e2bccb67a20a138d302023-12-03T13:33:17ZengMDPI AGApplied Sciences2076-34172021-01-0111282610.3390/app11020826Semantic Scene Graph Generation Using RDF Model and Deep LearningSeongyong Kim0Tae Hyeon Jeon1Ilsun Rhiu2Jinhyun Ahn3Dong-Hyuk Im4Department of Big Data and AI, Hoseo University, Asan 31499, KoreaDepartment of Computer Engineering, Hoseo University, Asan 31499, KoreaDivision of Future Convergence (HCI Science Major), Dongduk Women’s University, Seoul 02748, KoreaDepartment of Management Information Systems, Jeju National University, Jeju 63243, KoreaSchool of Information Convergence, Kwangwoon University, Seoul 01890, KoreaOver the last several years, in parallel with the general global advancement in mobile technology and a rise in social media network content consumption, multimedia content production and reproduction has increased exponentially. Therefore, enabled by the rapid recent advancements in deep learning technology, research on scene graph generation is being actively conducted to more efficiently search for and classify images desired by users within a large amount of content. This approach lets users accurately find images they are searching for by expressing meaningful information on image content as nodes and edges of a graph. In this study, we propose a scene graph generation method based on using the Resource Description Framework (RDF) model to clarify semantic relations. Furthermore, we also use convolutional neural network (CNN) and recurrent neural network (RNN) deep learning models to generate a scene graph expressed in a controlled vocabulary of the RDF model to understand the relations between image object tags. Finally, we experimentally demonstrate through testing that our proposed technique can express semantic content more effectively than existing approaches.https://www.mdpi.com/2076-3417/11/2/826scene graphRDF modeldeep learningimage annotation |
| spellingShingle | Seongyong Kim Tae Hyeon Jeon Ilsun Rhiu Jinhyun Ahn Dong-Hyuk Im Semantic Scene Graph Generation Using RDF Model and Deep Learning Applied Sciences scene graph RDF model deep learning image annotation |
| title | Semantic Scene Graph Generation Using RDF Model and Deep Learning |
| title_full | Semantic Scene Graph Generation Using RDF Model and Deep Learning |
| title_fullStr | Semantic Scene Graph Generation Using RDF Model and Deep Learning |
| title_full_unstemmed | Semantic Scene Graph Generation Using RDF Model and Deep Learning |
| title_short | Semantic Scene Graph Generation Using RDF Model and Deep Learning |
| title_sort | semantic scene graph generation using rdf model and deep learning |
| topic | scene graph RDF model deep learning image annotation |
| url | https://www.mdpi.com/2076-3417/11/2/826 |
| work_keys_str_mv | AT seongyongkim semanticscenegraphgenerationusingrdfmodelanddeeplearning AT taehyeonjeon semanticscenegraphgenerationusingrdfmodelanddeeplearning AT ilsunrhiu semanticscenegraphgenerationusingrdfmodelanddeeplearning AT jinhyunahn semanticscenegraphgenerationusingrdfmodelanddeeplearning AT donghyukim semanticscenegraphgenerationusingrdfmodelanddeeplearning |