A Scientometric Visualization Analysis of Image Captioning Research From 2010 to 2020

Image captioning has gradually gained attention in the field of artificial intelligence and become an interesting and challenging task for image understanding. It needs to identify important objects in images, extract attributes, tell relationships, and help the machine generate human-like descripti...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Wenxuan Liu, Huayi Wu, Kai Hu, Qing Luo, Xiaoqiang Cheng
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Image captioning image description generation scientometric analysis visualization Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/a82aadf5d8ff4318ad165d5237f3c318
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:a82aadf5d8ff4318ad165d5237f3c318
record_format	dspace
spelling	oai:doaj.org-article:a82aadf5d8ff4318ad165d5237f3c3182021-12-02T00:00:11ZA Scientometric Visualization Analysis of Image Captioning Research From 2010 to 20202169-353610.1109/ACCESS.2021.3129782https://doaj.org/article/a82aadf5d8ff4318ad165d5237f3c3182021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9623457/https://doaj.org/toc/2169-3536Image captioning has gradually gained attention in the field of artificial intelligence and become an interesting and challenging task for image understanding. It needs to identify important objects in images, extract attributes, tell relationships, and help the machine generate human-like descriptions. Recent works in deep neural networks have greatly improved the performance of image caption models. However, machines are still unable to imitate the way humans think, talk and communicate, so image captioning remains an ongoing task. It is thus very important to keep up with the latest research and results in the field of image captioning whereas publications on this topic are numerous. Our work aims to help researchers to have a macro-level understanding of image captioning from four aspects: spatial-temporal distribution characteristics, collaborative networks, trends in subject research, and historical evolutionary path. We employ scientometric visualization methods to achieve this goal. The results show that China has published the largest amount of publications in image captioning, but the United States has the greatest impact on research in this area. Besides, thirteen academic groups are identified in the field of image description, with institutions such as Microsoft, Google, Australian National University, and Georgia Institute of Technology being the most prominent research institutions. Meanwhile, we find that evaluation methods, datasets, novel image captioning models based on generative adversarial networks, reinforcement learning, and Transformer, as well as remote sensing image captioning, are the new research trends. Lastly, we conclude that image captioning research has gone through three major development stages from 2010 to 2020, and on this basis, we propose a more comprehensive taxonomy of image captioning.Wenxuan LiuHuayi WuKai HuQing LuoXiaoqiang ChengIEEEarticleImage captioningimage description generationscientometric analysisvisualizationElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 156799-156817 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Image captioning image description generation scientometric analysis visualization Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Image captioning image description generation scientometric analysis visualization Electrical engineering. Electronics. Nuclear engineering TK1-9971 Wenxuan Liu Huayi Wu Kai Hu Qing Luo Xiaoqiang Cheng A Scientometric Visualization Analysis of Image Captioning Research From 2010 to 2020
description	Image captioning has gradually gained attention in the field of artificial intelligence and become an interesting and challenging task for image understanding. It needs to identify important objects in images, extract attributes, tell relationships, and help the machine generate human-like descriptions. Recent works in deep neural networks have greatly improved the performance of image caption models. However, machines are still unable to imitate the way humans think, talk and communicate, so image captioning remains an ongoing task. It is thus very important to keep up with the latest research and results in the field of image captioning whereas publications on this topic are numerous. Our work aims to help researchers to have a macro-level understanding of image captioning from four aspects: spatial-temporal distribution characteristics, collaborative networks, trends in subject research, and historical evolutionary path. We employ scientometric visualization methods to achieve this goal. The results show that China has published the largest amount of publications in image captioning, but the United States has the greatest impact on research in this area. Besides, thirteen academic groups are identified in the field of image description, with institutions such as Microsoft, Google, Australian National University, and Georgia Institute of Technology being the most prominent research institutions. Meanwhile, we find that evaluation methods, datasets, novel image captioning models based on generative adversarial networks, reinforcement learning, and Transformer, as well as remote sensing image captioning, are the new research trends. Lastly, we conclude that image captioning research has gone through three major development stages from 2010 to 2020, and on this basis, we propose a more comprehensive taxonomy of image captioning.
format	article
author	Wenxuan Liu Huayi Wu Kai Hu Qing Luo Xiaoqiang Cheng
author_facet	Wenxuan Liu Huayi Wu Kai Hu Qing Luo Xiaoqiang Cheng
author_sort	Wenxuan Liu
title	A Scientometric Visualization Analysis of Image Captioning Research From 2010 to 2020
title_short	A Scientometric Visualization Analysis of Image Captioning Research From 2010 to 2020
title_full	A Scientometric Visualization Analysis of Image Captioning Research From 2010 to 2020
title_fullStr	A Scientometric Visualization Analysis of Image Captioning Research From 2010 to 2020
title_full_unstemmed	A Scientometric Visualization Analysis of Image Captioning Research From 2010 to 2020
title_sort	scientometric visualization analysis of image captioning research from 2010 to 2020
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/a82aadf5d8ff4318ad165d5237f3c318
work_keys_str_mv	AT wenxuanliu ascientometricvisualizationanalysisofimagecaptioningresearchfrom2010to2020 AT huayiwu ascientometricvisualizationanalysisofimagecaptioningresearchfrom2010to2020 AT kaihu ascientometricvisualizationanalysisofimagecaptioningresearchfrom2010to2020 AT qingluo ascientometricvisualizationanalysisofimagecaptioningresearchfrom2010to2020 AT xiaoqiangcheng ascientometricvisualizationanalysisofimagecaptioningresearchfrom2010to2020 AT wenxuanliu scientometricvisualizationanalysisofimagecaptioningresearchfrom2010to2020 AT huayiwu scientometricvisualizationanalysisofimagecaptioningresearchfrom2010to2020 AT kaihu scientometricvisualizationanalysisofimagecaptioningresearchfrom2010to2020 AT qingluo scientometricvisualizationanalysisofimagecaptioningresearchfrom2010to2020 AT xiaoqiangcheng scientometricvisualizationanalysisofimagecaptioningresearchfrom2010to2020
_version_	1718404005896388608

A Scientometric Visualization Analysis of Image Captioning Research From 2010 to 2020

Ejemplares similares