Features to Text: A Comprehensive Survey of Deep Learning on Semantic Segmentation and Image Captioning
With the emergence of deep learning, computer vision has witnessed extensive advancement and has seen immense applications in multiple domains. Specifically, image captioning has become an attractive focal direction for most machine learning experts, which includes the prerequisite of object identif...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2021/5538927 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832552805787762688 |
|---|---|
| author | Ariyo Oluwasammi Muhammad Umar Aftab Zhiguang Qin Son Tung Ngo Thang Van Doan Son Ba Nguyen Son Hoang Nguyen Giang Hoang Nguyen |
| author_facet | Ariyo Oluwasammi Muhammad Umar Aftab Zhiguang Qin Son Tung Ngo Thang Van Doan Son Ba Nguyen Son Hoang Nguyen Giang Hoang Nguyen |
| author_sort | Ariyo Oluwasammi |
| collection | DOAJ |
| description | With the emergence of deep learning, computer vision has witnessed extensive advancement and has seen immense applications in multiple domains. Specifically, image captioning has become an attractive focal direction for most machine learning experts, which includes the prerequisite of object identification, location, and semantic understanding. In this paper, semantic segmentation and image captioning are comprehensively investigated based on traditional and state-of-the-art methodologies. In this survey, we deliberate on the use of deep learning techniques on the segmentation analysis of both 2D and 3D images using a fully convolutional network and other high-level hierarchical feature extraction methods. First, each domain’s preliminaries and concept are described, and then semantic segmentation is discussed alongside its relevant features, available datasets, and evaluation criteria. Also, the semantic information capturing of objects and their attributes is presented in relation to their annotation generation. Finally, analysis of the existing methods, their contributions, and relevance are highlighted, informing the importance of these methods and illuminating a possible research continuation for the application of semantic image segmentation and image captioning approaches. |
| format | Article |
| id | doaj-art-bbf0293988b0454181d97d3a1c9fae6e |
| institution | Kabale University |
| issn | 1076-2787 1099-0526 |
| language | English |
| publishDate | 2021-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-bbf0293988b0454181d97d3a1c9fae6e2025-02-03T05:57:50ZengWileyComplexity1076-27871099-05262021-01-01202110.1155/2021/55389275538927Features to Text: A Comprehensive Survey of Deep Learning on Semantic Segmentation and Image CaptioningAriyo Oluwasammi0Muhammad Umar Aftab1Zhiguang Qin2Son Tung Ngo3Thang Van Doan4Son Ba Nguyen5Son Hoang Nguyen6Giang Hoang Nguyen7School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610054, ChinaDepartment of Computer Science, National University of Computer and Emerging Sciences, Islamabad, Chiniot-Faisalabad Campus, Chiniot 35400, PakistanSchool of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610054, ChinaICT Department, FPT University, Hanoi 10000, VietnamICT Department, FPT University, Hanoi 10000, VietnamICT Department, FPT University, Hanoi 10000, VietnamICT Department, FPT University, Hanoi 10000, VietnamICT Department, FPT University, Hanoi 10000, VietnamWith the emergence of deep learning, computer vision has witnessed extensive advancement and has seen immense applications in multiple domains. Specifically, image captioning has become an attractive focal direction for most machine learning experts, which includes the prerequisite of object identification, location, and semantic understanding. In this paper, semantic segmentation and image captioning are comprehensively investigated based on traditional and state-of-the-art methodologies. In this survey, we deliberate on the use of deep learning techniques on the segmentation analysis of both 2D and 3D images using a fully convolutional network and other high-level hierarchical feature extraction methods. First, each domain’s preliminaries and concept are described, and then semantic segmentation is discussed alongside its relevant features, available datasets, and evaluation criteria. Also, the semantic information capturing of objects and their attributes is presented in relation to their annotation generation. Finally, analysis of the existing methods, their contributions, and relevance are highlighted, informing the importance of these methods and illuminating a possible research continuation for the application of semantic image segmentation and image captioning approaches.http://dx.doi.org/10.1155/2021/5538927 |
| spellingShingle | Ariyo Oluwasammi Muhammad Umar Aftab Zhiguang Qin Son Tung Ngo Thang Van Doan Son Ba Nguyen Son Hoang Nguyen Giang Hoang Nguyen Features to Text: A Comprehensive Survey of Deep Learning on Semantic Segmentation and Image Captioning Complexity |
| title | Features to Text: A Comprehensive Survey of Deep Learning on Semantic Segmentation and Image Captioning |
| title_full | Features to Text: A Comprehensive Survey of Deep Learning on Semantic Segmentation and Image Captioning |
| title_fullStr | Features to Text: A Comprehensive Survey of Deep Learning on Semantic Segmentation and Image Captioning |
| title_full_unstemmed | Features to Text: A Comprehensive Survey of Deep Learning on Semantic Segmentation and Image Captioning |
| title_short | Features to Text: A Comprehensive Survey of Deep Learning on Semantic Segmentation and Image Captioning |
| title_sort | features to text a comprehensive survey of deep learning on semantic segmentation and image captioning |
| url | http://dx.doi.org/10.1155/2021/5538927 |
| work_keys_str_mv | AT ariyooluwasammi featurestotextacomprehensivesurveyofdeeplearningonsemanticsegmentationandimagecaptioning AT muhammadumaraftab featurestotextacomprehensivesurveyofdeeplearningonsemanticsegmentationandimagecaptioning AT zhiguangqin featurestotextacomprehensivesurveyofdeeplearningonsemanticsegmentationandimagecaptioning AT sontungngo featurestotextacomprehensivesurveyofdeeplearningonsemanticsegmentationandimagecaptioning AT thangvandoan featurestotextacomprehensivesurveyofdeeplearningonsemanticsegmentationandimagecaptioning AT sonbanguyen featurestotextacomprehensivesurveyofdeeplearningonsemanticsegmentationandimagecaptioning AT sonhoangnguyen featurestotextacomprehensivesurveyofdeeplearningonsemanticsegmentationandimagecaptioning AT gianghoangnguyen featurestotextacomprehensivesurveyofdeeplearningonsemanticsegmentationandimagecaptioning |