Deep learning-based image captioning
A Common problem linking computer vision and natural language processing is the ability to generate an accurate caption for a given image. In this paper, various approaches of image captioning models towards achieving state of the art results are studied. After the various approaches are studied, th...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2019
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/136507 |
| _version_ | 1826120591411773440 |
|---|---|
| author | Chong, Kaydon |
| author2 | Zhang Hanwang |
| author_facet | Zhang Hanwang Chong, Kaydon |
| author_sort | Chong, Kaydon |
| collection | NTU |
| description | A Common problem linking computer vision and natural language processing is the ability to generate an accurate caption for a given image. In this paper, various approaches of image captioning models towards achieving state of the art results are studied. After the various approaches are studied, the best approaches are then extracted and then recombined into a new single model in hopes to achieve a new state of the art model. A comparison of each model’s result will be used to determine the best performing model to be implemented. In this paper, we study the model of 2 different groups that created their image captioning model. They are namely the Google Brain team and the team that won the 2017 Visual Question Answering (VQA) Challenge in 2017. |
| first_indexed | 2024-10-01T05:18:57Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/136507 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T05:18:57Z |
| publishDate | 2019 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1365072019-12-20T07:22:47Z Deep learning-based image captioning Chong, Kaydon Zhang Hanwang School of Computer Science and Engineering hanwangzhang@ntu.edu.sg Engineering Engineering::Computer science and engineering A Common problem linking computer vision and natural language processing is the ability to generate an accurate caption for a given image. In this paper, various approaches of image captioning models towards achieving state of the art results are studied. After the various approaches are studied, the best approaches are then extracted and then recombined into a new single model in hopes to achieve a new state of the art model. A comparison of each model’s result will be used to determine the best performing model to be implemented. In this paper, we study the model of 2 different groups that created their image captioning model. They are namely the Google Brain team and the team that won the 2017 Visual Question Answering (VQA) Challenge in 2017. Bachelor of Engineering (Computer Science) 2019-12-20T07:22:47Z 2019-12-20T07:22:47Z 2019 Final Year Project (FYP) https://hdl.handle.net/10356/136507 en application/pdf Nanyang Technological University |
| spellingShingle | Engineering Engineering::Computer science and engineering Chong, Kaydon Deep learning-based image captioning |
| title | Deep learning-based image captioning |
| title_full | Deep learning-based image captioning |
| title_fullStr | Deep learning-based image captioning |
| title_full_unstemmed | Deep learning-based image captioning |
| title_short | Deep learning-based image captioning |
| title_sort | deep learning based image captioning |
| topic | Engineering Engineering::Computer science and engineering |
| url | https://hdl.handle.net/10356/136507 |
| work_keys_str_mv | AT chongkaydon deeplearningbasedimagecaptioning |